search

vasgaowei / pytorch_MELM

The pytorch implementation of the Min-Entropy Latent Model for Weakly Supervised Object Detection
104 stars 19 forks source link

pool5_roi = self._roi_ring_pool_layer(net_conv, rois, 0., 1.0) pool5_context = self._roi_ring_pool_layer(net_conv, rois, 1.0, 1.8) pool5_frame = self._roi_ring_pool_layer(net_conv, rois, scale_inner = 1.0 / 1.8, scale_outer = 1.0) #4

Open yjyyy opened 5 years ago

yjyyy commented 5 years ago

pool5_roi = self._roi_ring_pool_layer(net_conv, rois, 0., 1.0) pool5_context = self._roi_ring_pool_layer(net_conv, rois, 1.0, 1.8) pool5_frame = self._roi_ring_pool_layer(net_conv, rois, scale_inner = 1.0 / 1.8, scale_outer = 1.0)

these codes are from network.py file row 584 to row 586, i guess they are used to generate three different output by making different scale parameter and using the RoIRingPoolFunction structure. but i have no idea about how does it work and why do you set the parameter to 0, 1.0, 1.8, 1.0/1.8. thank you a lot.

vasgaowei commented 5 years ago

RoiRingPoolingFunction is similiar with RoiPoolFunction but with a few differences, and I suggest to read the paper 《ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization》to know more about the idea.