fanwuyang/neural-enhance-super-resolution
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
86 Commits 1 Branch 0 Tags
9d8ab0ea8e96ee238e6b3e4b65efa50e0a3fc6da
Commit Graph
78 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Alex J. ChampandardandGitHub 9d8ab0ea8e Merge pull request #69 from alexjc/v0.3 
Release 0.3
 2016-11-10 17:29:18 +01:00
Alex J. Champandard 80d7b57bec Prepare build scripts for merge and update README. 2016-11-10 17:20:20 +01:00
Alex J. Champandard b706599cb1 Fix alias for bash and zsh, Closes #54. Add standalone alias-free docker example, Closes #46. 2016-11-10 17:06:52 +01:00
Alex J. Champandard c03a0b7fa3 Fix for trained models loaded from script directory. Closes #67. 2016-11-10 16:55:56 +01:00
Alex J. Champandard a69d2ae060 Add histogram color matching, enabled with --rendering-histogram. 2016-11-10 16:45:30 +01:00
Alex J. Champandard 965bd55090 Add new model selection (by image type and 'enhance' operation) and parameters and documentation in README. 2016-11-10 13:16:40 +01:00
Alex J. Champandard e6120878c6 Minor rework of the training parameters. 2016-11-09 17:04:35 +01:00
Alex J. Champandard 0d4621df0a Simplify architecture outside of convolution blocks for speed, improve training code. 2016-11-08 17:41:28 +01:00
Alex J. Champandard c8e805667f Fix for padding in convolution. 2016-11-08 17:15:54 +01:00
Alex J. Champandard 2a29fc954b Buffer chunks of images proportionally to size. 2016-11-08 17:15:41 +01:00
Alex J. Champandard da354f3e55 Remove reflection layer, important but not the bottleneck right now and quite slower. 2016-11-04 14:29:15 +01:00
Alex J. Champandard 9bba9850d5 Improve pre-processing steps to include more randomness: scales, blur... 2016-11-04 14:28:37 +01:00
Alex J. Champandard 149ae4e566 Update training parameters. 2016-11-04 00:34:52 +01:00
Alex J. Champandard de047d6a74 Fix for images that are not multiples of 2 or 4, depending on the rescaling. 2016-11-04 00:32:08 +01:00
Alex J. Champandard 29bfe58d73 Merged documentation changes. 2016-11-04 00:03:21 +01:00
Alex J. ChampandardandGitHub 9a228c1d78 Merge pull request #44 from wieczorek1990/master 
Fixed typo.
 2016-11-03 23:58:24 +01:00
Alex J. ChampandardandGitHub b24fa7490d Merge pull request #47 from alexjc/v0.2 
Release 0.2: Tiled Rendering, 1:1 Noise/Blur Fixing
 2016-11-03 22:33:15 +01:00
Alex J. Champandard 03914db364 Fix formatting, minor tweaks to Docker build files for release. 2016-11-03 22:27:28 +01:00
Alex J. Champandard 448e7b93dc Fix progress output when tiled rendering, changed default zoom level. 2016-11-03 22:01:08 +01:00
Alex J. Champandard cabaaeeefe Add training scripts for networks currently being trained, for release v0.2. 2016-11-03 20:12:58 +01:00
Alex J. Champandard 1ad40b6d71 Merge branch 'master' into v0.2 2016-11-03 19:27:10 +01:00
Alex J. Champandard ac49676415 Add tiled rendering with padding, no feather-blending but looks good enough. 2016-11-03 19:26:55 +01:00
Alex J. Champandard 095fe42dc3 Add tiled rendering, currently with no padding for each tile. 2016-11-03 10:35:43 +01:00
Alex J. Champandard d18c08f1b5 Integrated reflection padding instead of zero padding for extra quality during training and inference. 2016-11-02 21:39:34 +01:00
Alex J. Champandard 90c0b7ea43 Fix padding code, more reliable for specific upscale/downscale combinations. 2016-11-02 13:03:00 +01:00
Alex J. Champandard 3b2a6b9d8d Add extra padding on input to avoid zero-padding. Experiment with training values from ENet (segmentation). 2016-11-02 12:08:07 +01:00
Alex J. Champandard 7924cc4a85 Improve display and filenames for saving output. 2016-11-02 10:16:31 +01:00
Alex J. Champandard 93e5a41d9a Fix and optimize pre-processing of images. 2016-11-01 20:40:10 +01:00
Alex J. Champandard 11ba505252 Fix for gradient clipping code. 2016-11-01 16:04:33 +01:00
Alex J. Champandard cf65207a2e Use full range of tanh output rather than [-0.5, +0.5], avoids clipping. 2016-11-01 16:02:18 +01:00
Alex J. Champandard 0c31e53731 Fix suggested alias for relative paths. Closes #37 #28. 2016-11-01 15:11:55 +01:00
Alex J. Champandard 34f8e629c2 Improve the alias used to invoke docker, so it's more robust to directory locations and input paths. 2016-11-01 09:54:58 +01:00
Alex J. Champandard c610623b11 Add gradient clipping, helpful for preventing problems with extreme parameters/architectures. 2016-10-31 21:38:23 +01:00
Alex J. Champandard 02d2fca6c5 Corrected value for adversarial loss. Don't refactor math the day after stopping coffee. 2016-10-31 20:55:11 +01:00
Alex J. Champandard f2494f8078 Add new downscale layers, separate from upscale steps. Renamed --scales to --zoom for inference. 2016-10-31 13:49:17 +01:00
Alex J. ChampandardandGitHub 0c9937a317 Merge pull request #22 from msfeldstein/master 
Remove cnmem theano flag.
 2016-10-31 13:29:31 +01:00
Alex J. Champandard 064f9dd589 Add three image pre-processing options, improve loading code. 2016-10-31 06:21:52 +01:00
Alex J. Champandard 5ef872b876 Add warning for files that may be too large for 4x. 2016-10-30 20:45:10 +01:00
Alex J. ChampandardandGitHub a5ad2c25e6 Merge pull request #18 from alexjc/training 
Training Improvements
 2016-10-30 20:29:13 +01:00
Alex J. Champandard 17fcad8d28 Refactor of changes related to training. 2016-10-30 20:26:03 +01:00
Alex J. ChampandardandGitHub 2b67daedb6 Merge pull request #12 from dribnet/generic_seeds 
Move generation of seeds out of training network.
 2016-10-30 17:19:33 +01:00
Alex J. ChampandardandGitHub cad5eff572 Merge pull request #11 from dribnet/save_every_epoch 
Added --save-every-epoch option
 2016-10-30 17:18:33 +01:00
Alex J. ChampandardandGitHub a9b0cd9887 Merge pull request #9 from zuphilip/patch-1 
Fix some typos in README.
 2016-10-30 17:07:15 +01:00
Alex J. ChampandardandGitHub fcc5e87858 Merge pull request #4 from dribnet/valid_dir 
Add valid dir when necessary.
 2016-10-30 17:06:33 +01:00
Alex J. ChampandardandGitHub 1478977f18 Merge pull request #10 from OndraM/fix-duplicate-param 
Fix duplicate param definition.
 2016-10-30 16:53:48 +01:00
Alex J. Champandard f68f04fb1c Improve instructions to train custom models so a new file is output and existing one is not loaded. Use --model parameter! 2016-10-30 10:50:57 +01:00
Alex J. Champandard 203917d122 Switch default to small model to reduce memory usage. 2016-10-30 10:49:23 +01:00
Alex J. Champandard 2b5fc8f51d Add docker instructions, fix for slow compute in CPU image. 2016-10-30 02:04:28 +02:00
Alex J. Champandard 74cb95609e Fix for docker build using latest Miniconda and Python 3.5 explicitly. 2016-10-29 23:57:08 +02:00
Alex J. Champandard 99c767b7e2 Add docker configuration files for CPU and GPU. 2016-10-29 22:29:30 +02:00
Alex J. Champandard bf22450b8d Update documentation for new --train usage, minor improvements. 2016-10-29 14:15:24 +02:00
Alex J. Champandard 4c55c48f62 Add argument for specifying training images, cleaned up file handling. 2016-10-29 12:39:07 +02:00
Alex J. Champandard 1c38f2ca31 New meme-friendly image and link to demo. 2016-10-29 01:35:44 +02:00
Alex J. Champandard b1c054ce9f Improve the README for applying and training models. 2016-10-29 00:39:32 +02:00
Alex J. Champandard f868514be3 Improve code for simply applying super-resolution. 2016-10-29 00:18:44 +02:00
Alex J. Champandard 30534c6dd1 Add old station example, fix bank example. 2016-10-28 22:55:10 +02:00
Alex J. Champandard 801a4707f4 Improve README and the visual examples. 2016-10-28 16:29:37 +02:00
Alex J. Champandard 39e12ea205 Add example GIF to the README, tweak text. 2016-10-28 14:38:28 +02:00
Alex J. Champandard c456221cb5 Experiment with recursive super-resolution and weight reuse, mixed results. 2016-10-28 04:28:30 +02:00
Alex J. Champandard 87304c93a6 Use traditional learning rate decaying rather than fast-restarts, works better when training continuously adapting GAN. 2016-10-28 04:27:17 +02:00
Alex J. Champandard 3809e9b02a Add loading of images into a buffer, using multiple fragments per JPG loaded. Works well with larger datasets like OpenImages, fully GPU bound. 2016-10-28 04:25:10 +02:00
Alex J. Champandard 619fad7f3c Add loading parameters from saved models. Clean up learning-rate code. 2016-10-11 17:24:10 +02:00
Alex J. Champandard bb3b24b04c Add README and requirements file. 2016-10-11 17:16:06 +02:00
Alex J. Champandard f978f058dd Add descriptions for command-line arguments. 2016-10-11 11:12:49 +02:00
Alex J. Champandard d8c9292b80 Tweak code for generalized super-resolution. 2016-10-11 08:59:42 +02:00
Alex J. Champandard 9558a11397 Add command-line for super-resolving images without training. 2016-10-07 21:05:38 +02:00
Alex J. Champandard 03a6813e95 Enable adversarial loss during training. 2016-10-05 14:52:28 +02:00
Alex J. Champandard 6542f435b4 Stabilize the training, tuned the architecture. 2016-10-05 00:27:26 +02:00
Alex J. Champandard 4580e5531a Add .gitignore and removed symlink. 2016-10-04 13:19:53 +02:00
Alex J. Champandard b52530cf20 Add support for PRELU (default), optional load/save. 2016-10-04 11:25:03 +02:00
Alex J. Champandard 4d82c7f157 Improve console output. 2016-10-04 02:16:34 +02:00
Alex J. Champandard 8770113f9a Add support for loading/saving models. Fixed regressions. 2016-10-04 01:40:30 +02:00
Alex J. Champandard 58e1bed4a6 Improve display and code structure. 2016-10-03 22:17:37 +02:00
Alex J. Champandard 749b467f94 Switch to sub-pixel deconvolution layer. 2016-10-02 21:25:02 +02:00
Alex J. Champandard 9f13695050 Add discriminator network too. 2016-10-02 14:01:51 +02:00
Alex J. Champandard 3f24714039 Add residual blocks to generator. 2016-10-02 14:01:10 +02:00
Alex J. Champandard 058e3d3b9e Add simple but working prototype, perceptual loss. 2016-10-01 21:46:32 +02:00
Alex J. Champandard c36e677041 Initial commit 2016-10-01 15:01:50 +02:00