AndrewNg's CNN notes(practical issues)

In this example, the author adapted the architecture obtained from training ILSVRC-2011 dataset which consists of 1000 classes with approximately 1.5 million images. And using the pre-trained VGG-16 network, the author fine-tuned the network on PASCAL VOC detection data (20 object classes, and 1 background class) and replaced the original 1000 way classification layer by a randomly initialized 21-way classification layer. Apart from that, the author keep the rest of the CNN architecture remains unchanged.

After training of CNN parameters and filter the region proposals based on their IoU value, at the test stage, RCNN uses Selective Search to extract ~300 boxes that likely contain objects and evaluates the ConvNet on each one of them, followed by NMS(non-maximum suppression) within each class.