HOU Yuenan
HOU Yuenan
@ycszen , tensorflow version of SCNN is available at [this repo](https://github.com/cardwing/Codes-for-Lane-Detection).
@virajdeokar , you can refer to [this repo](https://github.com/cardwing/Codes-for-Lane-Detection) which is implemented by Tensorflow.
@Matrixio , it is normal since SCNN propagates the information in a sequential way. As to the acceleration of training process, a naive way is to use multiple gpus. An...
@Matrixio , you can refer to [Codes-for-Lane-Detection](https://github.com/cardwing/Codes-for-Lane-Detection) where I will put my implemented version of lane detection models.
@planckztd , please refer to [this issue](https://github.com/1adrianb/binary-human-pose-estimation/issues/2). The error should be caused by the version of cudnn. You just need to upgrade cudnn from 4.0 to 5.0.
@planckztd , you can also refer to [this repo](https://github.com/cardwing/Codes-for-Lane-Detection) which is a bit faster.
@OneMondy , you can also refer to [this repo](https://github.com/cardwing/Codes-for-Lane-Detection).
@jcdubron , VGG-16 is loaded from the LargeFOV model (released by deeplab) according to the description of their paper.
@gexiaosulynn , please refer to [seg_label_generate](https://github.com/XingangPan/seg_label_generate)
@juntawu , @virajdeokar , please refer to this issue [143](https://github.com/facebook/fb.resnet.torch/issues/143).