tf.nn.conv2d() / tf.nn.depthwise_conv2d() 和 Batchsize效益
1.卷积函数tf.nn.conv2d()tf.nn.conv2d(input,filter,strides,padding,use_cudnn_on_gpu=True,data_format='NHWC',dilations=[1,1,1,1],name=None)对于给定的4-D张量输入,利用给定的filter执行2-D卷积运算。input:[batch,in_height,in_width,i