zhao181
zhao181
I am using pytorch version to train the mnistedge, but after more than 20000 iterations, the results are like random noise. Can someone offered help?!
Hi author, I am running the train_net.py, and set _C.TRAIN.HAS_RPN=True. When the function "get_boxes_grid" is called, it produces 234150000 grid boxes for an image of size 333*500. I find that...
Dear author, The WFLW offers 98 landmarks. Are the 68 landmark in 300W a subset of the 98 landmarks here?Can you offer the corresponding relations? Thanks a lot.
Dear author, how can I understand the post-processing part in the decode_preds function？ # pose-processing for n in range(coords.size(0)): for p in range(coords.size(1)): hm = output[n][p] px = int(math.floor(coords[n][p][0])) py...
Hello everyone, it is the first time I could successfully run a demo. Many thanks to the author. To use cpu only, I follow the author's instruction and make the...
Has anyone trained the encnet on cityscapes? How is the result?
When I run "python setup.py install" in the folder A:\semantic\PyTorch-Encoding\encoding\lib\cpu It issues the following errors, C:\ProgramData\Anaconda3\lib\site-packages\torch\lib\include\c10/util/Exception.h(29): warning C4251: 'c10::Error::backtrace_': class 'std::basic_string' needs to have dll-interface to be used by clients...
Dear author, how can I get the aux_labels? Can you offer them? Very thanks
Dear author, can you providea link for your prepared training data in baidu pan? thanks