-
when run 'depth_anything = DepthAnything.from_pretrained(pretrained_model_name_or_path='LiheYoung/depth_anything_{}14'.format(args.encoder)).to(DEVICE).eval()', there is a error 'TypeError: __init__()…
-
## 🐛 Bug
Unable to use BLEU as a metric for saving best checkpoint, despite [example translation scripts](https://github.com/pytorch/fairseq/tree/master/examples/translation#iwslt14-german-to-engli…
-
**Describe the bug**
I fine-tuned an SSDlite320 MobileNetV3-Large model using the code provided by [torhcvision](https://github.com/pytorch/vision/tree/main/references/detection). The pytorch model w…
-
I tried to reproduce results from the paper on WMT En2De, base model. In my experiments I tried both BPE and word piece model. Here are the steps I made to train models:
```
# For BPE model I used…
-
when i run the ``` python demo.py```, I met a problem like the flowing. My trimesh edition is 2.35.39.
> Loaded checkpoint /data/cxy/code/votenet/demo_files/pretrained_votenet_on_sunrgbd.tar (ep…
-
Error(s) in loading state_dict for Sam:
Unexpected key(s) in state_dict: "mask_decoder.hf_token.weight", "mask_decoder.hf_mlp.layers.0.weight", "mask_decoder.hf_mlp.layers.0.bias", "mask_decoder.hf…
-
Works as expected when loading the base model, but when a LoRA checkpoint is loaded in place of the base model, unsloth returns:
`Unsloth cannot patch Attention layers with our manual autograd engine…
-
Ideally we would have a function that takes as input the path of a pickle checkpoint file which the function then inserts into the database as a new model entry.
-
CommitPollingClient should re-sequentialize the order of commit when reading. This allows saving checkpointId X before X-1.
To allow this result we need to have a CheckpointId Long instead of a simpl…
-
Trying to run:
trtexec --onnx=data/mobile_sam_mask_decoder.onnx --saveEngine=data/mobile_sam_mask_decoder.engine --minShapes=point_coords:1x1x2,point_labels:1x1 --optShapes=point_coords:1x1x2,point…