Skip to content
This repository has been archived by the owner on Dec 8, 2024. It is now read-only.

Training results in detections at all anchorboxes #139

Open
aaronrmm opened this issue Mar 30, 2020 · 0 comments
Open

Training results in detections at all anchorboxes #139

aaronrmm opened this issue Mar 30, 2020 · 0 comments

Comments

@aaronrmm
Copy link

aaronrmm commented Mar 30, 2020

After training on the VOC2007 dataset with default options except epochs=5, and efficientdet-d2, I am getting detections of all classes at all anchorboxes when using both eval.py and demo.py. Changing thresholds to 0.99+ does not curb the detections.

I get the same result when training with a very tiny dataset with fewer epochs. Additionally my validation mAP is always 0, even when I evaluate on the training set.

I am using Luke Melas's backbone as suggested in this issue#111.

  • Relevant packages in my conda environment are:
  • Name Version Build Channel

  • albumentations == 0.4.5 == pypi_0 pypi
  • cudatoolkit == 10.1.243 == h6bb024c_0
  • numpy == 1.18.1 == py38h4f9e942_0
  • numpy-base == 1.18.1 == py38hde5b4d6_1
  • opencv-contrib-python == 4.2.0.32 == pypi_0 pypi
  • pytoan == 0.6.4 == pypi_0 pypi
  • pytorch == 1.4.0 == py3.8_cuda10.1.243_cudnn7.6.3_0 pytorch
  • torchvision == 0.5.0 == py38_cu101 pytorch

Here is the output for python demo.py --cam -w=./saved/weights/VOC/efficientdet-d2/checkpoint_5.pth -t=.999 -it=.999 :
Detection_screenshot_30 03 2020

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant