-
Traceback (most recent call last):
File "tools/train.py", line 263, in
main()
File "tools/train.py", line 259, in main
meta=meta)
File "/home/ly/tr3d-main/mmdet3d/apis/train.py", l…
-
Hi
Currently, webdataset dataset using the default Pytorch Dataloader or WebLoader doesn't work with Pytorch Lightning. You need to set a length attribute (see [lightining example](https://github.c…
-
Hi,
I wonder if the angle information is used in the process, either passed to the network directly or in some other ways.
I notice there's performance loss when the model gets sketches of uns…
-
## 🐛 Bug
## To Reproduce
Steps to reproduce the behavior:
1. python temporal_link_prediction.py
```
Training in cpu-cuda mode.
Loading data
Downloading datasets/diginetica-r2ne.zip …
-
Motivating example is returning bounding box annotation for images along with an image. An annotation list can contain variable number of boxes depending on an image, and padding them to a single leng…
-
Hello,
I'd like to load a byte[] or MemoryStream as a glb file without a file path from script (not using Inspector at all).
Is this possible? Didn't find anything in examples or tests.
-
### Prerequisite
- [X] I have searched [Issues](https://github.com/open-mmlab/mmcv/issues) and [Discussions](https://github.com/open-mmlab/mmcv/discussions) but cannot get the expected help.
- [X] Th…
-
I have this piece of code:
```
batch_size = 8
with converter_train.make_torch_dataloader(transform_spec=transform, batch_size=batch_size, num_epochs=1) as dataloader_train, \
converter_test.ma…
-
**After [fine-tuning,](https://github.com/AILab-CVC/YOLO-World/blob/master/docs/finetuning.md) the detector fails to detect objects,the Output Image Has No Detected Boxes， even though the loss keeps d…
-
In certain scenarios, it becomes necessary to modify the train_dataloader after each epoch. This can be managed through callbacks since the train dataloader is passed to the callback function. However…