提交 b5781703 authored 作者: Frederic Bastien's avatar Frederic Bastien

use the common parameter to don't duplicate them.

上级 6030673d
...@@ -155,8 +155,8 @@ def run_conv_nnet2(shared_fn): # pretend we are training LeNet for MNIST ...@@ -155,8 +155,8 @@ def run_conv_nnet2(shared_fn): # pretend we are training LeNet for MNIST
n_train=30 n_train=30
logical_hid_shape = tcn.blas.GpuConv.logical_output_shape_2d((32, 32), (5, 5), 'valid') logical_hid_shape = tcn.blas.GpuConv.logical_output_shape_2d(tuple(shape_img[2:]),tuple(shape_kern[2:]), 'valid')
logical_hid_shape1 = tcn.blas.GpuConv.logical_output_shape_2d((logical_hid_shape[0]/2, logical_hid_shape[1]/2), (5, 5), 'valid') logical_hid_shape1 = tcn.blas.GpuConv.logical_output_shape_2d((logical_hid_shape[0]/2, logical_hid_shape[1]/2), tuple(shape_kern1[2:]), 'valid')
n_hid = n_kern1 * logical_hid_shape1[0] * logical_hid_shape1[1] n_hid = n_kern1 * logical_hid_shape1[0] * logical_hid_shape1[1]
n_out = 10 n_out = 10
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论