search

gkioxari / RstarCNN

R*CNN
Other
132 stars 53 forks source link

How can I get the Stanford40/ground_truth #8

Open gdy920201 opened 8 years ago

gdy920201 commented 8 years ago

In the dataset of Stanford40,how can i get the primary region and secondary region？Can you share the code ?Thanks!

gkioxari commented 8 years ago

a. To download the Stanford 40 data, please refer to the README. It provides a link to the data

b. In lib/fast_rcnn/test_stanford40.py in line 279 im_detect returns the overall score, the score of the secondary regions as well as the secondary regions. The primary regions are the ground truth regions, gt_boxes

gdy920201 commented 8 years ago

How can I add the dataset of stanford40 to /tools/train.py .I am learning of the caffe.

gkioxari commented 8 years ago

This is not related to Caffe, but to Python.

In tools/train.py in line 15 is where the dataset is imported and then called again in line 78. All you need to do is change line 15 to, import datasets.stanford40 and then subsequentely call in line 78 imdb = datasets.stanford40('train')