koki madono comments

Results 8 comments of


                                            koki madono

Which version of Keras should be used?

Did you upgrade tensorflow or Keras? I had a same problem, but by upgrading, I can fix it. try `pip3 install keras --upgrade`

original paper using deepcut to fuse body part info

@chenyuan1994 @shensheng27 I also want to use gpu version of deepmatch....Please tell me how to set up it!!

original paper using deepcut to fuse body part info

@chenyuan1994 thank you!!

run train.py occur error

@zhenyezi @zhenyezi num of training samples: 2112 Using TensorFlow backend. I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcublas.so locally I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcudnn.so locally I tensorflow/stream_executor/dso_loader.cc:111] successfully opened...

Some points predicted by a net can't be backward using gpu.

I have the same issues too. (CPU works but GPU does not work). Or we will have illegal memory access error

CUDA Runtime Error: an illegal memory access was encountered

Does anyone happen similar situation at backpropagation? (no error on CPU but error on GPU) Ubuntu 18.04 cuda 10.0 cudnn 7.0 It might be due to a large amount of...

how to get the yolo output data?

@Anida-qin @dongqiaqia @masoumeh1 @suryaprakaz If you are find the solution of using the molo code, Please tell me!!!

Is it Possible to apply this code to multiple object tracking?

seq_dets = np.loadtxt('3rd_party/sort-master/output/%s.txt'%(sequence_name),delimiter=',') #load detections i ca't use this point