我在这里编写了一个简单的TensorFlow程序，用于读取特征列表并尝试预测类别。
with tf.Session() as sess: sess.run(tf.initialize_all_variables()) for epoch in range (hm_epochs): epoch_loss = 0 itere = int(X_train.shape[0]/batch_size) last = 0 add = 1 for start in range(itere): x_train_epoch = X_train[last: ((start + add) * batch_size),:] y_train_epoch = y_1Hot_train.eval()[last: ((start + add) * batch_size),:]# print("shape of x", x_train_epoch.shape, "shape of y", y_train_epoch.shape) _, c = sess.run([optimizer, cost], feed_dict = {x: x_train_epoch, y: y_train_epoch}) epoch_loss += c last = start * batch_size add = 0 print('Epoch', epoch, 'completed out of', hm_epochs, 'loss', epoch_loss ) correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct, 'float')) print('Accuracy:', accuracy.eval( {x: X_test, y: y_1Hot_test.eval() }))链接: https://gist.github.com/makark/79af6ca53ca27d51abb1d87c9b9bac07
数据文件: https://gist.github.com/makark/eb859f50237edb9343f3ca32aeb3be2b
然而，当我运行代码时，损失值一直返回“nan”。我不确定发生了什么…任何帮助将不胜感激！
WARNING:tensorflow:From <ipython-input-149-0164f4af7d52>:46: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.Instructions for updating:Use `tf.global_variables_initializer` instead.Epoch 0 completed out of 10 loss nanEpoch 1 completed out of 10 loss nanEpoch 2 completed out of 10 loss nanEpoch 3 completed out of 10 loss nanEpoch 4 completed out of 10 loss nanEpoch 5 completed out of 10 loss nanEpoch 6 completed out of 10 loss nanEpoch 7 completed out of 10 loss nanEpoch 8 completed out of 10 loss nanEpoch 9 completed out of 10 loss nanAccuracy: 0.589097回答：
- 输入数据中包含NaN值，可以通过
X[np.isnan(X)] = 0来修复。 -
输入数据未进行缩放，可以使用sklearn的
StandardScaler来标准化你的输入数据。 -
将权重设置为较小的初始值，使用random_normal中的stddev参数。
- 修复输出计算中的错误：
output = tf.add(tf.matmul(l3, output_layer['weights']),output_layer['biases'] )。
