wqingze
wqingze
os: ubuntu 16.04 I installed the driver, it works fine, but after a few days, it dose not work, I have no ideas
this is the problem https://stackoverflow.com/questions/48368441/mnists-deep-feature-visualizations-is-nothing
for what I understand, it needs 30 stock data to train a model, if there is a lot of stocks(> 30), I want to use all of them to train...
Operating system: centos 6.3 Compiler: gcc4.64 CUDA version (if applicable):7.5 CUDNN version (if applicable):v5 BLAS:atlas it seams that run out of memory
when deploy the model, no groundtruth, so no trackids, so how to compute [rois_disp](https://github.com/feichtenhofer/Detect-Track/blob/master/models/rfcn_prototxts/ResNeXt-101L_ILSVRCvid_corr/test_track_reg.prototxt#L16) in the test network, use all of the rois?
in the function of build_model, I saw a lots of weight mtarix, for example `image_att_W, hidden_att_W, att_W, image_encode_W` and so on, I don't know why. in my opion, the lstm...
File "\", line 1, in Error detected while processing /Users/wqz/.vim/bundle/python-mode/autoload/pymode/lint.vim: line 1: File "/Users/wqz/.vim/bundle/python-mode/pymode/lint.py", line 9, in Error detected while processing /Users/wqz/.vim/bundle/python-mode/autoload/pymode/lint.vim: line 1: from pylama.lint.extensions import LINTERS Error detected...