eva_giant_patch14_224.clip_ft_in1k 排名第九支持224

eva_giant_patch14_224.clip_ft_in1k 的模型卡

EVA-CLIP 图像分类模型。论文作者在 LAION-400M 上使用 CLIP 进行预训练，并在 ImageNet-1k 上进行微调。EVA-CLIP 使用 MIM 预训练图像塔和预训练文本塔、FLIP 补丁 dropout 以及不同的优化器和 hparams 来加速训练。

注意：timm为了与其他模型保持一致，检查点是 float32。在某些情况下，原始检查点是 float16 或 bfloat16，如果愿意，请参阅原始检查点。

模型详细信息

• 模型类型：图像分类/特征主干
• 模型统计：
• 参数（M）：1012.6
• GMAC：267.2
• 激活数（百万）：192.6
• 图片尺寸：224 x 224
• 文件：
• EVA-CLIP：改进的大规模 CLIP 训练技术：
• 原来的：

模型使用

图像分类  from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png')) model = timm.create_model('eva_giant_patch14_224.clip_ft_in1k', pretrained=True) model = model.eval() # get model specific transforms (normalization, resize)data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1 top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)

图像嵌入  from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png')) model = timm.create_model( 'eva_giant_patch14_224.clip_ft_in1k', pretrained=True, num_classes=0,  # remove classifier nn.Linear) model = model.eval() # get model specific transforms (normalization, resize)data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor # or equivalently (without needing to set num_classes=0) output = model.forward_features(transforms(img).unsqueeze(0)) # output is unpooled, a (1, 257, 1408) shaped tensor output = model.forward_head(output, pre_logits=True) # output is a (1, num_features) shaped tensor

模型比较

中探索该模型的数据集和运行时指标。

引用  @article{EVA-CLIP, title={EVA-02: A Visual Representation for Neon Genesis}, author={Sun, Quan and Fang, Yuxin and Wu, Ledell and Wang, Xinlong and Cao, Yue}, journal={arXiv preprint arXiv:2303.15389}, year={2023} }   @misc{rw2019timm, author = {Ross Wightman}, title = {PyTorch Image Models}, year = {2019}, publisher = {GitHub}, journal = {GitHub repository}, doi = {10.5281/zenodo.4414861}, howpublished = {\url{https://github.com/huggingface/pytorch-image-models}} }