maskrcnn.mxnet
maskrcnn.mxnet copied to clipboard
Mask-RCNN implementation in MXNet
When I run the training code, I get this error. But I can't find the API 'mx.contrib.sym.ChannelOperator' in mxnet. Dose anyone meet the same error?
Ubuntu16.04 Processor: i5-7500CPU @3.40GHz x 4 Memory:15.6G Graphics: GTX960 4G I am run "./run.sh". I am get this error: INFO:root:lr 0.001000 lr_epoch_diff [12, 18] lr_iters [984960, 1477440] [03:09:44] src/operator/nn/./cudnn/./cudnn_algoreg-inl.h:107: Running...
When I perform the code, I met the problem "No module named "rcnn.cython.bbox"". I find that there eixts bbox.pyx. After I install VS2015, the problem still exits. Is there anybody...
![image](https://user-images.githubusercontent.com/16440889/34291351-df2d262a-e736-11e7-8235-07c76b8e38e8.png) ![image](https://user-images.githubusercontent.com/16440889/34291375-f50da186-e736-11e7-8581-a7d60c4b0a6a.png) the result of roialign is not correct. but use roipooling is ok.
problems
when i try to training according the first step, it appear a error that No module named bbox(maskrcnn.mxnet-master\rcnn\processing\bbox_transform.py from ..cython.bbox import bbox_overlaps_cython)
can you please share the pretrained model?
When I run the "python maskrcnn_demo.py --gpu 0 --prefix model/e2e --epoch 10", the error is "maskrcnn.mxnet/rcnn/core/module.py", line 269, in _impl raise RuntimeError("%s is not presented" % name) RuntimeError: rpn_conv_3x3_weight is...
I try to use --gpus=0,1,2,3 to train ,but get error: >>raise MXNetError(py_str(_LIB.MXGetLastError())) >>mxnet.base.MXNetError: Error in operator rois: Shape inconsistent, Provided=(1,3), inferred shape=(4,3) How to fix the params?
I trained the model with "python maskrcnn_train_end2end.py --gpus 0 --prefix model/e2e --end_epoch 10". Following is the error message. It seems like a problem in reading mask files. But I can't...