- 01 4月, 2019 1 次提交
-
-
由 cclauss 提交于
[flake8](http://flake8.pycqa.org) testing of https://github.com/matterport/Mask_RCNN on Python 3.7.1 $ __flake8 . --count --select=E9,F63,F72,F82 --show-source --statistics__ ``` ./mrcnn/utils.py:381:9: F821 undefined name 'logging' logging.warning("You are using the default load_mask(), maybe you need to define your own one.") ^ ./mrcnn/model.py:2359:12: F632 use ==/!= to compare str, bytes, and int literals if os.name is 'nt': ^ 1 F632 use ==/!= to compare str, bytes, and int literals 1 F821 undefined name 'logging' 2 ``` __E901,E999,F821,F822,F823__ are the "_showstopper_" [flake8](http://flake8.pycqa.org) issues that can halt the runtime with a SyntaxError, NameError, etc. These 5 are different from most other flake8 issues which are merely "style violations" -- useful for readability but they do not effect runtime safety. * F821: undefined name `name` * F822: undefined name `name` in `__all__` * F823: local variable name referenced before assignment * E901: SyntaxError or IndentationError * E999: SyntaxError -- failed to compile a file into an Abstract Syntax Tree
-
- 04 3月, 2019 2 次提交
-
-
由 Karanbir Chahal 提交于
Fixed the Todo for matching multiple anchors with the same IOU, and setting their value to 1. The previous version only picked the first anchor that had a maximum IOU. Now, if multiple anchors had the same IOU < 0.7, all of them will be set to a foreground class.
-
由 Zhen Ju 提交于
Replace 256*256*3 with 256x256x3, since the '*' won't be displayed in Markdown
-
- 10 2月, 2019 1 次提交
-
-
由 xelmirage 提交于
use logging.warning() instead of print()
-
- 04 2月, 2019 2 次提交
-
-
由 Yanfeng Liu 提交于
Remove unused code
-
由 Manas Satish Bedmutha 提交于
Reference to #1255
-
- 28 1月, 2019 2 次提交
-
-
-
由 keineahnung2345 提交于
-
- 22 1月, 2019 1 次提交
-
-
由 keineahnung2345 提交于
Fix visualize activations (Squashed 4 commits by @keineahnung2345) # Get activations of a few sample layers activations = model.run_graph([image], [ ("input_image", model.keras_model.get_layer("input_image").output) ]) leads to the error: InvalidArgumentError: input_image:0 is both fed and fetched. Revise the code according to https://stackoverflow.com/questions/39307108/placeholder-20-is-both-fed-and-fetched
-
- 28 10月, 2018 5 次提交
-
-
由 mowoe 提交于
Fix typo "ceate" to "create"
-
由 keineahnung2345 提交于
In compute_overlaps_masks(), the code checking the shape of masks1 and masks2 is not correct. 1. It should check masks' last dimension instead of first dimension to determine whether it's empty or not 2. When masks1 or masks2 is empty, it should return a zero array of shape (masks1.shape[-1], masks2.shape[-1])
-
由 marluca 提交于
Valid index 0 is not regarded, leading to possibly more prediction_matches than grountruh_matches and recall values higher than 1.
-
由 keineahnung2345 提交于
In current version of log(), when you pass a zero size array, it will throw an error: `ValueError: Unknown format code 'f' for object of type 'str'`. This PR fixes it.
-
由 keineahnung2345 提交于
pass name=None to tf.boolean_mask will lead to ValueError: At least one of name (None) and default_name (None) must be provided.
-
- 29 9月, 2018 3 次提交
-
-
由 keineahnung2345 提交于
Fix the input shape of anchors in ProposalLayer and use "num_anchors" to replace "anchors" to avoid confusing
-
由 keineahnung2345 提交于
* fix comment in DetectionTargetLayer * fix comment of target_deltas' shape * make parenthesis compatible
-
由 Waleed 提交于
-
- 28 9月, 2018 7 次提交
-
-
由 Waleed 提交于
-
由 Waleed 提交于
skimage generates different warnings depending on the version. This wrapper function calls skimage.tranform.resize() with the right parameter for each version.
-
由 lichi huang 提交于
-
由 keineahnung2345 提交于
1. fix description on window 2. fix output shape of detection layer
-
由 Waleed 提交于
As discussed in: https://github.com/matterport/Mask_RCNN/issues/919
-
由 keineahnung2345 提交于
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
-
由 keineahnung2345 提交于
For PyramidROIAlign's output shape, use pool_height and pool_width instead of height and width to avoid confusion with those of feature_maps.
-
- 22 9月, 2018 4 次提交
-
-
由 Waleed 提交于
-
由 Waleed 提交于
-
由 Waleed 提交于
-
由 Matthew Moore 提交于
add IMAGE_CHANNEL_COUNT class variable to config to make it easier to use Mask_RCNN for non 3-channel images
-
- 21 9月, 2018 12 次提交
-
-
由 Max Frei 提交于
Fixed comment on GPU_COUNT
-
由 Waleed 提交于
-
由 keineahnung2345 提交于
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.
-
由 Viredery 提交于
-
由 Waleed 提交于
-
由 Max Frei 提交于
Unified regex expression for both, Linux and Windows.
-
由 Adam Kelly 提交于
- 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.
-
由 keineahnung2345 提交于
-
由 Waleed 提交于
-
由 Shivam K. Thakkar 提交于
VIA has changed JSON formatting in later versions. Now instead of a dictionary, "regions" has a list, see the issue #928
-
由 keineahnung2345 提交于
-
由 keineahnung2345 提交于
-