pihai
pihai
I also faces this problem. When I load the model using local weights, I run `depth_anything = DepthAnything.from_pretrained('checkpoints/depth_anything_{}14'.format(args.encoder), local_files_only=True).to(DEVICE).eval()`. I got the following error message: ```text xFormers not available xFormers...
> > I also faces this problem. When I load the model using local weights, I run `depth_anything = DepthAnything.from_pretrained('checkpoints/depth_anything_{}14'.format(args.encoder), local_files_only=True).to(DEVICE).eval()`. I got the following error message: > > ```...
> @LiheYoung Hello, I try to download the file from [link](https://huggingface.co/spaces/LiheYoung/Depth-Anything/blob/main/checkpoints/depth_anything_vitl14.pth), but it still shows that I cannot access it. > > ``` > # wget https://huggingface.co/spaces/LiheYoung/Depth-Anything/blob/main/checkpoints/depth_anything_vitl14.pth > --2024-03-07 01:43:23--...
> > I also faces this problem. > > When I load the model using local weights, I run depth_anything = DepthAnything.from_pretrained('checkpoints/depth_anything_{}14'.format(args.encoder), local_files_only=True).to(DEVICE).eval(). > > I got the following error...
@antimattergroup `pip list` ```text Package Version ------------------------- ---------- aiofiles 23.2.1 altair 5.2.0 annotated-types 0.6.0 anyio 4.3.0 attrs 23.2.0 certifi 2024.2.2 charset-normalizer 3.3.2 click 8.1.7 colorama 0.4.6 contourpy 1.2.0 cycler 0.12.1...
> Thank you for your appreciation. > > In my experience, the training loss is quite high, too. I would double check if the model is using the backbone pretrained...
> You could try using the provided checkpoint and test it on your data/code and see if the results match the ones provided. If they match then the problem is...
> Honestly, I do not know, you are not seeing any overfitting, but it does not generalize either since the training metrics are good, but not the validation ones. Moreover,...
```python # ... As above ... import copy ckp_copy = copy.deepcopy(ckp) ckp2_copy = copy.deepcopy(ckp2) model.eval() compare_model_weights(ckp_copy, ckp2_copy) ``` The above code now reports that `ckp_copy` and `ckp2_copy` are identical. This...
same issue. I found that the problem was caused by `XFormPrim.get_world_poses()` returning the same `poses` and `quat` every time. I thikn this is a BUG. Meanwhile, the camera data capture...