Test Error

[zjxi]

Hi, thanks for this incredible net. I've already trained the dataset, but when I aim to test it and
I input the following command: python main.py --phrase test --light true
However, I got the error in the log:

##### Information #####
# light :  True
# dataset :  selfie2anime
# batch_size :  1
# iteration per epoch :  1000000

##### Generator #####
# residual blocks :  4

##### Discriminator #####
# discriminator layer :  6

##### Weight #####
# adv_weight :  1
# cycle_weight :  10
# identity_weight :  10
# cam_weight :  1000
 [*] Load FAILURE
 [*] Test finished!

[znxlwm]

Above error occurred in the following code in my guess:

    def test(self):
        model_list = glob(os.path.join(self.result_dir, self.dataset, 'model', '*.pt'))
        if not len(model_list) == 0:
            model_list.sort()
            iter = int(model_list[-1].split('_')[-1].split('.')[0])
            self.load(os.path.join(self.result_dir, self.dataset, 'model'), iter)
            print(" [*] Load SUCCESS")
        else:
            print(" [*] Load FAILURE")
            return

It works well for me. I'm sorry, I don't know why you got the error...
Debug the above code.

Thank you

[zjxi]

Thanks, I wanna know if the model folder under the results directory is empty after training.
And mine was empty.

[Trueyellow]

The state dict of model is saved to the model folder every 100k iterations by default. Make sure you have reached that point.

[youyouhdhd]

Did you solve it? I also met the same problem.

[zjxi]

@youyouhdhd
Not yet.

[YangyangQu]

You need to put the pretrained model to results/selfie2anime/model/