model.set_input(data) # unpack data from data loader
model.test() # run inference
visuals = model.get_current_visuals() # get image results
img_path = model.get_image_paths() # get image paths
if i % 5 == 0: # save images to an HTML file
print('processing (%04d)-th image... %s' % (i, img_path))
save_images(webpage,
visuals,
img_path,
aspect_ratio=opt.aspect_ratio,
width=opt.display_winsize)
image_list.append(visuals)
fid.append(get_FIDScore(image_list))
del image_list
#import pdb;pdb.set_trace()
# evaluate by fid score (target -> source)
## Your Implementation Here ##
fid_scoreA = fid[0]
# evaluate by fid score (source -> target)
## Your Implementation Here ##
fid_scoreB = fid[1]
print('source-like target / source fid score = %d \n' % (fid_scoreA))
print('target-like source / target fid score = %d \n' % (fid_scoreB))
webpage.save() # save the HTML
model.set_input(data) # unpack data from data loader
model.test() # run inference
visuals = model.get_current_visuals() # get image results
img_path = model.get_image_paths() # get image paths
if i % 5 == 0: # save images to an HTML file
print('processing (%04d)-th image... %s' % (i, img_path))
save_images(webpage, visuals, img_path, aspect_ratio=opt.aspect_ratio, width=opt.display_winsize)
real_list.append(visuals['real'])
fake_list.append(visuals['fake'])
#fid.append(get_FIDScore(real_list, fake_list))
fake.append(fake_list)
real.append(real_list)
#import pdb;pdb.set_trace()
# evaluate by fid score (target -> source)
## Your Implementation Here ##
#fid_scoreA = fid[0]
fid_scoreA = get_FIDScore(real[1], fake[0])
# evaluate by fid score (source -> target)
## Your Implementation Here ##
#fid_scoreB = fid[1]
fid_scoreB = get_FIDScore(real[0], fake[1])
print('source-like target / source fid score = %d \n' % (fid_scoreA))
print('target-like source / target fid score = %d \n' % (fid_scoreB))
webpage.save() # save the HTML