Open
Conversation
Add test infrastructure
* ignore pycharm idea file * Add img ids for S2L1C and S2L2A.
* Intial refactoring of training script. * Rename create_random file. * Create a data_utils for data handeling. * Refactor create_patches to utlize data_utils. * Use lowercase naming * Refactor s2_tiles_superres to utlize data_utils class * Fix some of the linting errors * Add unittests for data_utils. * Add two more unittests * Update the naming of files. * Use typing more defined parameters of the method
* Freeze keras version to be compatible with tf1 * minor refactoring * Revert naming of saved patches. * Uncomment the commented line * Add tests for inference * Black update and fix some liniting issues.
* Stub out patches tests * Fix shape of dataset * Explicitly pass patch size and border * Update defaults to working params * Add aditional asserts * Add multiple tests * Skip long running tests * Add blockutils to requirements * Skip too long tests * Add fstring linter * Fix unused vars * Disable unary operator * Add description * Use get_patches function * Add description * Use get_patches * Import patches from context * Add get_random_patches methods separate from save method * Fix del * Add helper methods * Apply patch utils * Remove hardcoded patch sizes * Add typing * Remove unused variable * Add typing
* Fix import and data_path * Fix path to xml file * Add data_name to class * Handle unever array case in downsizing * Add data_name instance var * Format * Format * Add generate patches script * Add logger * Add sys * Add md file for patch gen * Add test imgs ids for L1C * Add test images L2A * Add test commands * Remove xtra - * Remove duplicated test_data * remove / * Fix linter issues * Fix duplicated code * Disable tuple unbalance error * Disable type for var input_shape
* Remove package pinning * Add missing reqs * Use input path to fetch data * Add CLI to create val train * Add glob * Add os lib * Use args.path * Return args * Format * Change import order * Set channels first in layer * Use distributed strategy for multiple gpus * Add scope to inference * Format * Add skip inference if no GPU available
* Add copied over AESR model * Simplify model creation, add tests * Add AESR model option * format * Fix linter * Add run_60 to val_patch
* Add new AESR model example (20 - 10m) * load AESR model from file * rename model file * Remove deep argument * Add another placeholder for 60m
* Add quality metrics. * Rename the filename * Add evaluation script * use load_model mechanism * Use image-similarity-measures package. * Remove redundant var * Remove pdb
* Make sure patch size is the same * Add all instructions for patch generation * Add adpated rmse * Add comparison with bicubic * fix bug * add bic flag * Add eval code * Format * Add scale * Add all metrics * Fix linter * Add one pixel to size of d20 due to change in patch generation * format * Fix out array size * Fix linter
* Add srcnn, rednet and resnet to model zoo * Fix linter issues * Add choices in command line * Add imports * Replace PreLu with ReLu in ResNetSR
* Add uiq adapted metric * Parametrize metrics comming from image-similarity-metrics
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add some extra commnets.