search

vasgaowei / pytorch_MELM

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

In the Github source code you provided，the test experiment is 45.86%.Can you check it again？ #20

Open Elaineok opened 4 years ago

Elaineok commented 4 years ago

In the Github source code you provided，the test experiment is 45.86%.Can you check it again？

vasgaowei commented 4 years ago

In network.py, modify a line of code in return_ss_boxes function. The original code is following: def return_ss_boxes(self, boxes_index, mode='TRAIN'): if mode == 'TEST': return boxes_index box_num = min(500, len(boxes_index)) indexes = np.random.choice(boxes_index, size=box_num, replace=False) return indexes

The modified version is : def return_ss_boxes(self, boxes_index, mode='TRAIN'): if mode == 'TEST': return boxes_index box_num = min(1000, len(boxes_index)) indexes = np.random.choice(boxes_index, size=box_num, replace=False) return indexes You can even use all the proposals for training if you have enough GPU memory. Then you can set the number larger.