- 28 1月, 2019 1 次提交
-
-
由 keineahnung2345 提交于
-
- 22 9月, 2018 2 次提交
-
-
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 2 次提交
-
-
由 Max Frei 提交于
Fixed comment on GPU_COUNT
-
由 keineahnung2345 提交于
-
- 12 7月, 2018 1 次提交
-
-
由 Corey Hu 提交于
-
- 05 6月, 2018 2 次提交
-
-
由 Julien Rebetez 提交于
This allows one to set a callable in Config.BACKBONE to use a custom backbone model.
-
由 Julien Rebetez 提交于
-
- 16 4月, 2018 1 次提交
-
-
由 Kolesnikov Sergey 提交于
-
- 09 4月, 2018 1 次提交
-
-
由 Waleed Abdulla 提交于
config.IMAGE_RESIZE_MODE = "crop" can be used in training only to pick random crops from training images.
-
- 07 4月, 2018 2 次提交
-
-
由 Waleed Abdulla 提交于
This is useful to run prediction on images of variable sizes without resizing them to a fixed size. While using mode=“none” is another option, it requires that you pre-process your images to ensure the width and height are multiples of 64. This mode handles that automatically.
-
由 jirka 提交于
* create package mrcnn * move notebooks to samples
-
- 06 4月, 2018 3 次提交
-
-
由 Waleed Abdulla 提交于
-
由 Waleed Abdulla 提交于
-
由 Waleed Abdulla 提交于
A step towards supporting detection on different image sizes.
-
- 04 4月, 2018 1 次提交
-
-
由 Waleed Abdulla 提交于
This doesn’t change the functionality, other than cleaning up the code to prepare for future changes to support detection on different image sizes.
-
- 02 4月, 2018 2 次提交
-
-
由 Waleed Abdulla 提交于
Allows using a config variable, TRAIN_NB, rather that updating the BatchNorm class.
-
由 Waleed Abdulla 提交于
-
- 27 3月, 2018 1 次提交
-
-
由 Waleed Abdulla 提交于
-
- 16 3月, 2018 1 次提交
-
-
由 Waleed Abdulla 提交于
-
- 26 11月, 2017 2 次提交
-
-
由 Waleed Abdulla 提交于
* Remove dropout layer. Unnecessary. * Reduce anchor stride from 2 to 1 * Increase training proposals to 200/image * Reduce pre-NMS limit to 6000 * Improve computing proposal post:neg ratio * Updated COCO training schedule
-
由 Waleed Abdulla 提交于
Reduces odds of weight explosion.
-
- 11 11月, 2017 1 次提交
-
-
由 Waleed Abdulla 提交于
-
- 06 11月, 2017 1 次提交
-
-
由 Waleed Abdulla 提交于
-
- 02 11月, 2017 1 次提交
-
-
由 Waleed Abdulla 提交于
-