import tensorflow as tfimport numpy as npimport scipy as sciimport cv2import input_data_conv# 参数learning_rate = 0.001training_iters = 200000batch_size = 64display_step = 20n_classes=101 # 类别数量# 输入数据和类别global train_data,train_class,test_data,test_classs,train_i,test_itest_i, train_i = 0,0train_data=input_data_conv.train_list_filetrain_class=input_data_conv.train_single_classestest_data=input_data_conv.test_single_framestest_classs=input_data_conv.test_single_classes# 网络参数n_input = [227, 227, 3 ]# MNIST 数据输入（图像形状：227*227*3）dropout = 0.5 # Dropout，保留单元的概率# tf 图输入x = tf.placeholder(tf.float32, [None, 227,227,3])y = tf.placeholder(tf.float32, [None, n_classes])keep_prob = tf.placeholder(tf.float32) # dropout（保留概率）def init_weights(shape): return tf.Variable(tf.random_normal(shape, stddev=0.01))def conv2d(name, l_input, w, b,s): return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(l_input, w, strides=[1, s, s, 1], padding='SAME'),b), name=name)def max_pool(name, l_input, k,s): return tf.nn.max_pool(l_input, ksize=[1, k, k, 1], strides=[1, s, s, 1], padding='SAME', name=name)def norm(name, l_input, lsize): return tf.nn.lrn(l_input, lsize, bias=1.0, alpha=0.0001 / 9.0, beta=0.75, name=name)def vgg_single_frame(_X, _weights, _biases, _dropout): # 重塑输入图像 _X = tf.reshape(_X, shape=[-1, 227, 227, 3]) conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1'],s=2) pool1 = max_pool('pool1', conv1, k=3,s=2) norm1 = norm('norm1', pool1, lsize=5) conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2'],s=2) pool2 = max_pool('pool2', conv2, k=3,s=2) norm2 = norm('norm2', pool2, lsize=5) conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3'],s=2) conv4 = conv2d('conv4', conv3, _weights['wc4'], _biases['bc4'],s=2) conv5 = conv2d('conv4', conv4, _weights['wc5'], _biases['bc5'],s=2) pool5 = max_pool('pool5', conv5, k=3,s=2) # 全连接层 dense1 = tf.reshape(norm3, [-1, _weights['wd1'].get_shape().as_list()[0]]) # 重塑conv3输出以适应全连接层输入 dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc6') # Relu激活 dense1 = tf.nn.dropout(dense1, _dropout) dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc7') # Relu激活 dense2 = tf.nn.dropout(dense2, _dropout) # 输出，类别预测 out = tf.matmul(dense2, _weights['out']) + _biases['out'] return outweights = { 'wc1': tf.Variable(tf.random_normal([7, 7, 1, 96])), # 7x7卷积，1输入，96输出，步长2 'wc2': tf.Variable(tf.random_normal([5, 5, 96, 384])), # 5x5卷积，32输入，64输出 'wc3': tf.Variable(tf.random_normal([3, 3, 384, 512])),#s 2 ,p a 'wc4': tf.Variable(tf.random_normal([3, 3, 512, 512])),#s 2, p 1 'wc5': tf.Variable(tf.random_normal([3, 3, 512, 384])),#s 2, p 1 'wd1': tf.Variable(tf.random_normal([7*7*64, 4096])), # 全连接，7*7*64输入，1024输出 'wd2': tf.Variable(tf.random_normal([4096, 4096])), # 全连接，7*7*64输入，1024输出 'out': tf.Variable(tf.random_normal([4096, n_classes])) # 1024输入，10输出（类别预测）}biases = { 'bc1': tf.Variable(tf.random_normal([96])), 'bc2': tf.Variable(tf.random_normal([384])), 'bc3': tf.Variable(tf.random_normal([512])), 'bc4': tf.Variable(tf.random_normal([512])), 'bc5': tf.Variable(tf.random_normal([384])), 'bd1': tf.Variable(tf.random_normal([4096])), 'bd2': tf.Variable(tf.random_normal([4096])), 'out': tf.Variable(tf.random_normal([n_classes]))}def train_next_batch(batch_size): temp_data=np.ndarray(shape=(batch_size,227,227,3),dtype=float) temp_data=np.ndarray(shape=(batch_size,n_classes),dtype=float) for num,x in train_data[train_i:train_i+batch_size]: temp_data[num,:,:,:]=cv2.imread(x,1)pred = vgg_single_frame(x, weights, biases, keep_prob)cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)# 评估模型correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))# 初始化变量init = tf.initialize_all_variables()with tf.Session() as sess: sess.run(init) step = 1 # 继续训练直到达到最大迭代次数 while step * batch_size < training_iters: batch_xs, batch_ys = train_next_batch(batch_size) # 使用批次数据进行训练 sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout}) if step % display_step == 0: # 计算批次准确率 acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.}) # 计算批次损失 loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.}) print "Iter " + str(step*batch_size) + ", Minibatch Loss= " + "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc) step += 1 print "Optimization Finished!" # 计算256张测试图像的准确率 print "Testing Accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.})我想运行上面的代码，并向该网络输入大小为[227, 227, 3]的图像。然而，当我尝试构建网络时，出现了以下错误：
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcublas.so locallyI tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcudnn.so locallyI tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcufft.so locallyI tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcuda.so.1 locallyI tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcurand.so locallyTraceback (most recent call last): File "/home/anilil/projects/pycharm-community-5.0.4/helpers/pydev/pydevd.py", line 2411, in <module> globals = debugger.run(setup['file'], None, None, is_module) File "/home/anilil/projects/pycharm-community-5.0.4/helpers/pydev/pydevd.py", line 1802, in run launch(file, globals, locals) # execute the script File "/media/anilil/Data/charm/Cnn/build_vgg_model.py", line 104, in <module> pred = vgg_single_frame(x, weights, biases, keep_prob) File "/media/anilil/Data/charm/Cnn/build_vgg_model.py", line 50, in vgg_single_frame conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1'],s=2) File "/media/anilil/Data/charm/Cnn/build_vgg_model.py", line 38, in conv2d return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(l_input, w, strides=[1, s, s, 1], padding='SAME'),b), name=name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_nn_ops.py", line 211, in conv2d use_cudnn_on_gpu=use_cudnn_on_gpu, name=name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 655, in apply_op op_def=op_def) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2042, in create_op set_shapes_for_outputs(ret) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1528, in set_shapes_for_outputs shapes = shape_func(op) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/common_shapes.py", line 187, in conv2d_shape input_shape[3].assert_is_compatible_with(filter_shape[2]) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_shape.py", line 94, in assert_is_compatible_with % (self, other))ValueError: Dimensions Dimension(3) and Dimension(1) are not compatible我认为weights['wc1']变量的形状可能不对，但我不知道正确的形状是什么。
回答：
问题在于你的输入图像（在_X中）有3个通道（可能是红色、绿色和蓝色），而conv1层的卷积滤波器（在_weights['wc1']中）期望1个输入通道。
解决这个问题至少有两种方法：
-
重新定义
_weights['wc1']以接受3个输入通道：weights = { 'wc1': tf.Variable(tf.random_normal([7, 7, 3, 96])), # ... # ...} -
使用
tf.image.rgb_to_grayscale()操作将你的输入图像_X转换为1个输入通道：_X = tf.image.rgb_to_grayscale(_X)
