from PIL import Image
import matplotlib.pyplot as plt
The curve for generator and discriminator should converge to a similar value when the GAN managed to train
disc = Image.open('results/dgcnn_basic_discrim_loss.png')
gen = Image.open('results/dgcnn_basic_generator_loss.png')
plt.figure(figsize=(20,20))
plt.subplot(1,2,1)
plt.imshow(disc)
plt.subplot(1,2,2)
plt.imshow(gen)
disc = Image.open('results/dgcnn_deluxe_discrim_loss.png')
gen = Image.open('results/dgcnn_deluxe_generator_loss.png')
plt.figure(figsize=(20,20))
plt.subplot(1,2,1)
plt.imshow(disc)
plt.subplot(1,2,2)
plt.imshow(gen)
We can see that at iteration 200, the generated image looks more like noise. We can only see some vague black and white pattern. At iteration 6000, it is able to generate details of the cat like mouth, nose and eyes. The result looks much more realistic.
iter200 = Image.open('results/sample-000200_vanilla_deluxe.jpg')
iter6000 = Image.open('results/sample-006000_vanilla_deluxe.jpg')
plt.figure(figsize=(20,20))
plt.subplot(1,2,1)
plt.imshow(iter200)
plt.subplot(1,2,2)
plt.imshow(iter6000)
xy = Image.open('results/sample-000600-X-Y.jpg')
yx = Image.open('results/sample-000600-Y-X.jpg')
plt.figure(figsize=(20,20))
plt.subplot(1,2,1)
plt.imshow(xy)
plt.subplot(1,2,2)
plt.imshow(yx)
xy = Image.open('results/cycle_sample-000600-X-Y.jpg')
yx = Image.open('results/cycle_sample-000600-Y-X.jpg')
plt.figure(figsize=(20,20))
plt.subplot(1,2,1)
plt.imshow(xy)
plt.subplot(1,2,2)
plt.imshow(yx)
xy = Image.open('results/sample-010000-X-Y.jpg')
yx = Image.open('results/sample-010000-Y-X.jpg')
plt.figure(figsize=(20,20))
plt.subplot(1,2,1)
plt.imshow(xy)
plt.subplot(1,2,2)
plt.imshow(yx)
xy = Image.open('results/cycle_sample-010000-X-Y.jpg')
yx = Image.open('results/cycle_sample-010000-Y-X.jpg')
plt.figure(figsize=(20,20))
plt.subplot(1,2,1)
plt.imshow(xy)
plt.subplot(1,2,2)
plt.imshow(yx)
It seems images generated without cycle consistency is a little bit darker than the images generated with cycle consistency. This is more obvious in early iterations and for grumpy cat to russian blue. I belive it is caused by the cycle consistency force the generated image to have colors that are failthful to original real images.