Closed nihao-eng closed 1 year ago
It appears that your CLIP installation may not be correct. To resolve this issue, you can attempt to reinstall it by following the instructions provided at https://github.com/openai/CLIP
您的 CLIP 安装可能不正确。要解决此问题,您可以按照https://github.com/openai/CLIP中提供的说明尝试重新安装它
Thanks, I have solved this problem
Hello, when I run render.py and train, it gives me an error message saying "Method 'forward' is not defined."
Could you please let me know what could be causing this issue?
Traceback (most recent call last): File "/home/sda/cv3d/anaconda3/envs/xkuo_nerfart2/lib/python3.8/runpy.py", line 192, in _run_module_as_main return _run_code(code, main_globals, None, File "/home/sda/cv3d/anaconda3/envs/xkuo_nerfart2/lib/python3.8/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/sda/cv3d/xkuo/NeRF-Art/train.py", line 342, in
main_function(config)
File "/home/sda/cv3d/xkuo/NeRF-Art/train.py", line 100, in main_function
model, trainer, render_kwargs_train, render_kwargs_test, volume_render_fn = get_model(args,target_hw)
File "/home/sda/cv3d/xkuo/NeRF-Art/models/frameworks/init.py", line 11, in get_model
return get_model(args,target_hw)
File "/home/sda/cv3d/xkuo/NeRF-Art/models/frameworks/volsdf.py", line 992, in get_model
trainer = Trainer(model, args.device_ids, batched=render_kwargs_train['batched'],is_finetune = args.training.is_finetune,target_hw=render_target)
File "/home/sda/cv3d/xkuo/NeRF-Art/models/frameworks/volsdf.py", line 639, in init
contrastive_loss = ContrastiveLoss()
File "/home/sda/cv3d/xkuo/NeRF-Art/criteria/contrastive_loss.py", line 97, in init
self.model, clip_preprocess = clip.load("ViT-B/32", device="cuda")
File "/home/sda/cv3d/anaconda3/envs/xkuo_nerfart2/lib/python3.8/site-packages/clip/clip.py", line 133, in load
model.apply(patch_device)
File "/home/sda/cv3d/anaconda3/envs/xkuo_nerfart2/lib/python3.8/site-packages/torch/nn/modules/module.py", line 473, in apply
module.apply(fn)
File "/home/sda/cv3d/anaconda3/envs/xkuo_nerfart2/lib/python3.8/site-packages/torch/nn/modules/module.py", line 473, in apply
module.apply(fn)
File "/home/sda/cv3d/anaconda3/envs/xkuo_nerfart2/lib/python3.8/site-packages/torch/nn/modules/module.py", line 473, in apply
module.apply(fn)
[Previous line repeated 3 more times]
File "/home/sda/cv3d/anaconda3/envs/xkuo_nerfart2/lib/python3.8/site-packages/torch/nn/modules/module.py", line 474, in apply
fn(self)
File "/home/sda/cv3d/anaconda3/envs/xkuo_nerfart2/lib/python3.8/site-packages/clip/clip.py", line 124, in patch_device
graphs = [module.graph] if hasattr(module, "graph") else []
File "/home/sda/cv3d/anaconda3/envs/xkuo_nerfart2/lib/python3.8/site-packages/torch/jit/_script.py", line 449, in graph
return self._c._get_method("forward").graph
RuntimeError: Method 'forward' is not defined.