sanhai77
sanhai77
i am confused and i cant give my answer during any research. roi pooling involves non-differentiable operations like indexing(quantizing the coordinate(like 3.5) to integers(3)). However why we detaching the proposals?...
i don't understand exactly approximate joint training method. i know RPN and detector merged as a one network during training. the forward path is started pre trained conv network and...
hi in the 3.3 section : > On the re-scaled images, the total stride for both ZF and VGG nets on the last convolutional layer is 16 pixels, and thus...
I read the faster r-cnn paper and i confused about region proposal section(3.1). now i dont know sibling layer in the RPN are fully connected layers or 1x1 convolutional layers?...
i don't understand exactly approximate joint training method. i know RPN and detector merged as a one network during training. the forward path is started pre trained conv network and...
hi i have problem in mask branch. in the paper mentioned: The mask branch has a Km^2- dimensional output for each RoI, which encodes K binary masks of resolution m...
hi i have problem in mask branch. in the paper mentioned: The mask branch has a Km^2- dimensional output for each RoI, which encodes K binary masks of resolution m...
i am confused and i cant give my answer during any research. roi pooling involves non-differentiable operations like indexing(quantizing the coordinate(like 3.5) to integers(3)). However why we detaching the proposals?...
i don't understand exactly approximate joint training method. i know RPN and detector merged as a one network during training. the forward path is started pre trained conv network and...
i am confused and i cant give my answer during any research. roi pooling involves non-differentiable operations like indexing(quantizing the coordinate(like 3.5) to integers(3)). However why we detaching the proposals?...