Closed yryun closed 6 years ago
This appears to be a hyperparameter tuning problem rather than a bug or feature with the object detection code itself. Such support questions are outside the purview of this repo's issues, and are better asked on the TensorFlow Stack Overflow page. There is also a larger community that reads questions there.
If you think we've misinterpreted a bug, please comment again with a clear explanation, as well as all of the information requested in the issue template. Thanks!
System information
Describe the problem
I've been training Faster R-CNN with mobilenet feature extractor for 400k iteration, batch 8, learning rate 3e-03. But it's mAP is almost zero. I'm using my own dataset and it's going well with inceptionV2, resnet50, 101. Only mobilenet has problem.... It seems like first stage loss too high so that second stage dose not processed most of the time. I tried stride size 16 and 8 but same problem.
Source code / logs
here is loss of first and second stage.
here is my tensorboard distributions. Compared to Incepction V2, mobilenet has No change in second stage conv2d_12, conv2d_13 - moving_mean, moving_variance. It could be a clue
here is my config file