Open hgfm opened 7 years ago
have you solved the problem? I also want to use deconv layer
@yaoqi-zd Sorry, I am not, maybe the problem caused when generate anchor. I'm still trying to solve it, if you have solved, please tell me how to do, thanks!
yes the anchor size needs to be the same as your feature map after deconv.
@hgfm are you solve this problem ?can you tell me what to do ,thanks in advance.
I changed /tf-faster-rcnn/lib/nets/vgg16.py .
after
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv5')
addnet = slim.conv2d_transpose(net, 512, [4, 4], stride=4, scope='deconv')
I used
./experiments/scripts/train_faster_rcnn.sh 0 pascal_voc vgg16
to train, but it error. What else file should I change? I'm not sure what result inValueError: cannot reshape array of size 17100 into shape (1,152,200,9)
Thank you for your help!Here is the error log: