1

I am trying to debug this project : https://github.com/VisualComputingInstitute/TrackR-CNN This is a MaskRCNN based project and I want to visualize the data flow among various functions in network/FasterRCNN.py(https://github.com/VisualComputingInstitute/TrackR-CNN/blob/master/network/FasterRCNN.py) mainly rpn_head(), fastrcnn_head(). I tried it with py_func and pdb but was not successful. SEssion.run() is created inside core/Engine.py(https://github.com/VisualComputingInstitute/TrackR-CNN/blob/master/core/Engine.py). Is there any way to see the image manipulation during the training(i.e. rpn values, reid_dim, etc)?

Thanks.

Samiha Sara
  • 11
  • 1
  • 3
  • There is a library in Tensorflow called TensorBoard is used to visualize the data, metrics, model graph. For more details on the library you can find here [Tensorboard](https://www.tensorflow.org/tensorboard). Thanks –  Nov 10 '20 at 09:41
  • @TFer thank you. I am trying tensorboard for visualization. Could you please tell, if the training process needs to finish before to loss, model graph in tensorboard? I need to see the dataflow, is there any way to visualize these as the training process progresses? – Samiha Sara Nov 14 '20 at 22:00

0 Answers0