zhujiagang
zhujiagang
Sorry for the trouble brought to you in running the code due to my unseriousness. I've update the README.md and you could refer to the `eval_net_tpp_hmdb.py` for more details. Our...
About out of memory due to batch_size, how did you compile caffe-tpp-net? Have you installed openmpi before compiling caffe-tpp-net? Please refer to the command in TSN repo for more details...
@csantosbh You can refer to the `eval_scores_rgb_flow.py`
@csantosbh You should use the `kinetics_hmdb_split_1/train_kinetics_rgb_tpp_p124_split_1.sh `, because the authors of TSN provide kinetics pretraining model and prototxt in [http://yjxiong.me/others/kinetics_action/](http://yjxiong.me/others/kinetics_action/) with different name from using imagenet pretraining.
Yes, I've also found the error and have updated README.md. You just have to `cp -r caffe-tpp-net/ caffe-tpp-net-python/`.
Curious too. And should we replace the softmax activation with sigmoid? As implied by many works like Mask R-CNN, SE net, that not competing is better.
Got It! Thank you very much!
Hi, I have the same question. @NicolasHug Have you modified it? Maybe too few points on the boundary 0 contribute to the final results.
Thank you very much！