omerbrandis

build of version 1.7.1 fails

11

hello, I'm unable to perform Drogon installattion: git clone https://github.com/an-tao/drogon - works cd drogon - works **but git submodule update --init failed with : fatal: reference is not a tree:...

inference (centermask_demo) showing mask data only for very few objects.

1

hello, I've trained centermask on my own dataset. used several versions of centermask_v configs (19,39,99). (all of them stalled at around loss = 0.65 .) I've executed centermask_demo on the...

hi , useage instructions and test_net.py code are misleading: cfg.merge_from_file(args.config_file) cfg.merge_from_list(args.opts) cfg.freeze() in practice , code in maskrcnn_bechmark/utils/checkpoint.py , loads the last existing checkpoint if present: def load(self, f=None): **if...

KeyboardInterrupt in train_net does not kill all processes.

1

hi, pressing ctrl+c during execution of tools/train_net.py does not kill all the spawned processes. ( this later leads to cuda out of memory error on the following re-executions of the...

hello, I'm trying to use the application in a docker container. i've downladed jetbrains/projector-webstorm:latest , installed all the requirements, managed to open webstorm , and with it the bat-3d project,...

hello , ( noticed some other "issues" with building this repo with other lib versions , also considering that both pcl 1.8.0 and vtk 8.1 are not available any more...

have been unable to visualize dense layer on graphs/dataSets

2

hello, i've managed to execute the visualize sense layer example, but I have not manged to reproduce results using other graphs (like the current [tensorflow classification tutorial graph](https://www.tensorflow.org/tutorials/images/classification) ) on...

ActivationMaximization fails after tf.keras.models.load_model

1

hello, I've manged to execute the Visualize Dense Layer example. then tried the following change : ``` OriginalModel = Model(weights='imagenet', include_top=True) OriginalModel.summary() OriginalModel.save('SavedVgg',include_optimizer=True) model = tf.keras.models.load_model('SavedVgg') activation_maximization = ActivationMaximization(model, model_modifier,...

re-executions of activation_maximization generate different results for same graph/weights

1

hello, I've made the following minor change to the visualize dense layer example: ``` for CurrentAttempt in range(0,4): print('attempt number {}'.format(CurrentAttempt)) activation = activation_maximization(loss,callbacks=[Print(interval=50)]) image = activation[0].astype(np.uint8) subplot_args = {...

Hello, I'm trying to decrease the amount of ram used on the gpu for inference. i've used the supplied cfgs.py that uses resnet101, it uses up about 6G during training,...