问基于TensorFlow的多对多LSTM视频分类

EN

import tensorflow as tf
from tensorflow.contrib import rnn
import numpy as np

# Training Parameters
batch = 5 # number of examples
frames = time_step_size = 20
height = 60
width = 80
channel = 3

lstm_size = 240
num_classes = 2

# Creating random data

input_x = np.random.normal(size=[batch, frames, height, width, channel])
input_y = np.zeros((batch, num_classes))
B = np.ones(batch)
input_y[:,1] = B

X = tf.placeholder("float", [None, frames, height, width, channel], name='InputData')
Y = tf.placeholder("float", [None, num_classes], name='LabelData')

with tf.name_scope('Model'):
    XR = tf.reshape(X, [-1, height*width*channel]) # shape=(?, 14400)
    X_split3 = tf.split(XR, time_step_size, 0) # 20 tensors of shape=(?, 14400)

    lstm = rnn.BasicLSTMCell(lstm_size, forget_bias=1.0, state_is_tuple=True)
    outputs, _states = rnn.static_rnn(lstm, X_split3, dtype=tf.float32) # 20 tensors of shape=(?, 240)
    logits = tf.layers.dense(outputs[-1], num_classes, name='logits') # shape=(?, 2)

prediction = tf.nn.softmax(logits)

# Define loss and optimizer
with tf.name_scope('Loss'):
    loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=Y))

with tf.name_scope('optimizer'):
    optimizer = tf.train.AdamOptimizer(learning_rate=0.001, beta1=0.9, beta2=0.999, epsilon=1e-08, use_locking=False, name='Adam')
train_op = optimizer.minimize(loss_op)

# Evaluate model (with test logits, for dropout to be disabled)
correct_pred = tf.equal(tf.argmax(prediction, 1), tf.argmax(Y, 1))
with tf.name_scope('Accuracy'):
    accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

with tf.Session() as sess:
    tf.global_variables_initializer().run()
    logits_output = sess.run(logits, feed_dict={X: input_x})
    print(logits_output.shape) # shape=(5, 2)

    sess.run(train_op, feed_dict={X: input_x, Y: input_y})

    loss, acc = sess.run([loss_op, accuracy], feed_dict={X: input_x, Y: input_y})
    print("Loss: ", loss) # loss:  1.46626135e-05
    print("Accuracy: ", acc) # Accuracy:  1.0