Lu Tao

In deeplab.py : replace raw code with follows: ``` from tensorflow.keras.models import Model from tensorflow.keras import layers from tensorflow.keras.layers import Input from tensorflow.keras.layers import Lambda from tensorflow.keras.layers import Activation from...

Faced some errors in validation part.

3

Faced some errors in validation part. ``` Traceback (most recent call last): File "train.py", line 432, in main() File "train.py", line 173, in main results_dict, loss_val = validate(val_loader, model, criterion_d,...

Nan loss on the half way to train the model.

2

I am using your framework on image translation task. The loss was fine at the very begining, but was changed into **Nan** in Epoch 006. Have you ever solved this...

Faced unexpected pause when training epoch is 16160

7

These are the output of console: ``` Iteration: 00161080/00170000 content_loss:0.0000 lap_loss:0.3854 rec_loss:0.0622 style_loss:1.4862 loss_tmp:0.5256 loss_tmp_GT:0.0664 Iteration: 00161090/00170000 content_loss:0.0000 lap_loss:0.1441 rec_loss:0.1067 style_loss:0.7328 loss_tmp:0.2622 loss_tmp_GT:0.0847 Iteration: 00161100/00170000 content_loss:0.0000 lap_loss:0.0956 rec_loss:0.0610 style_loss:0.3879 loss_tmp:0.4483...

TypeError: SANTAModel.translate() takes 2 positional arguments but 3 were given

4

How to handle this problem? ``` (epoch: 5, iters: 5000, time: 0.348, data: 0.002) G_GAN: 0.222 D_real: 0.411 D_fake: 0.198 G_rec: 0.092 G_idt: 0.042 G_kl: 1.145 G_path: 0.391 d1: 0.402...

Please use safetensors as code instead of in the formate of weights. It's toooooo hard for guys in China mainland to download a hug file in Gihub. see [https://github.com/huggingface/safetensors](https://github.com/huggingface/safetensors )