You can't use conv2d with a tensor of rank 1. Here's the description from the doc: Computes a 2-D convolution given 4-D input and filter ... ... <看更多>

An Open Source Machine Learning Framework for Everyone - tensorflow/convolutional.py at master · tensorflow/tensorflow. ... <看更多>

Convolutional Neural Network (CNN) · Import TensorFlow · Download and prepare the CIFAR10 dataset · Verify the data · Create the convolutional base · Add Dense ... ... <看更多>

Your calculation would be correct if the example were following the "usual" approach of having convolution chop off the edges. Instead the example you ... ... <看更多>

While using convolutional neural network, we don't have to manually calculate the dimension (the spatial size) of the output(s), ... ... <看更多>

placeholderCopy import tensorflow as tf i = tf.constant([1, 0, 2, 3, 0, 1, 1], dtype=tf.float32, name='i') k = tf.constant([2, 1, 3], ... ... <看更多>