tensorflow-fcn
tensorflow-fcn copied to clipboard
MarvinTeichmann
An Implementation of Fully Convolutional Networks in Tensorflow.
Hi, I was directed to here by [https://datascience.stackexchange.com/questions/12830/how-are-1x1-convolutions-the-same-as-a-fully-connected-layer](url) ``` if name == 'fc6': filt = self.get_fc_weight_reshape(name, [7, 7, 512, 4096]) elif name == 'score_fr': name = 'fc8' # Name of...
can't not open this website for download vgg16.npy: ftp://mi.eng.cam.ac.uk/pub/mttt2/models/vgg16.npy
As is described above , I wonder the speed FCN can achieve , but the paper doesn't show that......
when I convert the ckpt model to movidius graph, I meet the problem: `InvalidArgumentError (see above for traceback): Number of ways to split should evenly divide the split dimension, but...
When I ran fcn8_vgg.py,it throw an exception： 2017-09-06 19:42:22.785673: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Conv2DSlowBackpropInput: Size of out_backprop doesn't match computed: actual = 23, computed = 12 2017-09-06 19:42:22.785941: W tensorflow/core/framework/op_kernel.cc:1152]...
I use your code to train datasets(ADEChallengeData2016),But the loss is almost the same: epoch: 19 || batch: 92 || l: 3.161138 epoch: 19 || batch: 93 || l: 3.038326 epoch:...
Hello! I found that in fcn8s_vgg.py. The weight decay loss is not added into tf.GraphKeys.REGULARIZATION_LOSSES, since you specify another collection name. I would like to know if this will affect...
Dear Marvin thanks for your great code! I want just to use this code for image segmentation and cant download a bulky data to find out how to use it....
I can't understand what codes below want to do, does anybody can explain? Thanks so much !!! ``` if use_dilated: pad = [[0, 0], [0, 0]] self.pool4 = tf.nn.max_pool(self.conv4_3, ksize=[1,...
Metadata
Owner
Metadata
An Implementation of Fully Convolutional Networks in Tensorflow.