问Tensorflow vgg16预测显着减慢

EN

import tensorflow as tf
import numpy as np

with tf.Session() as sess:

    # mock the previous layer's output with a placeholder
    pool5_input = tf.placeholder(dtype = tf.float32, shape = (None,7,7,512))

    # insert a print operation to print the shape
    pool5 = tf.Print(pool5_input, [ tf.shape(pool5_input) ], "pool5 shape is ", summarize = 4)

    layer_name = 'fc1'
    wd = tf.Variable(np.ones((25088, 4096), dtype='float32'), trainable=False, name=layer_name+'_wd')
    bd = tf.Variable(np.ones((4096,), dtype='float32'), trainable=False, name=layer_name+'_bd')
    layer_shape = [-1, wd.get_shape().as_list()[0]]
    print('layer_shape:', layer_shape)

    fc1_flat = tf.reshape(pool5, shape=layer_shape)
    fc1_flat = tf.Print(fc1_flat, [ tf.shape(fc1_flat) ], "fc1_flat shape is ")

    fc1 = tf.nn.relu( tf.nn.bias_add( tf.matmul(fc1_flat, wd, name=layer_name), bd ) )
    fc1 = tf.Print(fc1, [ tf.shape(fc1) ], "fc1 shape is ")

    import time
    sess.run(tf.global_variables_initializer())

    # evaluate network for in input of (minibatch_size, 7, 7, 512)
    minibatch_size = 32

    start = time.time()
    output = sess.run(fc1, feed_dict = { pool5_input: np.ones((minibatch_size, 7, 7, 512), dtype = 'float32')})

    elapsed = time.time() - start
    print("time to evaluate fully connected layer for minibatch size %d: %.3f seconds" % (minibatch_size, elapsed))
    print("output shape is",output.shape)

layer_shape: [-1, 25088]
...: I tensorflow/core/kernels/logging_ops.cc:79] pool5 shape is [32 7 7 512]
...: I tensorflow/core/kernels/logging_ops.cc:79] fc1_flat shape is [32 25088]
...: I tensorflow/core/kernels/logging_ops.cc:79] fc1 shape is [32 4096]
time to evaluate fully connected layer for minibatch size 32: 0.329 seconds
output shape is (32, 4096)