检查python版本

!python --version

结果：

# Python 3.12.11

情感分析任务

from transformers import pipeline

# 仅指定任务时，使用默认模型（不推荐）
pipe = pipeline("sentiment-analysis")
pipe("今儿上海可真冷啊")

结果：

No model was supplied, defaulted to distilbert/distilbert-base-uncased-finetuned-sst-2-english and revision 714eb0f (https://huggingface.co/distilbert/distilbert-base-uncased-finetuned-sst-2-english).
Using a pipeline without specifying a model name and revision in production is not recommended.
Device set to use cuda:0
[{'label': 'NEGATIVE', 'score': 0.8957213759422302}]

pipe("我觉得这家店蒜泥白肉的味道一般")

结果：

[{'label': 'NEGATIVE', 'score': 0.9238728880882263}]

# 默认使用的模型 distilbert-base-uncased-finetuned-sst-2-english
# 并未针对中文做太多训练，中文的文本分类任务表现未必满意
pipe("你学东西真的好快，理论课一讲就明白了")

结果

[{'label': 'NEGATIVE', 'score': 0.8578684329986572}]

# 替换为英文后，文本分类任务的表现立刻改善
pipe("You learn things really quickly. You understand the theory class as soon as it is taught.")

结果：

[{'label': 'POSITIVE', 'score': 0.9961802959442139}]

pipe("Today Shanghai is really cold.")

结果：

[{'label': 'NEGATIVE', 'score': 0.9995032548904419}]

text_list = [
    "Today Shanghai is really cold.",
    "I think the taste of the garlic mashed pork in this store is average.",
    "You learn things really quickly. You understand the theory class as soon as it is taught."
]

pipe(text_list)

结果：

[{'label': 'NEGATIVE', 'score': 0.9995032548904419},
 {'label': 'NEGATIVE', 'score': 0.9984821677207947},
 {'label': 'POSITIVE', 'score': 0.9961802959442139}]

命令实体识别任务（NER）

from transformers import pipeline

classifier = pipeline(task="ner")

结果：

No model was supplied, defaulted to dbmdz/bert-large-cased-finetuned-conll03-english and revision 4c53496 (https://huggingface.co/dbmdz/bert-large-cased-finetuned-conll03-english).
Using a pipeline without specifying a model name and revision in production is not recommended.
config.json: 100%
 998/998 [00:00<00:00, 77.5kB/s]
model.safetensors: 100%
 1.33G/1.33G [00:27<00:00, 70.5MB/s]
Some weights of the model checkpoint at dbmdz/bert-large-cased-finetuned-conll03-english were not used when initializing BertForTokenClassification: ['bert.pooler.dense.bias', 'bert.pooler.dense.weight']
- This IS expected if you are initializing BertForTokenClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing BertForTokenClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
tokenizer_config.json: 100%
 60.0/60.0 [00:00<00:00, 7.62kB/s]
vocab.txt: 
 213k/? [00:00<00:00, 10.7MB/s]
Device set to use cuda:0

preds = classifier("Hugging Face is a French company based in New York City.")
preds = [
    {
        "entity": pred["entity"],
        "score": round(pred["score"], 4),
        "index": pred["index"],
        "word": pred["word"],
        "start": pred["start"],
        "end": pred["end"],
    }
    for pred in preds
]
print(*preds, sep="\n")

结果：

{'entity': 'I-ORG', 'score': np.float32(0.9968), 'index': 1, 'word': 'Hu', 'start': 0, 'end': 2}
{'entity': 'I-ORG', 'score': np.float32(0.9293), 'index': 2, 'word': '##gging', 'start': 2, 'end': 7}
{'entity': 'I-ORG', 'score': np.float32(0.9763), 'index': 3, 'word': 'Face', 'start': 8, 'end': 12}
{'entity': 'I-MISC', 'score': np.float32(0.9983), 'index': 6, 'word': 'French', 'start': 18, 'end': 24}
{'entity': 'I-LOC', 'score': np.float32(0.999), 'index': 10, 'word': 'New', 'start': 42, 'end': 45}
{'entity': 'I-LOC', 'score': np.float32(0.9987), 'index': 11, 'word': 'York', 'start': 46, 'end': 50}
{'entity': 'I-LOC', 'score': np.float32(0.9992), 'index': 12, 'word': 'City', 'start': 51, 'end': 55}

classifier = pipeline(task="ner", grouped_entities=True)
classifier("Hugging Face is a French company based in New York City.")

结果：

No model was supplied, defaulted to dbmdz/bert-large-cased-finetuned-conll03-english and revision 4c53496 (https://huggingface.co/dbmdz/bert-large-cased-finetuned-conll03-english).
Using a pipeline without specifying a model name and revision in production is not recommended.
Some weights of the model checkpoint at dbmdz/bert-large-cased-finetuned-conll03-english were not used when initializing BertForTokenClassification: ['bert.pooler.dense.bias', 'bert.pooler.dense.weight']
- This IS expected if you are initializing BertForTokenClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing BertForTokenClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Device set to use cuda:0
/usr/local/lib/python3.12/dist-packages/transformers/pipelines/token_classification.py:186: UserWarning: `grouped_entities` is deprecated and will be removed in version v5.0.0, defaulted to `aggregation_strategy="AggregationStrategy.SIMPLE"` instead.
  warnings.warn(
[{'entity_group': 'ORG',
  'score': np.float32(0.9674639),
  'word': 'Hugging Face',
  'start': 0,
  'end': 12},
 {'entity_group': 'MISC',
  'score': np.float32(0.99828726),
  'word': 'French',
  'start': 18,
  'end': 24},
 {'entity_group': 'LOC',
  'score': np.float32(0.99896103),
  'word': 'New York City',
  'start': 42,
  'end': 55}]

问答任务

from transformers import pipeline

question_answerer = pipeline(task="question-answering")

结果：

No model was supplied, defaulted to distilbert/distilbert-base-cased-distilled-squad and revision 564e9b5 (https://huggingface.co/distilbert/distilbert-base-cased-distilled-squad).
Using a pipeline without specifying a model name and revision in production is not recommended.
config.json: 100%
 473/473 [00:00<00:00, 11.3kB/s]
model.safetensors: 100%
 261M/261M [00:03<00:00, 107MB/s]
tokenizer_config.json: 100%
 49.0/49.0 [00:00<00:00, 1.36kB/s]
vocab.txt: 
 213k/? [00:00<00:00, 2.95MB/s]
tokenizer.json: 
 436k/? [00:00<00:00, 2.22MB/s]
Fetching 0 files: 
 0/0 [00:00<?, ?it/s]
Fetching 1 files: 100%
 1/1 [00:00<00:00, 15.78it/s]
Fetching 0 files: 
 0/0 [00:00<?, ?it/s]
Device set to use cuda:0

preds = question_answerer(
    question="What is the name of the repository?",
    context="The name of the repository is huggingface/transformers",
)
print(
    f"score: {round(preds['score'], 4)}, start: {preds['start']}, end: {preds['end']}, answer: {preds['answer']}"
)

结果：

score: 0.9333, start: 30, end: 54, answer: huggingface/transformers

preds = question_answerer(
    question="What is the capital of China?",
    context="On 1 October 1949, CCP Chairman Mao Zedong formally proclaimed the People's Republic of China in Tiananmen Square, Beijing.",
)
print(
    f"score: {round(preds['score'], 4)}, start: {preds['start']}, end: {preds['end']}, answer: {preds['answer']}"
)

结果：

score: 0.9458, start: 115, end: 122, answer: Beijing

摘要任务

from transformers import pipeline

summarizer = pipeline(task="summarization",
                      model="t5-base",
                      min_length=8,
                      max_length=32,
)

结果：

Device set to use cuda:0

summarizer(
    """
    In this work, we presented the Transformer, the first sequence transduction model based entirely on attention,
    replacing the recurrent layers most commonly used in encoder-decoder architectures with multi-headed self-attention.
    For translation tasks, the Transformer can be trained significantly faster than architectures based on recurrent or convolutional layers.
    On both WMT 2014 English-to-German and WMT 2014 English-to-French translation tasks, we achieve a new state of the art.
    In the former task our best model outperforms even all previously reported ensembles.
    """
)

结果：

Your max_length is set to 200, but your input_length is only 128. Since this is a summarization task, where outputs shorter than the input are typically wanted, you might consider decreasing max_length manually, e.g. summarizer('...', max_length=64)
[{'summary_text': 'the Transformer is the first sequence transduction model based entirely on attention . it replaces recurrent layers commonly used in encoder-decoder architectures with multi-headed self-attention . for translation tasks, the Transformer can be trained significantly faster than architectures based on convolutional layers .'}]

summarizer(
    '''
    Large language models (LLM) are very large deep learning models that are pre-trained on vast amounts of data.
    The underlying transformer is a set of neural networks that consist of an encoder and a decoder with self-attention capabilities.
    The encoder and decoder extract meanings from a sequence of text and understand the relationships between words and phrases in it.
    Transformer LLMs are capable of unsupervised training, although a more precise explanation is that transformers perform self-learning.
    It is through this process that transformers learn to understand basic grammar, languages, and knowledge.
    Unlike earlier recurrent neural networks (RNN) that sequentially process inputs, transformers process entire sequences in parallel.
    This allows the data scientists to use GPUs for training transformer-based LLMs, significantly reducing the training time.
    '''
)

结果：

Your max_length is set to 200, but your input_length is only 182. Since this is a summarization task, where outputs shorter than the input are typically wanted, you might consider decreasing max_length manually, e.g. summarizer('...', max_length=91)
[{'summary_text': 'large language models (LLMs) are very large deep learning models pre-trained on vast amounts of data . transformers are capable of unsupervised training, although a more precise explanation is that they perform self-learning . data scientists can use GPUs for training transformer-based LLMs, significantly reducing the training time .'}]

音频分类任务

from transformers import pipeline

classifier = pipeline(task="audio-classification", model="superb/hubert-base-superb-er")

结果：

config.json: 
 1.66k/? [00:00<00:00, 158kB/s]
pytorch_model.bin: 100%
 378M/378M [00:03<00:00, 143MB/s]
Fetching 1 files: 100%
 1/1 [00:00<00:00,  6.05it/s]
preprocessor_config.json: 100%
 213/213 [00:00<00:00, 11.1kB/s]
Device set to use cuda:0

# 使用 Hugging Face Datasets 上的测试文件
preds = classifier("https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/mlk.flac")
preds = [{"score": round(pred["score"], 4), "label": pred["label"]} for pred in preds]
preds

结果：

[{'score': 0.4532, 'label': 'hap'},
 {'score': 0.3622, 'label': 'sad'},
 {'score': 0.0943, 'label': 'neu'},
 {'score': 0.0903, 'label': 'ang'}]

# 使用本地的音频文件做测试
preds = classifier("data/audio/mlk.flac")
preds = [{"score": round(pred["score"], 4), "label": pred["label"]} for pred in preds]
preds

结果：

[{'score': 0.4532, 'label': 'hap'},
 {'score': 0.3622, 'label': 'sad'},
 {'score': 0.0943, 'label': 'neu'},
 {'score': 0.0903, 'label': 'ang'}]

语音识别任务

from transformers import pipeline
# 使用 `model` 参数指定模型
transcriber = pipeline(task="automatic-speech-recognition", model="openai/whisper-small")

结果：

config.json: 
 1.97k/? [00:00<00:00, 40.3kB/s]
model.safetensors: 100%
 967M/967M [01:10<00:00, 11.0MB/s]
generation_config.json: 
 3.87k/? [00:00<00:00, 404kB/s]
tokenizer_config.json: 
 283k/? [00:00<00:00, 26.3MB/s]
vocab.json: 
 836k/? [00:00<00:00, 23.7MB/s]
tokenizer.json: 
 2.48M/? [00:00<00:00, 80.2MB/s]
merges.txt: 
 494k/? [00:00<00:00, 27.8MB/s]
normalizer.json: 
 52.7k/? [00:00<00:00, 4.98MB/s]
added_tokens.json: 
 34.6k/? [00:00<00:00, 3.19MB/s]
special_tokens_map.json: 
 2.19k/? [00:00<00:00, 213kB/s]
Fetching 1 files: 100%
 1/1 [00:00<00:00,  5.83it/s]
preprocessor_config.json: 
 185k/? [00:00<00:00, 14.6MB/s]
Device set to use cuda:0

text = transcriber("data/audio/mlk.flac")
text

结果：

`return_token_timestamps` is deprecated for WhisperFeatureExtractor and will be removed in Transformers v5. Use `return_attention_mask` instead, as the number of frames can be inferred from it.
Using custom `forced_decoder_ids` from the (generation) config. This is deprecated in favor of the `task` and `language` flags/config options.
Transcription using a multilingual Whisper will default to language detection followed by transcription instead of translation to English. This might be a breaking change for your use case. If you want to instead always translate your audio to English, make sure to pass `language='en'`. See https://github.com/huggingface/transformers/pull/28687 for more details.
{'text': ' I have a dream that one day this nation will rise up and live out the true meaning of its creed.'}

图像识别任务

from transformers import pipeline

classifier = pipeline(task="image-classification")

结果：

No model was supplied, defaulted to google/vit-base-patch16-224 and revision 3f49326 (https://huggingface.co/google/vit-base-patch16-224).
Using a pipeline without specifying a model name and revision in production is not recommended.
/usr/local/lib/python3.12/dist-packages/huggingface_hub/utils/_auth.py:94: UserWarning: 
The secret `HF_TOKEN` does not exist in your Colab secrets.
To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.
You will be able to reuse this secret in all of your notebooks.
Please note that authentication is recommended but still optional to access public models or datasets.
  warnings.warn(
config.json: 
 69.7k/? [00:00<00:00, 6.10MB/s]
model.safetensors: 100%
 346M/346M [00:07<00:00, 55.1MB/s]
Fetching 1 files: 100%
 1/1 [00:00<00:00,  6.76it/s]
preprocessor_config.json: 100%
 160/160 [00:00<00:00, 20.6kB/s]
Fast image processor class <class 'transformers.models.vit.image_processing_vit_fast.ViTImageProcessorFast'> is available for this model. Using slow image processor class. To use the fast image processor class set `use_fast=True`.
Fetching 1 files: 100%
 1/1 [00:00<00:00, 113.94it/s]
Device set to use cuda:0

preds = classifier(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
)
preds = [{"score": round(pred["score"], 4), "label": pred["label"]} for pred in preds]
print(*preds, sep="\n")

结果：

{'score': 0.4335, 'label': 'lynx, catamount'}
{'score': 0.0348, 'label': 'cougar, puma, catamount, mountain lion, painter, panther, Felis concolor'}
{'score': 0.0324, 'label': 'snow leopard, ounce, Panthera uncia'}
{'score': 0.0239, 'label': 'Egyptian cat'}
{'score': 0.0229, 'label': 'tiger cat'}

from google.colab import drive
drive.mount('/content/drive')
# 使用本地图片（狼猫）
preds = classifier(
    "drive/MyDrive/data/image/cat-chonk.jpeg"
)
preds = [{"score": round(pred["score"], 4), "label": pred["label"]} for pred in preds]
print(*preds, sep="\n")

结果：

Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount("/content/drive", force_remount=True).
{'score': 0.4335, 'label': 'lynx, catamount'}
{'score': 0.0348, 'label': 'cougar, puma, catamount, mountain lion, painter, panther, Felis concolor'}
{'score': 0.0324, 'label': 'snow leopard, ounce, Panthera uncia'}
{'score': 0.0239, 'label': 'Egyptian cat'}
{'score': 0.0229, 'label': 'tiger cat'}

# 使用本地图片（熊猫）
preds = classifier(
    "drive/MyDrive/data/image/panda.jpg"
)
preds = [{"score": round(pred["score"], 4), "label": pred["label"]} for pred in preds]
print(*preds, sep="\n")

结果：

{'score': 0.9962, 'label': 'giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca'}
{'score': 0.0018, 'label': 'lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens'}
{'score': 0.0002, 'label': 'ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus'}
{'score': 0.0001, 'label': 'sloth bear, Melursus ursinus, Ursus ursinus'}
{'score': 0.0001, 'label': 'brown bear, bruin, Ursus arctos'}

图像目标检测任务

from transformers import pipeline

detector = pipeline(task="object-detection")

结果：

 No model was supplied, defaulted to facebook/detr-resnet-50 and revision 1d5f47b (https://huggingface.co/facebook/detr-resnet-50).
Using a pipeline without specifying a model name and revision in production is not recommended.
config.json:  4.59k/? [00:00<00:00, 266kB/s]model.safetensors: 100% 167M/167M [00:02<00:00, 168MB/s]model.safetensors: 100% 102M/102M [00:00<00:00, 209MB/s]/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.0.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.0.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.0.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.0.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.0.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.0.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.0.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.0.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.0.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.0.downsample.0.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.0.downsample.1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.0.downsample.1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.1.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.1.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.1.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.1.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.1.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.1.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.1.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.1.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.1.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.2.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.2.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.2.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.2.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.2.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.2.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.2.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.2.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer1.2.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.0.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.0.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.0.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.0.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.0.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.0.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.0.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.0.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.0.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.0.downsample.0.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.0.downsample.1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.0.downsample.1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.1.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.1.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.1.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.1.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.1.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.1.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.1.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.1.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.1.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.2.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.2.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.2.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.2.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.2.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.2.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.2.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.2.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.2.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.3.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.3.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.3.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.3.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.3.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.3.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.3.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.3.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer2.3.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.0.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.0.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.0.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.0.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.0.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.0.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.0.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.0.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.0.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.0.downsample.0.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.0.downsample.1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.0.downsample.1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.1.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.1.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.1.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.1.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.1.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.1.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.1.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.1.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.1.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.2.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.2.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.2.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.2.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.2.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.2.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.2.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.2.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.2.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.3.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.3.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.3.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.3.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.3.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.3.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.3.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.3.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.3.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.4.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.4.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.4.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.4.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.4.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.4.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.4.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.4.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.4.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.5.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.5.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.5.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.5.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.5.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.5.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.5.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.5.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer3.5.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.0.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.0.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.0.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.0.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.0.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.0.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.0.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.0.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.0.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.0.downsample.0.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.0.downsample.1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.0.downsample.1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.1.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.1.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.1.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.1.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.1.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.1.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.1.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.1.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.1.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.2.conv1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.2.bn1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.2.bn1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.2.conv2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.2.bn2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.2.bn2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.2.conv3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.2.bn3.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py:2441: UserWarning: for layer4.2.bn3.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(
Some weights of the model checkpoint at facebook/detr-resnet-50 were not used when initializing DetrForObjectDetection: ['model.backbone.conv_encoder.model.layer1.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer2.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer3.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer4.0.downsample.1.num_batches_tracked']
- This IS expected if you are initializing DetrForObjectDetection from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing DetrForObjectDetection from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Fetching 1 files: 100% 1/1 [00:00<00:00,  6.36it/s]preprocessor_config.json: 100% 290/290 [00:00<00:00, 18.5kB/s]Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Device set to use cuda:0

preds = detector(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
)
preds = [{"score": round(pred["score"], 4), "label": pred["label"], "box": pred["box"]} for pred in preds]
preds

结果：

[{'score': 0.9864,
  'label': 'cat',
  'box': {'xmin': 178, 'ymin': 154, 'xmax': 882, 'ymax': 598}}]

preds = detector(
    "drive/MyDrive/data/image/cat_dog.jpg"
)
preds = [{"score": round(pred["score"], 4), "label": pred["label"], "box": pred["box"]} for pred in preds]
preds

结果：

[{'score': 0.9985,
  'label': 'cat',
  'box': {'xmin': 78, 'ymin': 57, 'xmax': 309, 'ymax': 371}},
 {'score': 0.989,
  'label': 'dog',
  'box': {'xmin': 279, 'ymin': 20, 'xmax': 482, 'ymax': 416}}]

总结

以后可以利用hugging face 的transformers的api，轻松调用开源大模型了。这位极客时间的老师讲得是真的好。