ray0809 / pix2pix Goto Github PK

Using TensorFlow backend.
Epochs 200
Bathc_size 12
Batches per epoch 31
Traceback (most recent call last):
File "new_pix2pix.py", line 252, in
train(200,12)
File "new_pix2pix.py", line 209, in train
discriminator = discriminator_model()
File "new_pix2pix.py", line 147, in discriminator_model
inputs = Input(shape=(img_cols,img_rows,IN_CH*2))
NameError: global name 'img_cols' is not defined

I am getting the above error ...
Can you please help resolve this issue.

sir ,
QUE 1 ) https://github.com/ray0809/pix2pix/blob/master/data.py needs image files (jpg and png) in folder /home/ray/python_code/keras_examples/pix2pix/CMP_facade_DB_base/base .
How can I get those ?
QUE 2 ) My understanding is that parameters of neural network are learnt when we have pair of files labelled as corresponding input and output . After training we give an unknown input image and neural network generates output image using parameters it has learnt earlier . Is that alright ?
That leads me to think that pic folder should have atleast 2 files (jpg , one input and one output)
Target folder can have 1 png file if we desire to predict the output for this input png image .
Is that ok ?

Will wait for your reply.
Thanks for reading.

Hi, I have two errors during training.

1. error on G_loss.
--------------- Epoch 1 ---------------
0it [00:00, ?it/s]
Traceback (most recent call last):
File "new_pix2pix.py", line 255, in
train(200,12)
File "new_pix2pix.py", line 242, in train
G_loss.append(gloss)
UnboundLocalError: local variable 'gloss' referenced before assignment

So, I commented out G_loss and D_loss. And now it returns an another error
#G_loss.append(gloss)
#D_loss.append(dloss)
...
#D_loss = np.array(D_loss)
#G_loss = np.array(G_loss)
#np.save('Model_para/dloss.npy',D_loss)
#np.save('Model_para/gloss.npy',G_loss)

2. error on dimensions

--------------- Epoch 1 ---------------
0it [00:00, ?it/s]
Traceback (most recent call last):
File "new_pix2pix.py", line 255, in
train(200,12)
File "new_pix2pix.py", line 245, in train
generate_pic(generator,target[0:1],e)
File "new_pix2pix.py", line 187, in generate_pic
pic = generator.predict(target)
File "/home/marsha/anaconda2/lib/python2.7/site-packages/keras/engine/training.py", line 1576, in predict
check_batch_axis=False)
File "/home/marsha/anaconda2/lib/python2.7/site-packages/keras/engine/training.py", line 127, in _standardize_input_data
str(array.shape))
ValueError: Error when checking : expected input_1 to have 4 dimensions, but got array with shape (0, 1)

I cannot understand the format of *.npy, can u explain or push the files.
pic = np.load('pic.npy')
target = np.load('target.npy')