Python 在tensorflow代码中，文件名放在何处以及如何放？

我从Sirajology的github复制了一个tensorflow代码。它应该将.csv加载到单层神经网络中

我的问题是，如何以及在何处将.csv文件放入代码中

此外，我不知道代码是否会自动将.csv分割为训练和测试数据，或者在将其输入神经网络之前是否需要使用不同的代码

我花了很多时间学习python和tensorflow，了解一些基本概念，但我还是个新手。感谢您的帮助！谢谢

#I have eliminated all code that is obviously irrelevant to the question

tf.app.flags.DEFINE_string('train', None,
                       'File containing the training data (labels & features).')
tf.app.flags.DEFINE_string('test', None,
                       'File containing the test data (labels & features).')
tf.app.flags.DEFINE_integer('num_epochs', 1,
                        'Number of examples to separate from the training '
                        'data for the validation set.')
tf.app.flags.DEFINE_boolean('verbose', False, 'Produce verbose output.')
FLAGS = tf.app.flags.FLAGS

# Extract numpy representations of the labels and features given rows consisting of:
#   label, feat_0, feat_1, ..., feat_n
def extract_data(filename):

# Arrays to hold the labels and feature vectors.
    labels = []
    fvecs = []

# Iterate over the rows, splitting the label from the features. Convert labels
# to integers and features to floats.
for line in file(filename):
    row = line.split(",")
    labels.append(int(row[0]))
    fvecs.append([float(x) for x in row[1:]])

# Convert the array of float arrays into a numpy float matrix.
fvecs_np = np.matrix(fvecs).astype(np.float32)

# Convert the array of int labels into a numpy array.
labels_np = np.array(labels).astype(dtype=np.uint8)

# Convert the int numpy array into a one-hot matrix.
labels_onehot = (np.arange(NUM_LABELS) == labels_np[:, None]).astype(np.float32)

# Return a pair of the feature matrix and the one-hot label matrix.
return fvecs_np,labels_onehot

def main(argv=None):
# Be verbose?
verbose = FLAGS.verbose

# Get the data.
train_data_filename = FLAGS.train
test_data_filename = FLAGS.test

# Extract it into numpy matrices.
train_data,train_labels = extract_data(train_data_filename)
test_data, test_labels = extract_data(test_data_filename)

# Get the shape of the training data.
train_size,num_features = train_data.shape

# Get the number of epochs for training.
num_epochs = FLAGS.num_epochs

# This is where training samples and labels are fed to the graph.
# These placeholder nodes will be fed a batch of training data at each
# training step using the {feed_dict} argument to the Run() call below.
x = tf.placeholder("float", shape=[None, num_features])
y_ = tf.placeholder("float", shape=[None, NUM_LABELS])

# For the test data, hold the entire dataset in one constant node.
test_data_node = tf.constant(test_data)

# Define and initialize the network.

# These are the weights that inform how much each feature contributes to
# the classification.
W = tf.Variable(tf.zeros([num_features,NUM_LABELS]))
b = tf.Variable(tf.zeros([NUM_LABELS]))
y = tf.nn.softmax(tf.matmul(x,W) + b)

# Optimization.
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

# Evaluation.
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

# Create a local session to run this computation.
with tf.Session() as s:
    # Run all the initializers to prepare the trainable parameters.
    tf.initialize_all_variables().run()
    if verbose:
        print ('Initialized!')
        print
        print ('Training.')

    # Iterate and train.
    for step in xrange(num_epochs * train_size // BATCH_SIZE):
        if verbose:
            print (step,)

        offset = (step * BATCH_SIZE) % train_size
        batch_data = train_data[offset:(offset + BATCH_SIZE), :]
        batch_labels = train_labels[offset:(offset + BATCH_SIZE)]
        train_step.run(feed_dict={x: batch_data, y_: batch_labels})

        if verbose and offset >= train_size-BATCH_SIZE:
            print

    # Give very detailed output.
    if verbose:
        print
        print ('Weight matrix.')
        print (s.run(W))
        print
        print ('Bias vector.')
        print (s.run(b))
        print
        print ("Applying model to first test instance.")
        first = test_data[:1]
        print ("Point =", first)
        print ("Wx+b = ", s.run(tf.matmul(first,W)+b))
        print ("softmax(Wx+b) = ", s.run(tf.nn.softmax(tf.matmul(first,W)+b)))
        print

    print ("Accuracy:", accuracy.eval(feed_dict={x: test_data, y_: test_labels}))


if __name__ == '__main__':
tf.app.run()

---

它希望在终端中作为参数接收它

下面的行正在检查它：

tf.app.flags.DEFINE_string('train', None,
                       'File containing the training data (labels & features).')
tf.app.flags.DEFINE_string('test', None,
                       'File containing the test data (labels & features).')
tf.app.flags.DEFINE_integer('num_epochs', 1,
                        'Number of examples to separate from the training '
                        'data for the validation set.')

因此，您只需将其作为：

python YourScript.py --train FileName.csv --test TestName.csv --num_epochs 5 --verbose True

---

谢谢，这很有道理。我正在得到一个错误“文件不违抗”，但会试图解决Sootok，如果它解决了你的问题，请接受正确的答案。我应该把你的答案标记为正确，因为它回答了这个问题，然后为新的错误信息启动一个新的线程？通过修复，我相信文件正在进入代码，但似乎还有其他问题。谢谢是的，最好把不同的问题分成不同的问题。