-
Traceback (most recent call last):
File "test.py", line 68, in
num_query)
File "/home/pengyuzhou/workspace/TransReID/processor/processor.py", line 162, in do_inference
feat = model(im…
-
Hello there. I'm in the process of setting up a Colab notebook to train a couple models needed for inference in Soft-VC, mostly for personal ease-of-access. One of the first steps is obtaining a custo…
-
Currently for datasets with bounding boxes, we need to specify the max bounding boxes possible so all output batches are of the same size: https://github.com/MichiganCOG/ViP/blob/74776f2575bd5339ba39c…
-
https://github.com/pytorch-labs/tensordict
https://pytorch.org/rl/tensordict/index.html
Some random notes after a chat I had with @vmoens
----
TensorsDicts don't really work with our V2…
-
Thank you for providing such a well-written and understandable example. I did have problems running on multiple gpus (which sometimes seems like voodoo anyway). Here's my command line and status messa…
-
Traceback (most recent call last):
File "tools/train.py", line 245, in
main()
File "tools/train.py", line 241, in main
meta=meta)
File "/data/.conda/envs/mmdetection3d/mmdet3d/apis…
-
Hi everyone, I am wondering if it is possible for a user to create a custom batch of images with ffcv's speed.
- Specifically I would like to know if there is something like `get_batch(indices)` th…
-
### 🐛 Describe the bug
I've seen multiple individuals and groups using num_workers=0 in DataLoader, and significantly under-utilizing GPUs due to the following error message which appeared cryptic …
-
May I know what is the reason behind the warning message?
FYI, my input data is Pytorch Dataloader, which was constructed in tensor.
2023-05-12 16:16:31 | INFO | [1/2] Running PyTorch Optimi…
-
### Description of the bug | 错误描述
0: 1888x1312 299 embeddings, 1 isolated, 462.2ms
Speed: 20.8ms preprocess, 462.2ms inference, 34.8ms postprocess per image at shape (1, 3, 1888, 1312)
2024-08-03 1…