-
### Search before asking
- [X] I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and found no similar bug report.
### YOLOv5 Component
Training
### Bug
Traceback …
-
`The module torch.distributed.launch is deprecated and going to be removed in future.Migrate to torch.distributed.run
WARNING:torch.distributed.run:--use_env is deprecated and will be removed in futu…
vefak updated
7 months ago
-
python tools/train.py configs/yolox-pose_s_8xb32-300e_coco.py
(mmpose) --- projects/yolox-pose ‹main* M?› » python tools/train.py configs/yolox-pose_s_8xb32-300e_coco.py
Traceback (most recent…
-
Hi,
I really like the MMDetection toolbox, it is a great time saver and very useful! I have a few questions:
1. Nearly all of the models use images of size 1333x800, now this is relatively large…
-
I am trying to create a model using the `YOLOV8BackBone` but getting a strange error. This error was not present in the past and has appeared after updating to `keras-cv 0.5.1`. I tried downgrading to…
-
Dear Authors:
I write the issue to ask for help in the training process of OccDepth:
1) If it is convenient, can you release your model file based on multicam_flospdepth_crp_stereodepth_cascadec…
-
### Prerequisite
- [X] I have searched [Issues](https://github.com/open-mmlab/mmpose/issues) and [Discussions](https://github.com/open-mmlab/mmpose/discussions) but cannot get the expected help.
-…
-
My experimental equipment is 3xTitan, and according to the rules of Detectron2, set the learning rate to 0.045.
Without modifying any parameters, the resulting map is about 35.6.
why?
-
### Describe the bug
The original Backbone for yolox_s is CSPDarknet. I use ResNet18 instead. The detailed configuration is as follows:
```
algorithm = dict(
type='GeneralDistill',
arch…
-
compiled pytorch v1.11.0 from source using CUDA 11.3, ubuntu 20.04, python 3.8 , installed to `/usr/local/lib/python3.8/dist-packages/torch/`
```
> nvcc --version
nvcc: NVIDIA (R) Cuda compiler dri…