Python PyCaffe-更改脚本以获取10个图像作为输入，而不是一个

我有一个项目，我想在python脚本中使用Yahoo的OpenNSFW net，但实际上，该脚本只使用一个图像示例，计算向前传递大约需要270ms（有点太慢）

我认为将它摊销到50张图片上会更快，但我不确定我是否可以只用deployprototxt文档来实现这一点

我在这里更改了deploy.prototxt文档，方法是更改dim 1->10，如下所示：

name: "ResNet_50_1by2_nsfw"
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param { shape: { dim: 10 dim: 3 dim: 224 dim: 224 } }
}
...

现在我需要一种在这里编码的方法：

#!/usr/bin/env python
"""
Copyright 2016 Yahoo Inc.
Licensed under the terms of the 2 clause BSD license. 
Please see LICENSE file in the project root for terms.
"""

import numpy as np
import os
import sys
import argparse
import glob
import time
from PIL import Image
from StringIO import StringIO
import caffe


def resize_image(data, sz=(256, 256)):
    """
    Resize image. Please use this resize logic for best results instead of the 
    caffe, since it was used to generate training dataset 
    :param str data:
        The image data
    :param sz tuple:
        The resized image dimensions
    :returns bytearray:
        A byte array with the resized image
    """
    img_data = str(data)
    im = Image.open(StringIO(img_data))
    if im.mode != "RGB":
        im = im.convert('RGB')
    imr = im.resize(sz, resample=Image.BILINEAR)
    fh_im = StringIO()
    imr.save(fh_im, format='JPEG')
    fh_im.seek(0)
    return bytearray(fh_im.read())

def caffe_preprocess_and_compute(pimg, caffe_transformer=None, caffe_net=None,
    output_layers=None):
    """
    Run a Caffe network on an input image after preprocessing it to prepare
    it for Caffe.
    :param PIL.Image pimg:
        PIL image to be input into Caffe.
    :param caffe.Net caffe_net:
        A Caffe network with which to process pimg afrer preprocessing.
    :param list output_layers:
        A list of the names of the layers from caffe_net whose outputs are to
        to be returned.  If this is None, the default outputs for the network
        are returned.
    :return:
        Returns the requested outputs from the Caffe net.
    """
    if caffe_net is not None:

        # Grab the default output names if none were requested specifically.
        if output_layers is None:
            output_layers = caffe_net.outputs

        img_data_rs = resize_image(pimg, sz=(256, 256))
        image = caffe.io.load_image(StringIO(img_data_rs))

        H, W, _ = image.shape
        _, _, h, w = caffe_net.blobs['data'].data.shape
        h_off = max((H - h) / 2, 0)
        w_off = max((W - w) / 2, 0)
        crop = image[h_off:h_off + h, w_off:w_off + w, :]
        transformed_image = caffe_transformer.preprocess('data', crop)
        transformed_image.shape = (1,) + transformed_image.shape

        input_name = caffe_net.inputs[0]
        all_outputs = caffe_net.forward_all(blobs=output_layers,
                    **{input_name: transformed_image})

        outputs = all_outputs[output_layers[0]][0].astype(float)
        return outputs
    else:
        return []


def main(argv):
    pycaffe_dir = os.path.dirname(__file__)

    parser = argparse.ArgumentParser()
    # Required arguments: input file.
    parser.add_argument(
        "input_file",
        help="Path to the input image file"
    )

    # Optional arguments.
    parser.add_argument(
        "--model_def",
        help="Model definition file."
    )
    parser.add_argument(
        "--pretrained_model",
        help="Trained model weights file."
    )

    args = parser.parse_args()
    image_data = open(args.input_file).read()

    # Pre-load caffe model.
    nsfw_net = caffe.Net(args.model_def,  # pylint: disable=invalid-name
        args.pretrained_model, caffe.TEST)

    # Load transformer
    # Note that the parameters are hard-coded for best results
    caffe_transformer = caffe.io.Transformer({'data': nsfw_net.blobs['data'].data.shape})
    caffe_transformer.set_transpose('data', (2, 0, 1))  # move image channels to outermost
    caffe_transformer.set_mean('data', np.array([104, 117, 123]))  # subtract the dataset-mean value in each channel
    caffe_transformer.set_raw_scale('data', 255)  # rescale from [0, 1] to [0, 255]
    caffe_transformer.set_channel_swap('data', (2, 1, 0))  # swap channels from RGB to BGR

    # Classify.
    scores = caffe_preprocess_and_compute(image_data, caffe_transformer=caffe_transformer, caffe_net=nsfw_net, output_layers=['prob'])

    # Scores is the array containing SFW / NSFW image probabilities
    # scores[1] indicates the NSFW probability
    print "NSFW score:  " , scores[1]



if __name__ == '__main__':
    main(sys.argv)

---

有一种简单的方法可以做到这一点吗？

您可以在caffe提供的示例脚本中看到一个将多个图像提供给分类器的示例

---

基本上，您需要将

变换的_图像

制作成4D阵列，不同的图像沿第0轴堆叠。

您可以在caffe提供的示例脚本中看到将多个图像馈送到分类器的示例

---

基本上，您需要将

变换的\u图像

制作成4D阵列，不同的图像沿第0轴堆叠。

如何使用

NetSpec（）

设置输入形状？e、 g.

net.data=layers.Input（）

，但这并不指定输入shape@yellow01请考虑将此注释作为一个新问题。如何使用<代码> NETScript（）/代码>设置输入形状？e、 g.

net.data=layers.Input（）

，但这并不指定输入shape@yellow01请考虑把这个评论作为一个新的问题。