Andrey Rykov
Andrey Rykov
@xindongzhang thanks for your comment, but I believe, that the authors state the following: _We measure the speed with batch size 8 using Titan X and cuDNN v4 with Intel...
@MrXu as for training, I'm working on this part, hope to release the code this week. I also had to change some things in the architecture in order to be...
@xikaichen are you using the same setup as in README? Probsbly, something in `Keras` or `Tensorflow` has changed recently and that is the source of the problem.
@neil454 sorry for late reply. I believe, that you need to change the last activation to sigmoid (you have already done it) and use `binary_crossentropy` as your loss function for...
@neil454 sorry for late reply again. I haven't trained on regular VOC2007, but on my dataset training works quite well. I believe, that in the repo there is a bug...
@Dan1900, @mgaueca, @Elpidam if this is still relevant, I commented in #9 how to download the weights via wget, hope it helps