bkpgr35

Why only none-linear activation will be accepted?

1

Hi, there are some linear activation layers in my model. Since the keras-surgeon won't take linear activation layer into account, the pruning for my model failed. Here is the code...

16g gpu memory still got run out of memory error

8

Hi, I tried to run the command like python -m keras_segmentation train \ --checkpoints_path="path_to_checkpoints" \ --train_images="dataset1/images_prepped_train/" \ --train_annotations="dataset1/annotations_prepped_train/" \ --val_images="dataset1/images_prepped_test/" \ --val_annotations="dataset1/annotations_prepped_test/" \ --n_classes=50 \ --input_height=320 \ --input_width=640 \ --model_name="fcn_8_resnet50"...

plugin layer fails

2

Hi, thank you for your code. I tried to implement a upsample plugin layer the way you did, but I kept receiving errors as Segmentation fault.  Could you give...

Hi, thank you for your work. One thing I want to point out here is that you have some tiny difference compared with original implementaion, which may lead to more...