search

daijifeng001 / R-FCN

R-FCN: Object Detection via Region-based Fully Convolutional Networks
Other
1.25k stars 542 forks source link

About the input data in training #36

Open shudct opened 8 years ago

shudct commented 8 years ago

Hi all,

  1. In train_val.prototxt, I notice that the input data such as label is 1 * 5 * 1 * 1, the dim 5 means [batch_ind, x1, y1, x2, y2]. I wonder what dose the batch_ind means. Dose it mean the rois' index or others?
  2. Also in train_val.prototxt, the bbox_targets and bbox_loss_weights are both 1 * 8 * 1 * 1. Why not 1 * 4 * 1 * 1?
  3. If I wonder input multi rois for training, how should I change the input data?

Hope someone can give me some advice, thanks!