-
Hi,
I am training a Cascade RCNN ResNeSt S101 model using a mini-batch size of 8. On my GTX 1080ti with 12GB VRAM, the model uses ~10GB. On my Tesla P40 with 24GB of VRAM, the same config file uses…
-
Hello, when I try to train cascade rcnn with iterdet on crowdhuman, I found the performance very poor. The mAP is about 80% and i found a warning.
I don't know if it makes a problem.
===========log…
-
First of all thanks for providing slowonly [config](https://github.com/open-mmlab/mmaction2/blob/master/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes.py) for…
ImSau updated
3 years ago
-
Not compiled with GPU support (ROIAlign_forward at /home/oliver/PycharmProjects/detectron2/detectron2/layers/csrc/ROIAlign/ROIAlign.h:73)
I have searched the error in the Internet but still can't slo…
-
Hi,
I got `undefined symbol` when running the example in tutorial and I have tried solutions in `Common Installation Issues`.
```
File "/root/detectron2/detectron2/layers/__init__.py", line 3, in…
-
If you do not know the root cause of the problem / bug, and wish someone to help you, please
post according to this template:
## Instructions To Reproduce the Issue:
1. what changes you made (`…
-
If you do not know the root cause of the problem / bug, and wish someone to help you, please
post according to this template:
## Instructions To Reproduce the Issue:
1. what changes you made (`…
-
Hi, there are some issues for my training fasterRCNN model. I have download the voc2007 dataset in the colab, but the the error says no such file.
:
File "mmdetection/tools/train.py", line 151, in
main()
File "mmdetection/tools/train.py", line 147, in …
-
### problem description
I used my own dataset to train cascade rcnn, but it occurs error when meet some data. So I create a toy dataset to test the running code, my toy dataset is like this:
[{'fil…