我的卷积网络的输出非常不寻常。当我打印出前向传播结果的输出向量时，它始终是完美的[0, 0, 0, 1]，对于数据集中的整个标签都是恒定的。我怀疑我的构建中存在错误。
import osimport sysimport tensorflow as tfimport Inputimport os, re"""这是一个基于CIFAR10模型的模型。程序的总体结构和一些功能是从Tensorflow的CIFAR10模型示例中借用的。https://github.com/tensorflow/tensorflow/tree/r0.7/tensorflow/models/image/cifar10/如引用所说:"如果您现在有兴趣开发和训练您自己的图像分类系统，我们建议您fork这个教程，并替换组件以解决您的图像分类问题。"来源:https://www.tensorflow.org/tutorials/deep_cnn/"""FLAGS = tf.app.flags.FLAGSTOWER_NAME = 'tower'tf.app.flags.DEFINE_integer('batch_size', 1, "hello")tf.app.flags.DEFINE_string('data_dir', 'data', "hello")def _activation_summary(x): with tf.device('/cpu:0'): tensor_name = re.sub('%s_[0-9]*/' % TOWER_NAME, '', x.op.name) tf.histogram_summary(tensor_name + '/activations', x) tf.scalar_summary(tensor_name + '/sparsity', tf.nn.zero_fraction(x))def inputs(): if not FLAGS.data_dir: raise ValueError('Source Data Missing') data_dir = FLAGS.data_dir images, labels = Input.inputs(data_dir = data_dir, batch_size = FLAGS.batch_size) return images, labelsdef eval_inputs(): data_dir = FLAGS.data_dir images, labels = Input.eval_inputs(data_dir = data_dir, batch_size = 1) return images, labelsdef weight_variable(shape): with tf.device('/gpu:0'): initial = tf.random_normal(shape, stddev=0.1) return tf.Variable(initial)def bias_variable(shape): initial = tf.constant(0.1, shape = shape) return tf.Variable(initial)def conv(images, W): with tf.device('/gpu:0'): return tf.nn.conv2d(images, W, strides = [1, 1, 1, 1], padding = 'SAME')def forward_propagation(images): with tf.variable_scope('conv1') as scope: conv1_feature = weight_variable([20, 20, 3, 20]) conv1_bias = bias_variable([20]) image_matrix = tf.reshape(images, [-1, 1686, 1686, 3]) conv1_result = tf.nn.relu(conv(image_matrix, conv1_feature) + conv1_bias) _activation_summary(conv1_result) with tf.variable_scope('conv2') as scope: conv2_feature = weight_variable([10, 10, 20, 40]) conv2_bias = bias_variable([40]) conv2_result = tf.nn.relu(conv(conv1_result, conv2_feature) + conv2_bias) _activation_summary(conv2_result) conv2_pool = tf.nn.max_pool(conv2_result, ksize = [1, 281, 281, 1], strides = [1, 281, 281, 1], padding = 'SAME') with tf.variable_scope('conv3') as scope: conv3_feature = weight_variable([5, 5, 40, 80]) conv3_bias = bias_variable([80]) conv3_result = tf.nn.relu(conv(conv2_pool, conv3_feature) + conv3_bias) _activation_summary(conv3_result) conv3_pool = tf.nn.max_pool(conv3_result, ksize = [1, 2, 2, 1], strides = [1, 2, 2, 1], padding = 'SAME') with tf.variable_scope('local3') as scope: perceptron1_weight = weight_variable([3 * 3 * 80, 10]) perceptron1_bias = bias_variable([10]) flatten_dense_connect = tf.reshape(conv3_pool, [1, -1]) compute_perceptron1_layer = tf.nn.relu(tf.matmul(flatten_dense_connect, perceptron1_weight) + perceptron1_bias) _activation_summary(compute_perceptron1_layer) with tf.variable_scope('softmax_connect') as scope: perceptron3_weight = weight_variable([10, 4]) perceptron3_bias = bias_variable([4]) y_conv = tf.nn.softmax(tf.matmul(compute_perceptron1_layer, perceptron3_weight) + perceptron3_bias) _activation_summary(y_conv) return y_convdef error(forward_propagation_results, labels): with tf.device('/cpu:0'): labels = tf.cast(labels, tf.int64) cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(forward_propagation_results, labels) cost = tf.reduce_mean(cross_entropy) tf.add_to_collection('losses', cost) tf.scalar_summary('LOSS', cost) return costdef train(cost): with tf.device('/gpu:0'): train_loss = tf.train.GradientDescentOptimizer(learning_rate = 0.01).minimize(cost) return train_loss回答：
主要问题在于Softmax被调用了两次。
Softmax在代码的前向传播部分被调用，并且它被放置在Tensorflow的交叉熵代码中，该代码已经包含了一个Softmax，因此导致输出异常。
