Is deepflux reproducible

[Tcorpion]

Follow the deepflux training, I could NOT get skeletons on par with “Deepflux for skeletons in the wild CVPR2019” reported.
The loss always went to 'Nan' in a few steps in training when LR=1e-6, after reducing grad from grad = distL1 * (weightPos + weightNeg) / len(crop) to grad = distL1 * (weightPos + weightNeg) / len(crop) / (weightPos + weightNeg).sum() , here (weightPos + weightNeg).sum() was about 1e4, the loss finally converged.

In fact, the skeletons produced in Deepflux are really bad. For comparison, I trained same deepflux model with skeleton mask instead of flux field, the results were much better than that from flux field.

Did you reproduce the skeleton prediction as paper reported?

[Tcorpion]

By the way, after replacing upsampling to deconv2d as Deepflux did, the loss could NOT converge with any values of learning rate.

[sunsmarterjie]

Thanks for your efforts ! Training deepflux needs Adam optimizer as my experience. But I still did not reproduce the performance as the paper reported. Welcome to join the project and reproduce deepflux.

[Tcorpion]

I adopt adam optimizer and it help converge. The converged model of flux field is NOT on par with skeleton mask training.