我在尝试对MNIST数据库应用主成分分析（PCA）后进行神经网络训练，但由于应用PCA后的数据形状问题不断遇到错误。我不确定如何将所有部分整合在一起，以及如何遍历整个数据库，而不仅仅是其中的一小部分。
这是我的代码：
<pre> <code>import tensorflow as tfimport matplotlib.pyplot as pltimport numpy as npimport randomfrom sklearn.preprocessing import StandardScalerfrom tensorflow.examples.tutorials.mnist import input_datafrom sklearn.decomposition import PCAdatadir='/data' data= input_data.read_data_sets(datadir, one_hot=True)train_x = data.train.images[:55000]train_y= data.train.labels[:55000]test_x = data.test.images[:10000]test_y = data.test.labels[:10000]print("original shape: ", data.train.images.shape)percent=600pca=PCA(percent)train_x=pca.fit_transform(train_x)test_x=pca.fit_transform(test_x)print("transformed shape:", data.train.images.shape)train_x=pca.inverse_transform(train_x)test_x=pca.inverse_transform(test_x)c=pca.n_components_plt.figure(figsize=(8,4));plt.subplot(1, 2, 1);image=np.reshape(data.train.images[3],[28,28])plt.imshow(image, cmap='Greys_r')plt.title("Original Data")plt.subplot(1, 2, 2);image1=train_x[3].reshape(28,28)image.shapeplt.imshow(image1, cmap='Greys_r')plt.title("Original Data after 0.8 PCA")plt.figure(figsize=(10,8))plt.plot(range(c), np.cumsum(pca.explained_variance_ratio_))plt.grid()plt.title("Cumulative Explained Variance")plt.xlabel('number of components')plt.ylabel('cumulative explained variance');num_iters=10hidden_1=1024hidden_2=1024input_l=percentout_l=10'''input layer'''x=tf.placeholder(tf.float32, [None, 28,28,1])x=tf.reshape(x,[-1, input_l])w1=tf.Variable(tf.random_normal([input_l,hidden_1])) w2=tf.Variable(tf.random_normal([hidden_1,hidden_2]))w3=tf.Variable(tf.random_normal([hidden_2,out_l]))b1=tf.Variable(tf.random_normal([hidden_1]))b2=tf.Variable(tf.random_normal([hidden_2]))b3=tf.Variable(tf.random_normal([out_l]))Layer1=tf.nn.relu_layer(x,w1,b1)Layer2=tf.nn.relu_layer(Layer1,w2,b2)y_pred=tf.matmul(Layer2,w3)+b3y_true=tf.placeholder(tf.float32,[None,out_l])loss=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y_pred, labels=y_true))optimizer= tf.train.AdamOptimizer(0.006).minimize(loss)correct_pred=tf.equal(tf.argmax(y_pred,1), tf.argmax(y_true,1))accuracy= tf.reduce_mean(tf.cast(correct_pred, tf.float32))store_training=[]store_step=[]m = 10000init=tf.global_variables_initializer()with tf.Session() as sess: sess.run(init) for epoch in range(num_iters): indices = random.sample(range(0, m), 100) batch_xs = train_x[indices] batch_ys = train_y[indices] sess.run(optimizer, feed_dict={x:batch_xs, y_true:batch_ys}) training=sess.run(accuracy, feed_dict={x:test_x, y_true:test_y}) store_training.append(training) testing=sess.run(accuracy, feed_dict={x:test_x, y_true:test_y})print('Accuracy :{:.4}%'.format(testing*100))z_reg=len(store_training)x_reg=np.arange(0,z_reg,1)y_reg=store_trainingplt.figure(1)plt.plot(x_reg, y_reg,label='Regular Accuracy')这是我得到的错误信息：
"Traceback (most recent call last): File "<ipython-input-2-ff57ada92ef5>", line 135, in <module>sess.run(optimizer, feed_dict={x:batch_xs, y_true:batch_ys}) File "C:\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 929, in run run_metadata_ptr) File "C:\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1128, in _run str(subfeed_t.get_shape()))) ValueError: Cannot feed value of shape (100, 784) for Tensor 'Reshape:0', which has shape '(?, 600)'"
回答：
首先，我建议仅对训练集进行PCA拟合，因为训练集和测试集可能会得到不同的PCA分量。最简单的修复方法是更改以下代码段：
percent=600pca=PCA(percent)train_x=pca.fit_transform(train_x)test_x=pca.fit_transform(test_x)改为
percent=.80pca=PCA(percent)pca.fit(train_x)train_x=pca.transform(train_x)test_x=pca.transform(test_x)其次，你在进行PCA时使用了percent=600，然后应用了PCA的逆变换，这意味着你回到了原始特征数量的空间。为了开始学习减少后的PCA分量，你也可以尝试更改这段代码：
train_x=pca.inverse_transform(train_x)test_x=pca.inverse_transform(test_x)c=pca.n_components_<plotting code> input_l=percent改为：
c=pca.n_components_#plotting commented out input_l=c这应该会为后续的优化过程提供正确的张量维度。
