Question

我使用slim.conv2d设置VGG-net

with slim.arg_scope([slim.conv2d, slim.max_pool2d], padding='SAME'):
    conv1_1 = slim.conv2d(img, 64, [3, 3], scope='conv1')
    conv1_2 = slim.conv2d(conv1_1, 64, [3, 3], scope='conv1_1')
    pool1 = slim.max_pool2d(conv1_2, [2, 2], 2, scope='pool1_2')

    conv2_1 = slim.conv2d(pool1, 128, [3, 3], 1, scope='conv2_1')
    conv2_2 = slim.conv2d(conv2_1, 128, [3, 3], 1, scope='conv2_2')
    pool2 = slim.max_pool2d(conv2_2, [2, 2], 2, scope='pool2')

    conv3_1 = slim.conv2d(pool2, 256, [3, 3], 1, scope='conv3_1')
    conv3_2 = slim.conv2d(conv3_1, 256, [3, 3], 1, scope='conv3_2')
    conv3_3 = slim.conv2d(conv3_2, 256, [3, 3], 1, scope='conv3_3')
    pool3 = slim.max_pool2d(conv3_3, [2, 2], 2, scope='pool3')

    conv4_1 = slim.conv2d(pool3, 512, [3, 3], scope='conv4_1')
    # print conv4_1.shape
    conv4_2 = slim.conv2d(conv4_1, 512, [3, 3], scope='conv4_2')
    conv4_3 = slim.conv2d(conv4_2, 512, [3, 3], scope='conv4_3')  # 38

如果我想从现有的VGG模型中初始化conv1或conv2的变量。

我该怎么办？

Answer 1

您也可以按照此处的建议使用assign_from_values： Github - Initialize layers.convolution2d from numpy array

sess = tf.Session()
with sess.as_default():

    init = tf.global_variables_initializer()
    sess.run(init)

    path = pathlib.Path('./assets/classifier_weights.npz')
    if(path.is_file()):
        print("Initilize Weights from Numpy Array")
        init_weights = np.load(path)
        assign_op, feed_dict_init = slim.assign_from_values({
            'conv1/weights' : init_weights['conv1_w'],
        })
        sess.run(assign_op, feed_dict_init)

Answer 2

我假设你有一个现有VGG模型的检查点。

使用TF Slim执行此操作的一种方法是从检查点还原，但指定检查点中的变量名称与模型中的变量之间的自定义映射。请参阅此处的评论：https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/slim/python/slim/learning.py#L146

Answer 3

我用tf.nn.conv2d（输入，内核......）替换了slim.conv2d，其中内核是使用tf.get_variable创建的，并使用tf.assign分配。

如何使用现有模型的值初始化slim.conv2d（）中的权重

3 个答案: