RuntimeError: Pretrained weights (../sagav2/clip_ckpt/ViT-B-16-laion2b_s34b_b88k.bin) not found for model ViT-B-16.

[malong0115]

非常荣幸能够使用您开源的项目。 我在使用get_clip_features.py时报出了这个错误，没有找到../sagav2/clip_ckpt/ViT-B-16-laion2b_s34b_b88k.bin，我应该在哪里找到它？ 我运行的命令是：python get_clip_features.py --image_root data/360_v2/garden/

[Jumpat]

你好，感谢你的关注。可以从这里下载这个ckpt。

[L1n2hang]

I guess I managed to make it work somehow?

This is what I've done:

1. download the ckpt from the link Jumpat provided; and it should look like this 2）change the original clip_model_pretrained to the bin file in your downloaded direction

[Jumpat]

Yeah, thanks for your help! @L1n2hang

[tom-gao-gyc]

Traceback (most recent call last): File "get_clip_features.py", line 19, in clip_model = load_clip() File "/home/code/SegAnyGAussians-2/clip_utils/clip_utils.py", line 206, in load_clip return OpenCLIPNetwork(OpenCLIPNetworkConfig) File "/home/code/SegAnyGAussians-2/clip_utils/clip_utils.py", line 69, in init model, _, _ = open_clip.create_model_and_transforms( File "/root/miniconda3/envs/gaussian_splatting_saga/lib/python3.8/site-packages/open_clip/factory.py", line 292, in create_model_and_transforms model = create_model( File "/root/miniconda3/envs/gaussian_splatting_saga/lib/python3.8/site-packages/open_clip/factory.py", line 207, in create_model load_checkpoint(model, checkpoint_path) File "/root/miniconda3/envs/gaussian_splatting_saga/lib/python3.8/site-packages/open_clip/factory.py", line 98, in load_checkpoint state_dict = load_state_dict(checkpoint_path) File "/root/miniconda3/envs/gaussian_splatting_saga/lib/python3.8/site-packages/open_clip/factory.py", line 87, in load_state_dict checkpoint = torch.load(checkpoint_path, map_location=map_location) File "/root/miniconda3/envs/gaussian_splatting_saga/lib/python3.8/site-packages/torch/serialization.py", line 713, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "/root/miniconda3/envs/gaussian_splatting_saga/lib/python3.8/site-packages/torch/serialization.py", line 920, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, 'v'. 您好，这里为什么我会报这个错误，是因为open_clip版本的问题吗

[hakaqaq]

回溯（最近调用最后一次）：文件 “get_clip_features.py”，第 19 行，clip_model = load_clip（） 文件 “/home/code/SegAnyGAussians-2/clip_utils/clip_utils.py”，第 206 行，load_clip返回 OpenCLIPNetwork（OpenCLIPNetworkConfig） 文件 “/home/code/SegAnyGAussians-2/clip_utils/clip_utils.py”，第 69 行，init model，_， _ = open_clip.create_model_and_transforms（文件 “/root/miniconda3/envs/gaussian_splatting_saga/lib/python3.8/site-packages/open_clip/factory.py”，第 292 行，create_model_and_transforms模型 = create_model（文件 “/root/miniconda3/envs/gaussian_splatting_saga/lib/python3.8/site-packages/open_clip/factory.py”，第 207 行，create_model load_checkpoint（model， checkpoint_path）文件“/root/miniconda3/envs/gaussian_splatting_saga/lib/python3.8/site-packages/open_clip/factory.py”，第 98 行，load_checkpoint state_dict = load_state_dict（checkpoint_path）文件“/root/miniconda3/envs/gaussian_splatting_saga/lib/python3.8/site-packages/open_clip/factory.py”，第 87 行，load_state_dict检查点 = torch.load（checkpoint_path， map_location=map_location）文件“/root/miniconda3/envs/gaussian_splatting_saga/lib/python3.8/site-packages/torch/serialization.py”，第 713 行，加载返回_legacy_load（opened_file，map_location，pickle_module，**pickle_load_args）文件“/root/miniconda3/envs/gaussian_splatting_saga/lib/python3.8/site-packages/torch/serialization.py”，第 920 行，_legacy_load magic_number = pickle_module.load（f， **pickle_load_args） _pickle。UnpicklingError：无效的加载键 'v'。 您好，这里为什么我会报这个错误，是因为open_clip版本的问题吗

我也遇到了这个问题，请问你解决了吗

[sunhongling]

invalid load key, 'v'. <--- I ran into this problem because the downloaded model is incomplete