Gallon Deng
Gallon Deng
my system is ubuntu 16.04, conda , python3.6. Had the same issue
also expected feature, it will be very useful.
hi, @ailias @MAGI003769 , thus I can directly use tensorflow object_detection models api to merge focal loss with SSD. However, I am not sure, whether it can directly be used...
BTW, I use https://github.com/mystic123/tensorflow-yolo-v3.git
I run eval_gui.py, also got errors: 1 error detected in the compilation of tmp/tmpxft_00004b70_00000000-6_backward_warp_op.cu.cpp1.ii" tensorflow.python.framework.errors_impl.NotFoundError: ./backward_warp_op.so: cannot open shared object file: No such file or directory subprocess.CalledProcessError: Command 'nvcc -std=c++11...
yes, I am trying to do a project with a real dataset to detect whether or not a worker wears an uniform and a helmet in a factory. The person...
I just dowloaded a video from web and tested it with the repo. It ran a while and got stuck, showed warning invaild values in the code "cost_matrix[cost_matrix > max_distance]...
hi, @farmingyard , I am trying to compile it with caffe and it shows the error "‘caffe_gpu_set’ was not declared in this scope" in conv_dw_layer.cpp. Any suggestions to solve the...
compile without GPU
nice work. I tried it on some low-resolution images and the pretrained model performed badly. It is highly expected to train on our new dataset.