原文链接:http://blog.csdn.net/lanxuecc/article/details/52485077
1 第一种方法,使用caffe自带的caffe/python/classify.py
因为classify.py中的测试接口caffe.Classifier需要训练图片的均值文件作为输入参数,而实际lenet-5训练时并未计算均值文件,所以这里创建一个全0的均值文件输入。编写一个zeronp.py文件如下
import numpy as np
zeros=np.zeros((28,28,1),dtype=no.float32)
np.save('meanfile.npy',zeros)
python zeronp.py来生成均值文件meanfile.npy,这里注意宽高要与输入测试的图片宽高一致
caffe自带的classify.py,将其修改保存为classifymnist.py文件
#!/usr/bin/env python
"""
classify.py is an out-of-the-box image classifer callable from the command line.
By default it configures and runs the Caffe reference ImageNet model.
"""
import numpy as np
import os
import sys
import argparse
import glob
import time
import pandas as pd
sys.path.append('/home/zq/caffe/python')
import caffe
def main(argv):
pycaffe_dir = os.path.dirname(__file__)
parser = argparse.ArgumentParser()
# Required arguments: input and output files.
parser.add_argument(
"input_file",
help="Input image, directory, or npy."
)
parser.add_argument(
"output_file",
help="Output npy filename."
)
# Optional arguments.
parser.add_argument(
"--model_def",
default=os.path