-
when I train my faster-rcnn (mmdet==2.20.0,mmcv-full==1.3.17 )，it raise the error like this:
here is my config，can anybody know how to deal with ? thanks
==========================================…
-
I'm trying to train sparse rcnn with swin backbone on my own dataset, I already trained for some epochs using this config but now I get this error and I don't understand why . Please help!
### conf…
-
I run ./tools/deploy.py expecting to export the .onnx model, I get an error. How to deal with it?
2022-03-23 17:48:30,339 - mmdeploy - INFO - torch2onnx start.
2022-03-23:17:48:42,root ERROR [util…
-
您好！
我们使用SparseInst模型可以正常训练，但是训练开始时total_loss是8.x，训练几个小时后，就降到了2.6，然后连续训练了好一周左右，total_loss依然是2.6，没有任何变化。相同的数据集，使用SparseInst官方代码训练，是可以收敛的。
想请问一下这是什么原因造成的？怎么解决？
注：我们使用Yolov7来训练SparseInst主要是想用这里的工程化代码，转…
-
**Describe the bug**
When I train the YOLOX as a detector with MOT17 dataset, the training log showing `loss_cls = 0.000, loss_bbox=0.000` in every interval,
Simultaneously, this error :
`- mmd…
-
> Traceback (most recent call last):
> File "", line 983, in _find_and_load
> File "", line 953, in _find_and_load_unlocked
> File "", line 219, in _call_with_frames_removed
> File "D:\Det…
-
Hello I want to test my models from this framework against models from another framework using a script very similar to the evaluate method in the coco.py file:
```
cocoGt = COC…
-
**The Log:**
2022-07-29 10:34:45,983 - mmpose - INFO - workflow: [('train', 1)], max: 210 epochs
2022-07-29 10:35:08,868 - mmpose - INFO - Epoch [1][50/681] lr: 4.945e-05, eta: 18:10:25, time: 0.458…
-
I'm trying to train a custom COCO-format dataset. My datasets are json files with the aforementioned COCO-format, with each item in the "annotations" section looking like this:
[![Annotations][1]][…
-
Hello, I'm trying to train my model for table recognition with the distributed tool provided, but everytime I try to run it, I get an error and can not start the training. Following I will put the tra…