Eric J

Results 6 comments of Eric J

Implementation done on my side (ResNext-50 cardinal = 32m ResNext-101 cardinal = 32). Testing it. Will update you if it works

see [model.py](https://github.com/ericj974/Mask_RCNN/blob/master/model.py) and implementation of resnet_graph

@paulcx @chenyuZha sorry for my late reply. Actually you cannot load the h5 file (mask_rcnn_coco.h5) since it assumes a standard resnet and not resnext as backend encoder. You will have...

@ps48 This will be possible once #167 is complete no (python layer not serializable) ?

@Surmeh Code [here](https://github.com/ericj974/Mask_RCNN/blob/master/scripts/export_model.py)

I should have commented the function. It's a config instance used for inference (being related to the config used for training, albeit not exactly the same). Look at train_shapes.ipynb for...