xuwang1430 comments

Repositories
Issues
Comments

Results 6 comments of


                                            xuwang1430

there is a errer when runing

the code is a bit long,so i just provide the main code as follow conv1 = tf.nn.conv2d(x, filter=[3, 3, 1, 64], strides=[1, 1, 1, 1], padding='SAME') conv1_bn = group_norm(conv1) my...

there is a errer when runing

i use the norm code ,just the name of function is differ from you. x = tf.placeholder(tf.float32,[None, None, None, 1], name='x_input')

there is a errer when runing

thanks@shaohua0116, I made it by feeding x a fixed shape. However, the test result was bad when I replaced BN by GN. my data batch is 4.

how to do the dataset?

Fausto , thank you fou your reply I have a try by your suggestion from xu

#Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type: Python

hi fausto I am using your 3D-caffe.and my version of cudnn is 5.1

#Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type: Python

I have check my pythonpath environment variable. it is corrected .