manicman1999 / matchue-stylegan Goto Github PK

Hey, I have watched your video and read the code. I was trying to rerun the code in colab and It seems to appear that the data link that is pokemon.npy is not downloadable, I mean it shows 404 error on the drive page. Can you please update the link for the pokemon dataset.

It is great effort. I have a little bit issue. when I "Train the models" the error "TypeError: Cannot convert a symbolic Keras input/output to a numpy array. This error may indicate that you're trying to pass a symbolic value to a NumPy call, which is not supported. Or, you may be trying to pass Keras symbolic inputs/outputs to a TF API that does not register dispatching, preventing Keras from automatically converting the API call to a lambda layer in the Functional Model" occurs due to the line "loss = DiscriminatorModel.train_on_batch([real_images, latent_vectors], [real_labels, fake_labels, dummy_labels])" Please help anyone to resolve this issue

Thank you for your video. I found you on youtube and try to do this amazing GAN along with you, But I got this problem.

• call() got an unexpected keyword argument 'bias_initializer'

def g_block(input_tensor, latent_vector, filters):
gamma = Dense(filters)(latent_vector, bias_initializer = 'ones')
beta = Dense(filters)(latent_vector)

out = UpSampling2D()(input_tensor)
out = Conv2D(filters, 3, padding = 'same')(out)
out = Lambda(AdaIN)([out, gamma, beta])
out = Activation('relu')(out)

return out

#Latent input
latent_input = Input([64])

#Map latent input
latent = Dense(64, activation = 'relu')(latent_input)
latent = Dense(64, activation = 'relu')(latent)
latent = Dense(64, activation = 'relu')(latent)

#Reshape to 4x4x64
x = Dense(4464, activation = 'relu')(latent_input)
x = Reshape([4, 4, 64])(x)

#Size: 4x4x64
x = g_block(x, latent, 64)

#Size: 8x8x64
x = g_block(x, latent, 32)

#Size: 16x16x32
x = g_block(x, latent, 16)

#Size: 32x32x16
x = g_block(x, latent, 8)

#Size: 64x64x8, make RGB with values between 0 and 1
image_output = Conv2D(3, 1, padding = 'same', activation = 'sigmoid')(x)

#Make Model
generator = Model(inputs = latent_input, outputs = image_output)

#Model Summary
generator.summary()

call() got an unexpected keyword argument 'bias_initializer'

Could you tell me, What if bias_initializer didn't set. Thank you.