4

slim.conv2d用来设置 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

如果我想初始化现有 VGG 模型的变量conv1conv2来自现有 VGG 模型的变量。

我该怎么做?

4

3 回答 3

2

您还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)
于 2017-06-20T07:23:52.163 回答
0

我已经用 tf.nn.conv2d(input, kernel...) 替换了 slim.conv2d,其中内核是使用 tf.get_variable 创建的,并使用 tf.assign 进行分配。

于 2017-06-16T09:32:27.273 回答
0

我假设您有现有 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恢复,但在检查点中的变量名称和模型中的变量之间指定自定义映射。请参阅此处的评论:https ://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/slim/python/slim/learning.py#L146

于 2017-05-08T16:50:45.893 回答