-
[>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 19809/19809, 8.4 task/s, elapsed: 2364s, ETA: 0s2021-08-18 08:48:11,286 - mmdet - INFO - Evaluating bbox...
[08/18 08:48:11] mmdet INFO: Evalu…
-
Hello, author! I used your code to reproduce EQL loss, but the following error occurred:
File "/home/zhhu/eqlv2-master/mmdet/models/losses/eql.py", line 63, in forward
eql_w = 1 - self.exclude_…
-
In line 50-52 of nerfactor/nerfactor/util/vis.py,
#############################
img = xm.io.img.load(path)
img = img[:, :, :3] # discards alpha
hw = img.shape[:2]
#############################
T…
-
I am using quantization aware training on a custom dataset with ssd_mobilenet_v2_quantized_300x300_coco_2019_01_03. I tell it to train for 5000 steps yet it stops at 2700 and throws a bunch of errors …
-
**Describe the feature**
`mmpycocotools` is installed under the package name "pycocotools" - causing a conflict with the official pycocotools. This causes the following potential issues:
1. Users …
-
训练完毕进行测试的时候，测试展示的结果图仍让是原图，没有任何分割的结果，请问可能是什么原因造成的？
qzsrh updated
3 years ago
-
## Instructions To Reproduce the 🐛 Bug:
1. what changes you made (`git diff`) or what code you wrote
not change
```
2. what exact command you run:
python -m pip install 'git+https://gi…
-
TorchVision: 0.9.1+cu111
OpenCV: 4.5.1
MMCV: 1.0.5
MMDetection: 2.3.0+
MMDetection Compiler: GCC 9.3
MMDetection CUDA Compiler: 11.2
PyTorch: 1.8.1+cu111
PyTorch compiling details: PyTorch buil…
-
When I [run finetuning on the "all" split](https://github.com/ashkamath/mdetr/blob/main/.github/gqa.md):
```
python run_with_submitit.py --dataset_config configs/gqa.json --ngpus 8 --ema --epochs 12…
-
Im trying to train my model with my previus labelled images but i have this error. …