Dmitry Gordin
Dmitry Gordin
You call loadJSON twice: in onCreate and onStart, what is the sense to do that? The same problem with compositeDisposable – you call it in onStop as well as in...
You pass reference to activity (context) to static variable [activity](https://github.com/lawloretienne/ImageGallery/blob/master/sample/src/main/java/com/etiennelawlor/imagegallery/activities/MainActivity.java#L79) [static variable](https://github.com/lawloretienne/ImageGallery/blob/master/library/src/main/java/com/etiennelawlor/imagegallery/library/activities/FullScreenImageGalleryActivity.java#L34)
## 🐞Describe the bug Unable to make flexible input size when converting from pytorch. I think it's related to https://github.com/apple/coremltools/issues/890 https://github.com/apple/coremltools/issues/880 and https://github.com/apple/coremltools/issues/756. I extend this to input ImageType and...
Hey, looks like typo in [about_scope.py:73](https://github.com/gregmalcolm/python_koans/blob/75b749221afea775b9c23d84a26b9790ea7bd09e/python3/koans/about_scope.py#L73) ```python def test_incrementing_with_local_counter(self): global counter start = counter self.increment_using_local_counter(start) # should be `counter` instead of `start` self.assertEqual(False, counter == start + 1) ``` Yes,...
tested with python2 `conda create -n tf_older python=2`
Hello, first of all many thanks for you excellent work, with latest release it really become capable of reconstructing faces! I have two questions about how masks for use_face_segmentation_condition are...
It's more convenient to have autosuggestion and menu button in bot UI: 
Add int8 quantised model and compare their accuracy + speed on different frameworks. Compare baseline converted models with quantisation-aware fine tuning (eg in MNN)
Try to adopt gpu compatibility logic from TFLite to other frameworks https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/experimental/acceleration/compatibility
- [x] MNN - [x] NCNN - [ ] ONNX Runtime - [ ] OpenCV?