3 · 可选：固定模型，重算四个候选条件 · 实现代码

RUN_CLIP=False  # 已下载固定权重后改 True；默认只核对准备与预处理。
if RUN_CLIP:
    from transformers import CLIPModel, CLIPProcessor, CLIPImageProcessor, AutoTokenizer
    from PIL import Image
    REVISION='3d74acf9a28c67741b2f4f2ea7635f0aaf6f0268'
    local=ROOT/'.model-cache'/REVISION
    assert (local/'pytorch_model.bin').exists(), '先运行 python fetch_clip.py；本单元不伪造相似度。'
    assert sha_file(local/'pytorch_model.bin')==provenance['model_sha256'], '权重 SHA-256 不匹配，停止。'
    clip_model=CLIPModel.from_pretrained(local,local_files_only=True).eval()
    # Make the teacher run's slow image processing + fast tokenizer explicit.
    # A shared use_fast=False would also change the tokenizer; keep each choice separate.
    clip_processor=CLIPProcessor(
        image_processor=CLIPImageProcessor.from_pretrained(local,local_files_only=True),
        tokenizer=AutoTokenizer.from_pretrained(local,local_files_only=True,use_fast=True))
    for parameter in clip_model.parameters():parameter.requires_grad_(False)
    photo=Image.open(ROOT/'assets/chelsea-cat.png').convert('RGB')
    image_inputs=clip_processor(images=photo,return_tensors='pt')
    arms={
      'A_base':(['cat','dog','horse'],'a photo of a {}.'),
      'B_expand_only':(['cat','dog','horse','tiger','fox'],'a photo of a {}.'),
      'C_prompt_only':(['cat','dog','horse'],'a cropped photo of a {}.'),
      'D_remove_cat':(['dog','horse','tiger','fox'],'a photo of a {}.')}
    clip_records={}
    with torch.no_grad():
        image_feature=clip_model.get_image_features(**image_inputs)
        image_feature=image_feature/image_feature.norm(dim=-1,keepdim=True)
        scale=float(clip_model.logit_scale.exp())
        for arm,(names,template) in arms.items():
            prompts=[template.format(name) for name in names]
            text_inputs=clip_processor(text=prompts,return_tensors='pt',padding=True)
            text_features=clip_model.get_text_features(**text_inputs)
            text_features=text_features/text_features.norm(dim=-1,keepdim=True)
            cosine=(image_feature@text_features.T).squeeze(0)
            probabilities=(cosine*scale).softmax(-1)
            clip_records[arm]={'candidate_names':names,'prompts':prompts,'cosine':cosine.tolist(),
              'softmax':probabilities.tolist(),'top1':names[int(cosine.argmax())]}
    assert np.allclose(clip_records['A_base']['cosine'],clip_records['B_expand_only']['cosine'][:3],atol=2e-6)
    clip_result={'status':'actually run locally on CPU','model_repo':'openai/clip-vit-base-patch32','revision':REVISION,
      'model_sha256':sha_file(local/'pytorch_model.bin'),'image_sha256':sha_file(ROOT/'assets/chelsea-cat.png'),
      'image_source':'scikit-image v0.25.2 chelsea.png; Stefan van der Walt; CC0','logit_scale':scale,
      'arms':clip_records,'limitations':['one image; no dataset-level accuracy estimate','relative candidate scores are not open-set certainty']}
    (OUT/'clip-results.json').write_text(json.dumps(clip_result,indent=2))
    fig,axes=plt.subplots(1,3,figsize=(12,3.8));axes[0].imshow(photo);axes[0].axis('off');axes[0].set_title('Same real photograph in all arms')
    for arm,color in [('A_base',BLUE),('B_expand_only',GOLD)]:
        rr=clip_records[arm]; loc=np.arange(len(rr['candidate_names']))
        axes[1].plot(loc,rr['cosine'],marker='o',label=arm,color=color)
        axes[2].plot(loc,rr['softmax'],marker='o',label=arm,color=color)
    for ax,title in zip(axes[1:],['Shared cosine remains fixed','Relative softmax changes']):
        ax.set(xticks=range(5),xticklabels=arms['B_expand_only'][0],title=title);ax.legend(fontsize=8);ax.grid(alpha=.18)
    axes[1].set_ylabel('Cosine similarity');axes[2].set_ylabel('Softmax over chosen candidates')
    savefig('05-clip-candidates.png')
    print('Actual checkpoint SHA-256:',clip_result['model_sha256'])
    print('arm | top1 | candidate : cosine / softmax')
    for arm,r in clip_records.items():
        print(arm,r['top1'],[(name,round(co,4),round(pr,4)) for name,co,pr in zip(r['candidate_names'],r['cosine'],r['softmax'])])
else:
    print('CLIP 未运行：请不要将空结果写成真实相似度。')