-
While running the following codes:
`net = NMF(data.shape, rank=self.basis_num, W=torch.Tensor(self.W), trainable_W=False).cuda()`
`net.fit(data.cuda(), verbose=True, max_iter=200, tol=1e-18, beta=1)…
-
# ❓ Questions and Help
Hi guys,
Thanks a lot for the amazing work. I am trying to use `xformers` on CLIP, following the `timm` tutorial I've put together the following code
```python
MODEL_NAM…
-
## Description
I ran this command:
```
spineps sample -ignore_bids_filter -ignore_inference_compatibility -i raw/sub-247876_acq-sagittal_T2w.nii.gz -model_semantic t2w_segmentor_2.0 -model_instan…
-
I have implemented partialconv, and stumbled with the problem that layer activations are peaking at edges, though "Partial Convolution based Padding" paper at Figure 5 ([paper](https://arxiv.org/abs/1…
-
**Describe the bug:**
When using a 16x16 tile map that has collision, for some reason the collision object appears to give the tiles bounding boxes that are closer to 17x17 pixels in size, in additio…
-
- total searches of all routes
- partitioned by route
- aggregated on different times
Idea is to see if there's a time in the year where A LOT of searches are happening vs other months.
-
I get this error when I run test_on_video.py file.
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call…
-
Steps to reproduce:
1. Check out https://github.com/ezyang/pytorch/pull/new/poc/layer-norm-misannot
2. Run `pytest test/quantization/test_quantize_script.py -k test_layer_norm`
Expected result: n…
-
/home/hinux/anaconda3/bin/conda run -n 38 --no-capture-output python /home/hinux/pythonProject/surveilling-surveillance/detection/main.py
Skip loading parameter 'roi_heads.box_predictor.cls_score.we…
-
Thank you for your work!
But when I trained based on ViT-L/14, the size of q,k,v are mismatch.
Traceback (most recent call last):
File "main.py", line 292, in main
main_training(logger, co…