7924cc4a85
Improve display and filenames for saving output.
9 years ago
93e5a41d9a
Fix and optimize pre-processing of images.
9 years ago
11ba505252
Fix for gradient clipping code.
9 years ago
cf65207a2e
Use full range of tanh output rather than [-0.5, +0.5], avoids clipping.
9 years ago
c610623b11
Add gradient clipping, helpful for preventing problems with extreme parameters/architectures.
9 years ago
f2494f8078
Add new downscale layers, separate from upscale steps. Renamed --scales to --zoom for inference.
9 years ago
064f9dd589
Add three image pre-processing options, improve loading code.
9 years ago
5ef872b876
Add warning for files that may be too large for 4x.
9 years ago
17fcad8d28
Refactor of changes related to training.
9 years ago
2b67daedb6
Merge pull request #12 from dribnet/generic_seeds
...
Move generation of seeds out of training network.
9 years ago
cad5eff572
Merge pull request #11 from dribnet/save_every_epoch
...
Added --save-every-epoch option
9 years ago
fcc5e87858
Merge pull request #4 from dribnet/valid_dir
...
Add valid dir when necessary.
9 years ago
8f5167d235
Fix enhancer.process to pass img, seed
9 years ago
37cb208374
Move generation of seeds out of training network
...
This moves the generation of the image seeds out of the
training network and into the DataLoader. Currently seeds
are computed as bilinear downsamplings of the original image.
This is almost functionly equivalent to the version
it replaces, but opens up new possibilities at training
time because the seeds are now decoupled from the netork.
For example, seeds could be made with different interpolations
or even with other transformations such as image compression.
9 years ago
b05ee6ad08
Added --save-every-epoch option
9 years ago
c5053806bd
Add valid dir when necessary
9 years ago
eb25e737cf
Fix duplicate param definition
9 years ago
203917d122
Switch default to small model to reduce memory usage.
9 years ago
4c55c48f62
Add argument for specifying training images, cleaned up file handling.
9 years ago
b1c054ce9f
Improve the README for applying and training models.
9 years ago
f868514be3
Improve code for simply applying super-resolution.
9 years ago
c456221cb5
Experiment with recursive super-resolution and weight reuse, mixed results.
9 years ago
87304c93a6
Use traditional learning rate decaying rather than fast-restarts, works better when training continuously adapting GAN.
9 years ago
3809e9b02a
Add loading of images into a buffer, using multiple fragments per JPG loaded. Works well with larger datasets like OpenImages, fully GPU bound.
9 years ago
619fad7f3c
Add loading parameters from saved models. Clean up learning-rate code.
9 years ago
f978f058dd
Add descriptions for command-line arguments.
9 years ago
d8c9292b80
Tweak code for generalized super-resolution.
9 years ago
9558a11397
Add command-line for super-resolving images without training.
9 years ago
03a6813e95
Enable adversarial loss during training.
9 years ago
6542f435b4
Stabilize the training, tuned the architecture.
9 years ago
b52530cf20
Add support for PRELU (default), optional load/save.
9 years ago
4d82c7f157
Improve console output.
9 years ago
8770113f9a
Add support for loading/saving models. Fixed regressions.
9 years ago
58e1bed4a6
Improve display and code structure.
9 years ago
749b467f94
Switch to sub-pixel deconvolution layer.
9 years ago
9f13695050
Add discriminator network too.
9 years ago
3f24714039
Add residual blocks to generator.
9 years ago
058e3d3b9e
Add simple but working prototype, perceptual loss.
9 years ago
Alex J. Champandard
Tom White
Ondřej Machulda