Chainer ui v0.3 and imagereport
2 likes1,799 views
ChainerUI v0.3 was released with new features like sampled log visualization and performance tuning. It also introduced the experimental ImageReport extension for visualizing images generated during training. Examples shown include using ImageReport with a DCGAN and pix2pix model to display generated images. Future work includes improving the usability of ImageReport, adding support for charts, logging improvements, and enhancing the user experience of ChainerUI.
![Example: VAE (MNIST)
# Run the training
trainer.run()
# Visualize the results
def save_images(x, filename):
# ...snip
model.to_cpu()
train_ind = [1, 3, 5, 10, 2, 0, 13, 15, 17]
x = chainer.Variable(np.asarray(train[train_ind]))
with chainer.using_config('train', False), chainer.no_backprop_mode():
x1 = model(x)
save_images(x.data, os.path.join(args.out, 'train'))
save_images(x1.data, os.path.join(args.out, 'train_reconstructed'))
test_ind = [3, 2, 1, 18, 4, 8, 11, 17, 61]
x = chainer.Variable(np.asarray(test[test_ind]))
with chainer.using_config('train', False), chainer.no_backprop_mode():
x1 = model(x)
save_images(x.data, os.path.join(args.out, 'test'))
save_images(x1.data, os.path.join(args.out, 'test_reconstructed'))
# draw images from randomly sampled z
z = chainer.Variable(
np.random.normal(0, 1, (9, args.dimz)).astype(np.float32))
x = model.decode(z)
save_images(x.data, os.path.join(args.out, 'sampled'))
examples/vae
train_vae.py](https://image.slidesharecdn.com/chaineruiv0-180611065443/85/Chainer-ui-v0-3-and-imagereport-12-320.jpg)
![Example: VAE (MNIST)
# Run the training
trainer.run()
# Visualize the results
def save_images(x, filename):
# ...snip
model.to_cpu()
train_ind = [1, 3, 5, 10, 2, 0, 13, 15, 17]
x = chainer.Variable(np.asarray(train[train_ind]))
with chainer.using_config('train', False), chainer.no_backprop_mode():
x1 = model(x)
save_images(x.data, os.path.join(args.out, 'train'))
save_images(x1.data, os.path.join(args.out, 'train_reconstructed'))
test_ind = [3, 2, 1, 18, 4, 8, 11, 17, 61]
x = chainer.Variable(np.asarray(test[test_ind]))
with chainer.using_config('train', False), chainer.no_backprop_mode():
x1 = model(x)
save_images(x.data, os.path.join(args.out, 'test'))
save_images(x1.data, os.path.join(args.out, 'test_reconstructed'))
# draw images from randomly sampled z
z = chainer.Variable(
np.random.normal(0, 1, (9, args.dimz)).astype(np.float32))
x = model.decode(z)
save_images(x.data, os.path.join(args.out, 'sampled'))
def visualize(trainer):
train_ind = [1, 3, 5, 10, 2, 0, 13, 15, 17]
x = chainer.Variable(np.asarray(train[train_ind]))
with chainer.using_config('train', False), chainer.no_backprop_mode():
x1 = model(x)
def convert(x):
return x.reshape(9, 28, 28).transpose(0, 2, 1)
summary.image(convert(x), name='train', row=3)
summary.image(convert(x1), name='train_reconstructed', row=3)
test_ind = [3, 2, 1, 18, 4, 8, 11, 17, 61]
x = chainer.Variable(np.asarray(test[test_ind]))
with chainer.using_config('train', False), chainer.no_backprop_mode():
x1 = model(x)
summary.image(convert(x), name='test', row=3)
summary.image(convert(x1), name='test_reconstructed', row=3)
# draw images from randomly sampled z
z = chainer.Variable(
np.random.normal(0, 1, (9, args.dimz)).astype(np.float32))
x = model.decode(z)
summary.image(convert(x), name='sampled', row=3)
trainer.extend(ImageReport(image_generator=visualize))
# Run the training
trainer.run()](https://image.slidesharecdn.com/chaineruiv0-180611065443/85/Chainer-ui-v0-3-and-imagereport-13-320.jpg)
![examples/pix2pix
Example: pix2pix
def out_image(updater, enc, dec, rows, cols, seed, dst):
@chainer.training.make_extension()
def make_image(trainer):
# ...snip
def save_image(x, name, mode=None):
# ...snip
x = np.asarray(np.clip(gen_all * 128 + 128, 0.0, 255.0), dtype=np.uint8)
save_image(x, "gen")
x = np.ones((n_images, 3, w_in, w_in)).astype(np.uint8)*255
x[:,0,:,:] = 0
for i in range(12):
x[:,0,:,:] += np.uint8(15*i*in_all[:,i,:,:])
save_image(x, "in", mode='HSV')
x = np.asarray(np.clip(gt_all * 128+128, 0.0, 255.0), dtype=np.uint8)
save_image(x, "gt")
def main():
# ...snip
trainer = training.Trainer(
updater, (args.epoch, 'epoch'), out=args.out)
trainer.extend(
out_image(
updater, enc, dec,
5, 5, args.seed, args.out),
trigger=snapshot_interval)
train_facade.py
facade_visualizer.py](https://image.slidesharecdn.com/chaineruiv0-180611065443/85/Chainer-ui-v0-3-and-imagereport-15-320.jpg)
![Example: pix2pix
def out_image(updater, enc, dec, rows, cols, seed, dst):
@chainer.training.make_extension()
def make_image(trainer):
# ...snip
def save_image(x, name, mode=None):
# ...snip
x = np.asarray(np.clip(gen_all * 128 + 128, 0.0, 255.0), dtype=np.uint8)
save_image(x, "gen")
x = np.ones((n_images, 3, w_in, w_in)).astype(np.uint8)*255
x[:,0,:,:] = 0
for i in range(12):
x[:,0,:,:] += np.uint8(15*i*in_all[:,i,:,:])
save_image(x, "in", mode='HSV')
x = np.asarray(np.clip(gt_all * 128+128, 0.0, 255.0), dtype=np.uint8)
save_image(x, "gt")
def main():
# ...snip
trainer = training.Trainer(
updater, (args.epoch, 'epoch'), out=args.out)
trainer.extend(
out_image(
updater, enc, dec,
5, 5, args.seed, args.out),
trigger=snapshot_interval)
visualizer = out_image(updater, enc, dec, args.visualize_batchsize,
args.rows, args.seed)
trainer.extend(chainerui.extensions.ImageReport(
trigger=snapshot_interval, image_generator=visualizer))
summary.image(gen_all, name='gen', row=rows)
summary.image(x, name='in', row=rows, mode='HSV')
summary.image(gt_all, name='gt', row=rows)](https://image.slidesharecdn.com/chaineruiv0-180611065443/85/Chainer-ui-v0-3-and-imagereport-16-320.jpg)
More Related Content
Similar to Chainer ui v0.3 and imagereport (20)
Chainer ui v0.3 and imagereport
- 1. Jun. 9th, 2018 @Preferred Networks ChainerUI v0.3 and ImageReport
- 2. ChainerUI - mission - Provide useful user interface for Chainer users!
- 3. Basic information - github: https://github.com/chainer/chainerui - doc: https://docs.chainer.org/en/stable/ - MIT license - latest: v0.2.0 v0.3.0 (today!) - announce: - JP: https://research.preferred.jp/2017/12/chainerui-release/ - EN: https://preferredresearch.jp/2017/12/20/chainerui-release/
- 4. Getting Started Official document: http://chainerui.readthedocs.io/en/latest/getstart.html (JP) Tutorial by KIKAGAKU: https://qiita.com/yoshizaki_kkgk/items/2e4021c614529ab 9ba7b Thank you!
- 5. Quick start $ pip install chainerui $ chainerui db create $ chainerui db upgrade $ chainerui project create -d /path/to/results $ chainerui server → Demo! place to “log” file LogReport extension
- 6. Quick upgrade (to v0.3) $ # stop chainerui server $ pip install -U chainerui $ chainerui db upgrade $ chainerui server
- 7. What’s new, v0.3 - sampled log - more useful result table - performance tuning etc... - https://www.slideshare.net/pfi/chainer-ui-v02-v03 - https://github.com/chainer/chainerui/releases/tag/v0.3.0 → Let’s see!
- 8. Image API - ImageReport extension (v0.3~) - Experimental feature - API is not stable - only basic fucntion - no link to image page - /projects/{:project_id}/results/{:result_id}/images
- 9. examples/dcgan Example: DCGAN def out_generated_image(gen, dis, rows, cols, seed, dst): @chainer.training.make_extension() def make_image(trainer): np.random.seed(seed) n_images = rows * cols xp = gen.xp z = Variable(xp.asarray(gen.make_hidden(n_images))) with chainer.using_config('train', False): x = gen(z) x = chainer.backends.cuda.to_cpu(x.data) np.random.seed() x = np.asarray(np.clip(x * 255, 0.0, 255.0), dtype=np.uint8) _, _, H, W = x.shape x = x.reshape((rows, cols, 3, H, W)) x = x.transpose(0, 3, 1, 4, 2) x = x.reshape((rows * H, cols * W, 3)) preview_dir = '{}/preview'.format(dst) preview_path = preview_dir + '/image{:0>8}.png'.format(trainer.updater.iteration) if not os.path.exists(preview_dir): os.makedirs(preview_dir) Image.fromarray(x).save(preview_path) return make_image def main(): # ...snip trainer = training.Trainer( updater, (args.epoch, 'epoch'), out=args.out) trainer.extend( out_generated_image( gen, dis, 10, 10, args.seed, args.out), trigger=snapshot_interval) train_dcgan.py visualize.py
- 10. Example: DCGAN def out_generated_image(gen, dis, rows, cols, seed): @chainer.training.make_extension() def make_image(trainer): np.random.seed(seed) n_images = rows * cols xp = gen.xp z = Variable(xp.asarray(gen.make_hidden(n_images))) with chainer.using_config('train', False): x = gen(z) x = chainer.backends.cuda.to_cpu(x.data) np.random.seed() x = np.asarray(np.clip(x * 255, 0.0, 255.0), dtype=np.uint8) _, _, H, W = x.shape x = x.reshape((rows, cols, 3, H, W)) x = x.transpose(0, 3, 1, 4, 2) x = x.reshape((rows * H, cols * W, 3)) preview_dir = '{}/preview'.format(dst) preview_path = preview_dir + '/image{:0>8}.png'.format(trainer.updater.iteration) if not os.path.exists(preview_dir): os.makedirs(preview_dir) Image.fromarray(x).save(preview_path) return make_image def main(): # ...snip trainer = training.Trainer( updater, (args.epoch, 'epoch'), out=args.out) trainer.extend( out_generated_image( gen, dis, 10, 10, args.seed, args.out), trigger=snapshot_interval) chainerui.summary.image( x, row=rows) visualizer = out_generated_image(gen, dis, 10, 10, args.seed) trainer.extend(chainerui.extensions.ImageReport( trigger=(1, 'epoch'), image_generator=visualizer))
- 12. Example: VAE (MNIST) # Run the training trainer.run() # Visualize the results def save_images(x, filename): # ...snip model.to_cpu() train_ind = [1, 3, 5, 10, 2, 0, 13, 15, 17] x = chainer.Variable(np.asarray(train[train_ind])) with chainer.using_config('train', False), chainer.no_backprop_mode(): x1 = model(x) save_images(x.data, os.path.join(args.out, 'train')) save_images(x1.data, os.path.join(args.out, 'train_reconstructed')) test_ind = [3, 2, 1, 18, 4, 8, 11, 17, 61] x = chainer.Variable(np.asarray(test[test_ind])) with chainer.using_config('train', False), chainer.no_backprop_mode(): x1 = model(x) save_images(x.data, os.path.join(args.out, 'test')) save_images(x1.data, os.path.join(args.out, 'test_reconstructed')) # draw images from randomly sampled z z = chainer.Variable( np.random.normal(0, 1, (9, args.dimz)).astype(np.float32)) x = model.decode(z) save_images(x.data, os.path.join(args.out, 'sampled')) examples/vae train_vae.py
- 13. Example: VAE (MNIST) # Run the training trainer.run() # Visualize the results def save_images(x, filename): # ...snip model.to_cpu() train_ind = [1, 3, 5, 10, 2, 0, 13, 15, 17] x = chainer.Variable(np.asarray(train[train_ind])) with chainer.using_config('train', False), chainer.no_backprop_mode(): x1 = model(x) save_images(x.data, os.path.join(args.out, 'train')) save_images(x1.data, os.path.join(args.out, 'train_reconstructed')) test_ind = [3, 2, 1, 18, 4, 8, 11, 17, 61] x = chainer.Variable(np.asarray(test[test_ind])) with chainer.using_config('train', False), chainer.no_backprop_mode(): x1 = model(x) save_images(x.data, os.path.join(args.out, 'test')) save_images(x1.data, os.path.join(args.out, 'test_reconstructed')) # draw images from randomly sampled z z = chainer.Variable( np.random.normal(0, 1, (9, args.dimz)).astype(np.float32)) x = model.decode(z) save_images(x.data, os.path.join(args.out, 'sampled')) def visualize(trainer): train_ind = [1, 3, 5, 10, 2, 0, 13, 15, 17] x = chainer.Variable(np.asarray(train[train_ind])) with chainer.using_config('train', False), chainer.no_backprop_mode(): x1 = model(x) def convert(x): return x.reshape(9, 28, 28).transpose(0, 2, 1) summary.image(convert(x), name='train', row=3) summary.image(convert(x1), name='train_reconstructed', row=3) test_ind = [3, 2, 1, 18, 4, 8, 11, 17, 61] x = chainer.Variable(np.asarray(test[test_ind])) with chainer.using_config('train', False), chainer.no_backprop_mode(): x1 = model(x) summary.image(convert(x), name='test', row=3) summary.image(convert(x1), name='test_reconstructed', row=3) # draw images from randomly sampled z z = chainer.Variable( np.random.normal(0, 1, (9, args.dimz)).astype(np.float32)) x = model.decode(z) summary.image(convert(x), name='sampled', row=3) trainer.extend(ImageReport(image_generator=visualize)) # Run the training trainer.run()
- 15. examples/pix2pix Example: pix2pix def out_image(updater, enc, dec, rows, cols, seed, dst): @chainer.training.make_extension() def make_image(trainer): # ...snip def save_image(x, name, mode=None): # ...snip x = np.asarray(np.clip(gen_all * 128 + 128, 0.0, 255.0), dtype=np.uint8) save_image(x, "gen") x = np.ones((n_images, 3, w_in, w_in)).astype(np.uint8)*255 x[:,0,:,:] = 0 for i in range(12): x[:,0,:,:] += np.uint8(15*i*in_all[:,i,:,:]) save_image(x, "in", mode='HSV') x = np.asarray(np.clip(gt_all * 128+128, 0.0, 255.0), dtype=np.uint8) save_image(x, "gt") def main(): # ...snip trainer = training.Trainer( updater, (args.epoch, 'epoch'), out=args.out) trainer.extend( out_image( updater, enc, dec, 5, 5, args.seed, args.out), trigger=snapshot_interval) train_facade.py facade_visualizer.py
- 16. Example: pix2pix def out_image(updater, enc, dec, rows, cols, seed, dst): @chainer.training.make_extension() def make_image(trainer): # ...snip def save_image(x, name, mode=None): # ...snip x = np.asarray(np.clip(gen_all * 128 + 128, 0.0, 255.0), dtype=np.uint8) save_image(x, "gen") x = np.ones((n_images, 3, w_in, w_in)).astype(np.uint8)*255 x[:,0,:,:] = 0 for i in range(12): x[:,0,:,:] += np.uint8(15*i*in_all[:,i,:,:]) save_image(x, "in", mode='HSV') x = np.asarray(np.clip(gt_all * 128+128, 0.0, 255.0), dtype=np.uint8) save_image(x, "gt") def main(): # ...snip trainer = training.Trainer( updater, (args.epoch, 'epoch'), out=args.out) trainer.extend( out_image( updater, enc, dec, 5, 5, args.seed, args.out), trigger=snapshot_interval) visualizer = out_image(updater, enc, dec, args.visualize_batchsize, args.rows, args.seed) trainer.extend(chainerui.extensions.ImageReport( trigger=snapshot_interval, image_generator=visualizer)) summary.image(gen_all, name='gen', row=rows) summary.image(x, name='in', row=rows, mode='HSV') summary.image(gt_all, name='gt', row=rows)
- 19. ImageReport TODO - Issue#101 - DB cache / lazy load / document etc... - API usability - Show images with label - Support grayscale - Support hidden layer?
- 20. Roadmap - v0.3.1 / v0.4 - output chart (PR#112) - print(‘msg’) → logger - improve UX - easy to distinguish each log chart - deal with too many columns or keys