ECO-efficient-video-understanding
ECO-efficient-video-understanding copied to clipboard
Code and models of paper " ECO: Efficient Convolutional Network for Online Video Understanding", ECCV 2018
Hi @mzolfaghari , Thanks very much for this great work. It is not like an issue but just a general question. Could you please suggest if there is any replacement...
Thanks for your work! i test your code in PyTorch, but in fact, inference speed is always 10x slower than what you reported in your paper when using the same...
The presented method setting the number of segments seems not right. layer { name: "reshape_fc_st2" type: "Reshape" bottom: "global_pool2D" top: "reshape_fc_st2" reshape_param { shape { dim: [-1, 1, 16, 1024]...
Determining if the pthread_create exist failed with the following output: Change Dir: /home/lijie/ECO-efficient-video-understanding/caffe_3d/build/CMakeFiles/CMakeTmp Run Build Command:"/usr/bin/make" "cmTC_35b4f/fast" /usr/bin/make -f CMakeFiles/cmTC_35b4f.dir/build.make CMakeFiles/cmTC_35b4f.dir/build make[1]: Entering directory '/mnt/raid3/home/lijie/ECO-efficient-video-understanding/caffe_3d/build/CMakeFiles/CMakeTmp' Building C object CMakeFiles/cmTC_35b4f.dir/CheckSymbolExists.c.o /usr/bin/cc...
After I install caffe successfully,when I try to import caffe in python ,one error occurs: `Traceback (most recent call last): File "online_recognition.py", line 4, in import caffe File "/root/ECO4/caffe_3d/python/caffe/__init__.py", line...
Thank you for sharing your amazing work. I need to extract ECO features only. Can you help me how to do that? Specifically, I need to just extract ECO features...
I can't download from either "https://drive.google.com/open?id=1XNIq7byciKgrn011jLBggd2g79jKX4uD" or "https://pan.baidu.com/s/1Hx52akJLR_ISfX406bkIog", so how can I get "eco_lite_rgb_16F_kinetics_v1.pth.tar"?