Update from upstream #3
Merged
Conversation
This file contains 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
A previous fix to let validation run across more than one batch caused an issue with multi-GPU training. The issue seems to be in how Keras averages loss and metric values, where it expects them to be scalars rather than arrays. This fix causes scalar outputs from a model to remain scalar in multi-GPU training.
TF replaced keep_dims with keepdims a while ago and now shows a warning when using the old name.
Fixed the typo in the headline of the README.md file. "Spash" should be "Splash"
Reported here: #500
Print a message when re-starting from saved epoch
This allows one to set a callable in Config.BACKBONE to use a custom backbone model.
…t 'pip3 install imgaug' instructions
…--weights=last (or --model=last) to resume trainingbut the weights are not found now it raises a clear error message.
Improve previous commit to not break on older versions of Keras.
Add an optional parameter for calling a list of keras.callbacks to be add to the original list.
Add the possibility to exclude some sources from augmentation by passing a list of sources. This is useful when you want to retrain a model having few images.
VIA has changed JSON formatting in later versions. Now instead of a dictionary, "regions" has a list, see the issue #928
- Current implementation creates self.log_dir in set_log_dir() function, which creates an empty log directory if none exists. This causes find_last() to fail after creating a model because it finds this new empty directory instead of the previous training directory. - New implementation moves log_dir creation to the train() function to ensure it is only created when it will be used.
Unified regex expression for both, Linux and Windows.
Fix bugs of not showing boxes in 1.b RPN Predictions. TF 1.9 introduces "ROI/rpn_non_max_suppression/NonMaxSuppressionV3:0", so the original code can't work.
Fixed comment on GPU_COUNT
… use Mask_RCNN for non 3-channel images
For PyramidROIAlign's output shape, use pool_height and pool_width instead of height and width to avoid confusion with those of feature_maps.
1. fix the comment on output shape in fpn_classifier_graph 2. unify NUM_CLASSES and num_classes to NUM_CLASSES 3. unify boxes, num_boxes, num_rois, roi_count to num_rois 4. use more specific POOL_SIZE and MASK_ POOL_SIZE to replace pool_height and pool_width
As discussed in: #919
1. fix description on window 2. fix output shape of detection layer
skimage generates different warnings depending on the version. This wrapper function calls skimage.tranform.resize() with the right parameter for each version.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
No description provided.