本文共 440 字，大约阅读时间需要 1 分钟。
tensor shape depend on both strides and padding type
try strides in (1 1), (2 2), (3 3) and (4 4) combine with twice padding typeimport osimport numpy as npimport tensorflow as tfos.environ["CUDA_VISIBLE_DEVICES"] = "3"n = tf.convert_to_tensor(np.array(range(16)), np.float32)i = tf.reshape(n, [-1, 4, 4, 1])conv = tf.layers.conv2d(inputs=i, filters=32, kernel_size=[1, 1], strides=(3, 3), padding="same", activation=tf.nn.relu)print(conv)
转载地址：http://gydoi.baihongyu.com/