注册
登录
深度学习
在mxnet，python中为标签分配内存的问题
返回
在mxnet，python中为标签分配内存的问题
作者:
無口君
发布时间:
2024-06-11 07:23:35 (28天前)
转自：
<div class =“excerpt”> 我使用Generative Adversarial Network对五类，颜色，128x128像素图像，批量大小= 64进行分类。在创建鉴别器模块时，执行时 discriminator.bind（data_shapes = ... </DIV>
收藏
举报
2 条回复
0#
回复此人
部落用户
|
2019-08-31 10-32
<div class =“post-text”itemprop =“text”> <P> GAN就是这样的 <a href="http://mxnet.apache.org/tutorials/unsupervised_learning/gan.html" rel="nofollow noreferrer"> 例 </A> 期望输入为（batch_size，channels，64,64），但您的数据为（64,3,128,128）。所以你得到一个形状不匹配，因为鉴别器的输出是25而不是1。 </p> <pre> <code> print( mx.visualization.print_summary(discriminatorSymbol, shape={'data':(64,3,128,128)})) gives Layer (type) Output Shape Param # Previous Layer ======================================================================================================================== data(null) 3x128x128 0 ________________________________________________________________________________________________________________________ d1(Convolution) 128x64x64 6144 data ________________________________________________________________________________________________________________________ dact1(LeakyReLU) 128x64x64 0 d1 ________________________________________________________________________________________________________________________ d2(Convolution) 256x32x32 524288 dact1 ________________________________________________________________________________________________________________________ dbn2(BatchNorm) 256x32x32 512 d2 ________________________________________________________________________________________________________________________ dact2(LeakyReLU) 256x32x32 0 dbn2 ________________________________________________________________________________________________________________________ d3(Convolution) 512x16x16 2097152 dact2 ________________________________________________________________________________________________________________________ dbn3(BatchNorm) 512x16x16 1024 d3 ________________________________________________________________________________________________________________________ dact3(LeakyReLU) 512x16x16 0 dbn3 ________________________________________________________________________________________________________________________ d4(Convolution) 1024x8x8 8388608 dact3 ________________________________________________________________________________________________________________________ dbn4(BatchNorm) 1024x8x8 2048 d4 ________________________________________________________________________________________________________________________ dact4(LeakyReLU) 1024x8x8 0 dbn4 ________________________________________________________________________________________________________________________ d5(Convolution) 1x5x5 16384 dact4 ________________________________________________________________________________________________________________________ flatten0(Flatten) 25 0 d5 </code> </pre> </DIV>
编辑
登录
后才能参与评论
