Python TensorflowUtils.conv2d_transpose_strided方法代码示例

# 需要导入模块: import TensorflowUtils [as 别名]
# 或者: from TensorflowUtils import conv2d_transpose_strided [as 别名]
def generator(z, train_mode):
    with tf.variable_scope("generator") as scope:
        W_0 = utils.weight_variable([FLAGS.z_dim, 64 * GEN_DIMENSION / 2 * IMAGE_SIZE / 16 * IMAGE_SIZE / 16],
                                    name="W_0")
        b_0 = utils.bias_variable([64 * GEN_DIMENSION / 2 * IMAGE_SIZE / 16 * IMAGE_SIZE / 16], name="b_0")
        z_0 = tf.matmul(z, W_0) + b_0
        h_0 = tf.reshape(z_0, [-1, IMAGE_SIZE / 16, IMAGE_SIZE / 16, 64 * GEN_DIMENSION / 2])
        h_bn0 = utils.batch_norm(h_0, 64 * GEN_DIMENSION / 2, train_mode, scope="gen_bn0")
        h_relu0 = tf.nn.relu(h_bn0, name='relu0')
        utils.add_activation_summary(h_relu0)

        # W_1 = utils.weight_variable([5, 5, 64 * GEN_DIMENSION/2, 64 * GEN_DIMENSION], name="W_1")
        # b_1 = utils.bias_variable([64 * GEN_DIMENSION/2], name="b_1")
        # deconv_shape = tf.pack([tf.shape(h_relu0)[0], IMAGE_SIZE / 16, IMAGE_SIZE / 16, 64 * GEN_DIMENSION/2])
        # h_conv_t1 = utils.conv2d_transpose_strided(h_relu0, W_1, b_1, output_shape=deconv_shape)
        # h_bn1 = utils.batch_norm(h_conv_t1, 64 * GEN_DIMENSION/2, train_mode, scope="gen_bn1")
        # h_relu1 = tf.nn.relu(h_bn1, name='relu1')
        # utils.add_activation_summary(h_relu1)

        W_2 = utils.weight_variable([5, 5, 64 * GEN_DIMENSION / 4, 64 * GEN_DIMENSION / 2],
                                    name="W_2")
        b_2 = utils.bias_variable([64 * GEN_DIMENSION / 4], name="b_2")
        deconv_shape = tf.pack([tf.shape(h_relu0)[0], IMAGE_SIZE / 8, IMAGE_SIZE / 8, 64 * GEN_DIMENSION / 4])
        h_conv_t2 = utils.conv2d_transpose_strided(h_relu0, W_2, b_2, output_shape=deconv_shape)
        h_bn2 = utils.batch_norm(h_conv_t2, 64 * GEN_DIMENSION / 4, train_mode, scope="gen_bn2")
        h_relu2 = tf.nn.relu(h_bn2, name='relu2')
        utils.add_activation_summary(h_relu2)

        W_3 = utils.weight_variable([5, 5, 64 * GEN_DIMENSION / 8, 64 * GEN_DIMENSION / 4],
                                    name="W_3")
        b_3 = utils.bias_variable([64 * GEN_DIMENSION / 8], name="b_3")
        deconv_shape = tf.pack([tf.shape(h_relu2)[0], IMAGE_SIZE / 4, IMAGE_SIZE / 4, 64 * GEN_DIMENSION / 8])
        h_conv_t3 = utils.conv2d_transpose_strided(h_relu2, W_3, b_3, output_shape=deconv_shape)
        h_bn3 = utils.batch_norm(h_conv_t3, 64 * GEN_DIMENSION / 8, train_mode, scope="gen_bn3")
        h_relu3 = tf.nn.relu(h_bn3, name='relu3')
        utils.add_activation_summary(h_relu3)

        W_4 = utils.weight_variable([5, 5, 64 * GEN_DIMENSION / 16, 64 * GEN_DIMENSION / 8],
                                    name="W_4")
        b_4 = utils.bias_variable([64 * GEN_DIMENSION / 16], name="b_4")
        deconv_shape = tf.pack([tf.shape(h_relu3)[0], IMAGE_SIZE / 2, IMAGE_SIZE / 2, 64 * GEN_DIMENSION / 16])
        h_conv_t4 = utils.conv2d_transpose_strided(h_relu3, W_4, b_4, output_shape=deconv_shape)
        h_bn4 = utils.batch_norm(h_conv_t4, 64 * GEN_DIMENSION / 16, train_mode, scope="gen_bn4")
        h_relu4 = tf.nn.relu(h_bn4, name='relu4')
        utils.add_activation_summary(h_relu4)

        W_5 = utils.weight_variable([5, 5, NUM_OF_CHANNELS, 64 * GEN_DIMENSION / 16], name="W_5")
        b_5 = utils.bias_variable([NUM_OF_CHANNELS], name="b_5")
        deconv_shape = tf.pack([tf.shape(h_relu4)[0], IMAGE_SIZE, IMAGE_SIZE, NUM_OF_CHANNELS])
        h_conv_t5 = utils.conv2d_transpose_strided(h_relu4, W_5, b_5, output_shape=deconv_shape)
        pred_image = tf.nn.tanh(h_conv_t5, name='pred_image')
        utils.add_activation_summary(pred_image)

    return pred_image

# 需要导入模块: import TensorflowUtils [as 别名]
# 或者: from TensorflowUtils import conv2d_transpose_strided [as 别名]
def inference_strided(input_image):
    W1 = utils.weight_variable([9, 9, 3, 32])
    b1 = utils.bias_variable([32])
    tf.histogram_summary("W1", W1)
    tf.histogram_summary("b1", b1)
    h_conv1 = tf.nn.relu(utils.conv2d_basic(input_image, W1, b1))

    W2 = utils.weight_variable([3, 3, 32, 64])
    b2 = utils.bias_variable([64])
    tf.histogram_summary("W2", W2)
    tf.histogram_summary("b2", b2)
    h_conv2 = tf.nn.relu(utils.conv2d_strided(h_conv1, W2, b2))

    W3 = utils.weight_variable([3, 3, 64, 128])
    b3 = utils.bias_variable([128])
    tf.histogram_summary("W3", W3)
    tf.histogram_summary("b3", b3)
    h_conv3 = tf.nn.relu(utils.conv2d_strided(h_conv2, W3, b3))

    # upstrides
    W4 = utils.weight_variable([3, 3, 64, 128])
    b4 = utils.bias_variable([64])
    tf.histogram_summary("W4", W4)
    tf.histogram_summary("b4", b4)
    # print h_conv3.get_shape()
    # print W4.get_shape()
    h_conv4 = tf.nn.relu(utils.conv2d_transpose_strided(h_conv3, W4, b4))

    W5 = utils.weight_variable([3, 3, 32, 64])
    b5 = utils.bias_variable([32])
    tf.histogram_summary("W5", W5)
    tf.histogram_summary("b5", b5)
    h_conv5 = tf.nn.relu(utils.conv2d_transpose_strided(h_conv4, W5, b5))

    W6 = utils.weight_variable([9, 9, 32, 3])
    b6 = utils.bias_variable([3])
    tf.histogram_summary("W6", W6)
    tf.histogram_summary("b6", b6)
    pred_image = tf.nn.tanh(utils.conv2d_basic(h_conv5, W6, b6))

    return pred_image

# 需要导入模块: import TensorflowUtils [as 别名]
# 或者: from TensorflowUtils import conv2d_transpose_strided [as 别名]
def inpainter(embedding, train_mode):
    with tf.variable_scope("context_inpainter"):
        image_size = IMAGE_SIZE // 32
        with tf.name_scope("dec_fc") as scope:
            W_fc = utils.weight_variable([1024, image_size * image_size * 512], name="W_fc")
            b_fc = utils.bias_variable([image_size * image_size * 512], name="b_fc")
            h_fc = tf.nn.relu(tf.matmul(embedding, W_fc) + b_fc)

        with tf.name_scope("dec_conv1") as scope:
            h_reshaped = tf.reshape(h_fc, tf.pack([tf.shape(h_fc)[0], image_size, image_size, 512]))
            W_conv_t1 = utils.weight_variable_xavier_initialized([3, 3, 256, 512], name="W_conv_t1")
            b_conv_t1 = utils.bias_variable([256], name="b_conv_t1")
            deconv_shape = tf.pack([tf.shape(h_reshaped)[0], 2 * image_size, 2 * image_size, 256])
            h_conv_t1 = utils.conv2d_transpose_strided(h_reshaped, W_conv_t1, b_conv_t1, output_shape=deconv_shape)
            h_bn_t1 = utils.batch_norm(h_conv_t1, 256, train_mode, scope="conv_t1_bn")
            h_relu_t1 = tf.nn.relu(h_bn_t1)

        with tf.name_scope("dec_conv2") as scope:
            W_conv_t2 = utils.weight_variable_xavier_initialized([3, 3, 128, 256], name="W_conv_t2")
            b_conv_t2 = utils.bias_variable([128], name="b_conv_t2")
            deconv_shape = tf.pack([tf.shape(h_relu_t1)[0], 4 * image_size, 4 * image_size, 128])
            h_conv_t2 = utils.conv2d_transpose_strided(h_relu_t1, W_conv_t2, b_conv_t2, output_shape=deconv_shape)
            h_bn_t2 = utils.batch_norm(h_conv_t2, 128, train_mode, scope="conv_t2_bn")
            h_relu_t2 = tf.nn.relu(h_bn_t2)

        with tf.name_scope("dec_conv3") as scope:
            W_conv_t3 = utils.weight_variable_xavier_initialized([3, 3, 64, 128], name="W_conv_t3")
            b_conv_t3 = utils.bias_variable([64], name="b_conv_t3")
            deconv_shape = tf.pack([tf.shape(h_relu_t2)[0], 8 * image_size, 8 * image_size, 64])
            h_conv_t3 = utils.conv2d_transpose_strided(h_relu_t2, W_conv_t3, b_conv_t3, output_shape=deconv_shape)
            h_bn_t3 = utils.batch_norm(h_conv_t3, 64, train_mode, scope="conv_t3_bn")
            h_relu_t3 = tf.nn.relu(h_bn_t3)

        with tf.name_scope("dec_conv4") as scope:
            W_conv_t4 = utils.weight_variable_xavier_initialized([3, 3, 3, 64], name="W_conv_t4")
            b_conv_t4 = utils.bias_variable([3], name="b_conv_t4")
            deconv_shape = tf.pack([tf.shape(h_relu_t3)[0], 16 * image_size, 16 * image_size, 3])
            pred_image = utils.conv2d_transpose_strided(h_relu_t3, W_conv_t4, b_conv_t4, output_shape=deconv_shape)
    return pred_image

# 需要导入模块: import TensorflowUtils [as 别名]
# 或者: from TensorflowUtils import conv2d_transpose_strided [as 别名]
def decoder_conv(embedding):
    image_size = IMAGE_SIZE // 16
    with tf.name_scope("dec_fc") as scope:
        W_fc1 = utils.weight_variable([512, image_size * image_size * 256], name="W_fc1")
        b_fc1 = utils.bias_variable([image_size * image_size * 256], name="b_fc1")
        h_fc1 = tf.nn.relu(tf.matmul(embedding, W_fc1) + b_fc1)

    with tf.name_scope("dec_conv1") as scope:
        h_reshaped = tf.reshape(h_fc1, tf.pack([tf.shape(h_fc1)[0], image_size, image_size, 256]))
        W_conv_t1 = utils.weight_variable([3, 3, 128, 256], name="W_conv_t1")
        b_conv_t1 = utils.bias_variable([128], name="b_conv_t1")
        deconv_shape = tf.pack([tf.shape(h_fc1)[0], 2 * image_size, 2 * image_size, 128])
        h_conv_t1 = tf.nn.relu(
            utils.conv2d_transpose_strided(h_reshaped, W_conv_t1, b_conv_t1, output_shape=deconv_shape))

    with tf.name_scope("dec_conv2") as scope:
        W_conv_t2 = utils.weight_variable([3, 3, 64, 128], name="W_conv_t2")
        b_conv_t2 = utils.bias_variable([64], name="b_conv_t2")
        deconv_shape = tf.pack([tf.shape(h_conv_t1)[0], 4 * image_size, 4 * image_size, 64])
        h_conv_t2 = tf.nn.relu(
            utils.conv2d_transpose_strided(h_conv_t1, W_conv_t2, b_conv_t2, output_shape=deconv_shape))

    with tf.name_scope("dec_conv3") as scope:
        W_conv_t3 = utils.weight_variable([3, 3, 32, 64], name="W_conv_t3")
        b_conv_t3 = utils.bias_variable([32], name="b_conv_t3")
        deconv_shape = tf.pack([tf.shape(h_conv_t2)[0], 8 * image_size, 8 * image_size, 32])
        h_conv_t3 = tf.nn.relu(
            utils.conv2d_transpose_strided(h_conv_t2, W_conv_t3, b_conv_t3, output_shape=deconv_shape))

    with tf.name_scope("dec_conv4") as scope:
        W_conv_t4 = utils.weight_variable([3, 3, 3, 32], name="W_conv_t4")
        b_conv_t4 = utils.bias_variable([3], name="b_conv_t4")
        deconv_shape = tf.pack([tf.shape(h_conv_t3)[0], IMAGE_SIZE, IMAGE_SIZE, 3])
        pred_image = utils.conv2d_transpose_strided(h_conv_t3, W_conv_t4, b_conv_t4, output_shape=deconv_shape)

    return pred_image

# 需要导入模块: import TensorflowUtils [as 别名]
# 或者: from TensorflowUtils import conv2d_transpose_strided [as 别名]
def inference(image, keep_prob):
    """
    Semantic segmentation network definition
    :param image: input image. Should have values in range 0-255
    :param keep_prob:
    :return:
    """
    print("setting up vgg initialized conv layers ...")
    model_data = utils.get_model_data(FLAGS.model_dir, MODEL_URL)

    mean = model_data['normalization'][0][0][0]
    mean_pixel = np.mean(mean, axis=(0, 1))

    weights = np.squeeze(model_data['layers'])

    #processed_image = utils.process_image(image, mean_pixel)

    with tf.variable_scope("inference"):
        image_net = vgg_net(weights, image)
        conv_final_layer = image_net["conv5_3"]

        pool5 = utils.max_pool_2x2(conv_final_layer)

        W6 = utils.weight_variable([7, 7, 512, 4096], name="W6")
        b6 = utils.bias_variable([4096], name="b6")
        conv6 = utils.conv2d_basic(pool5, W6, b6)
        relu6 = tf.nn.relu(conv6, name="relu6")
        if FLAGS.debug:
            utils.add_activation_summary(relu6)
        relu_dropout6 = tf.nn.dropout(relu6, keep_prob=keep_prob)

        W7 = utils.weight_variable([1, 1, 4096, 4096], name="W7")
        b7 = utils.bias_variable([4096], name="b7")
        conv7 = utils.conv2d_basic(relu_dropout6, W7, b7)
        relu7 = tf.nn.relu(conv7, name="relu7")
        if FLAGS.debug:
            utils.add_activation_summary(relu7)
        relu_dropout7 = tf.nn.dropout(relu7, keep_prob=keep_prob)

        W8 = utils.weight_variable([1, 1, 4096, NUM_OF_CLASSESS], name="W8")
        b8 = utils.bias_variable([NUM_OF_CLASSESS], name="b8")
        conv8 = utils.conv2d_basic(relu_dropout7, W8, b8)
        # annotation_pred1 = tf.argmax(conv8, dimension=3, name="prediction1")

        # now to upscale to actual image size
        deconv_shape1 = image_net["pool4"].get_shape()
        W_t1 = utils.weight_variable([4, 4, deconv_shape1[3].value, NUM_OF_CLASSESS], name="W_t1")
        b_t1 = utils.bias_variable([deconv_shape1[3].value], name="b_t1")
        conv_t1 = utils.conv2d_transpose_strided(conv8, W_t1, b_t1, output_shape=tf.shape(image_net["pool4"]))
        fuse_1 = tf.add(conv_t1, image_net["pool4"], name="fuse_1")

        deconv_shape2 = image_net["pool3"].get_shape()
        W_t2 = utils.weight_variable([4, 4, deconv_shape2[3].value, deconv_shape1[3].value], name="W_t2")
        b_t2 = utils.bias_variable([deconv_shape2[3].value], name="b_t2")
        conv_t2 = utils.conv2d_transpose_strided(fuse_1, W_t2, b_t2, output_shape=tf.shape(image_net["pool3"]))
        fuse_2 = tf.add(conv_t2, image_net["pool3"], name="fuse_2")

        shape = tf.shape(image)
        deconv_shape3 = tf.stack([shape[0], shape[1], shape[2], NUM_OF_CLASSESS])
        W_t3 = utils.weight_variable([16, 16, NUM_OF_CLASSESS, deconv_shape2[3].value], name="W_t3")
        b_t3 = utils.bias_variable([NUM_OF_CLASSESS], name="b_t3")
        conv_t3 = utils.conv2d_transpose_strided(fuse_2, W_t3, b_t3, output_shape=deconv_shape3, stride=8)

        annotation_pred = tf.argmax(conv_t3, dimension=3, name="prediction")

    return tf.expand_dims(annotation_pred, dim=3), conv_t3