P.72 data_tf lose reshape? 书72页是否缺失一维化转换
Iamyang opened this issue · 1 comments
Iamyang commented
72页定义了数据转换:
data_tf=transforms.Compose([transforms.ToTensor(),transforms.Normalize([0.5],[0.5])])
运行之后出错,
RuntimeError: size mismatch, m1: [1792 x 28], m2: [784 x 300] at c:\programdata\miniconda3\conda-bld\pytorch-cpu_1524541161962\work\aten\src\th\generic/THTensorMath.c:2033
书中和deep-nn代码里面的data_tf不同,代码样例里面data_tf有reshape操作
L1aoXingyu commented
以 deep-nn 的代码为准,等1.0出来之后书会更新的