don choppy comments

Results 4 comments of


                                            don choppy

Accuracy and loss is shock

> how did you get graphs of the loss and accuracy?? with tensorboard it's implemented in the code, just type in your console tensorboard --logdir unet_trained

add support for tensorflow.keras API

Any updates about this?

Support of Tensorflow 2.x backend Keras models

Hello there, me again. I got this error after I excecuted `from kito import reduce_keras_model` `model_reduced = reduce_keras_model(model)` ![image](https://user-images.githubusercontent.com/22966368/92967189-319a2200-f44f-11ea-974b-fddef2e8ceda.png) tensorflow version: 1.15.0 keras version: 2.2.4-tf Best regards!

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [4, 512, 16, 16]], which is output 0 of ConstantPadNdBackward, is at version 1; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

> > > > > This error can be resolved by setting inplace=False in nn.ReLU and nn.LeakyReLU in blocks.py. > > > > > > > > > > >...