xsz
I experimented the model as below ``` with tf.variable_scope('vgg16'): (self.feed('data').conv(3, 3, 64, 1, 1, name='conv1_1') .conv(3, 3, 64, 1, 1, name='conv1_2') .max_pool(2, 2, 2, 2, padding='VALID',name='pool1')) (self.feed('pool1').conv(3, 3, 128, 1,...
@xmyqsh , thanks, I will replace a 1080ti, but for the moment VGG16 is the option I could experiment, I will reduce the RPN_BATCH_SIZE and BATCH_SIZE. when you mentioned about...
@xmyqsh, thanks for the answer. I am currently moving from Caffe to tensorflow, there are a few points not so well understood. additional question, why you use variable scope ('res1_2')...
oh, Thanks, I got your meaning..
@Supersak80 The size of my training pictures are all around 220 pixels width and length, there is only one object in the training pictures with around 150 pixel size. I...
can't work for me either, who can help to update it ? ????
The video in the VLC player just frozen after a while, sometimes it can be after 2 minutes, sometimes it can be after 10 minutes. There is no message in...
want to experiment them myself, so currently I am going to ask my friend back in China to print some circuits and components, still working on contacting the reliable PCB...
I want to do it, just work with my friends to see the possibility of working on the circuits in China, that will be more cheaper.
@newsoftxmc Thanks.