Coldmooon

@vvkv The original instruction is [here](https://github.com/weiliu89/caffe/tree/ssd). What I want to say is that the custom dataset is formatted the same as VOC dataset for convenience. So, before training SSD on...

@achaiah Sorry for the late reply. This generator is currently implemented to replicate the results of the original paper on the CIFAR dataset. I haven't implemented the generator for ImageNet....

@Coderx7 : The ZCA whitened CIFAR dataset (no pad) can be downloaded from https://gist.github.com/mavenlin/e56253735ef32c3c296d#descriptions. The ZCA whitened CIFAR dataset ( padded with 8 pixels for each side ) can be...

@dorioliu There are two possible reasons. 1. The `class.txt` of VOC dataset is empty. 2. Check up the `CmFile::loadStrList`. At running time. `Classname` has an extra character `\r` while `train/test...

Request +1