Deep-Feature-Flow
Deep-Feature-Flow copied to clipboard
msracver
Deep Feature Flow for Video Recognition
When I run the "dff_rfcn/demo.py", I encounted this error. Anybody know why? Please help me out!
that means mxnet cannot find cblas library, please install atlas/openblas correctly _Originally posted by @YuwenXiong in https://github.com/msracver/Deep-Feature-Flow/issues/19#issuecomment-315570625_ my platform is centos7 the error is below: /usr/bin/ld: cannot find -lcblas collect2:...
Hi, I have a custom dataset which I want to train. I would be very grateful for the steps on how to do it using Deep-Feature-Flow. Thanks
num_images 53639 wrote gt roidb to ./data/cache/ImageNetVID_DET_train_30classes_gt_roidb.pkl append flipped images to roidb num_images 57834 wrote gt roidb to ./data/cache/ImageNetVID_VID_train_15frames_gt_roidb.pkl append flipped images to roidb filtered 222946 roidb entries: 222946 ->...
I think line 32 and 68 have to be change from assert os.path.exists(roi_rec['image']), '%s does not exist'.format(roi_rec['image']) to assert os.path.exists(roi_rec['image']), '{} does not exist'.format(roi_rec['image']) . If the problem just regards...
Hi！I got an error like this: ~~~ In file included from /usr/local/cuda/include/cuda_runtime.h:115:0, from :0: /usr/local/cuda/include/crt/common_functions.h:74:24: error: token ""__CUDACC_VER__ is no longer supported. Use __CUDACC_VER_MAJOR__, __CUDACC_VER_MINOR__, and __CUDACC_VER_BUILD__ instead."" is not...
I follow the steps of `README`, however it output this after executing `make` ``` Makefile:35: mshadow/make/mshadow.mk: No such file or directory Makefile:36: /media/SecondDisk/yanpengxiang/incubator-mxnet/dmlc-core/make/dmlc.mk: No such file or directory Makefile:131: /media/SecondDisk/yanpengxiang/incubator-mxnet/ps-lite/make/ps.mk:...
I'm running the code on a server. However, when I run the `init.sh`, I received the following error messages. What's wrong with the code? I'm using python 2.7 and mxnet-1.2.1....
For some reason, I am not able to build mxnet from source to work with Python 2. I am thinking if I should modify the source code of Deep-Feature-Flow to...
@YuwenXiong @ancientmooner @daijifeng001 @einsiedler0408 @HaozhiQi: Is it possible to run the training experiments, with a different backbone? Have you implemented such an experiment for an ablation study? Any help provided...
