caffe 教程 Fine-tuning CaffeNet for Style Recognition on “Flickr Style” Data 遇到的问题及解决方案

在使用这个教程时，主要遇到了两个问题：

1、数据下不下来。

python examples/finetune_flickr_style/assemble_data.py --workers=1 --images=2000 --seed 831486

运行上述指令时，程序莫名其妙就不动了，也不下载文件，程序也没有挂掉，好像进入了死锁状态。

查看源程序：assemble_data.py，可以看出assemble_data.py用了大量多线程，多进程。我的解决方案就是改源程序，不使用进程来下载了。并且，对下载进行了超时限定，超过6s就认为超时，进而不下载。

====================================================================================================

assemble_data.py中使用多线程，多进程的源代码如下：

pool = multiprocessing.Pool(processes=num_workers)
map_args = zip(df['image_url'], df['image_filename'])
results = pool.map(download_image, map_args)

===================================================================================================

我修改后的源码如下：

#!/usr/bin/env python3
"""
Form a subset of the Flickr Style data, download images to dirname, and write
Caffe ImagesDataLayer training file.
"""
import os
import urllib
import hashlib
import argparse
import numpy as np
import pandas as pd
from skimage import io
import multiprocessing
import socket

# Flickr returns a special image if the request is unavailable.
MISSING_IMAGE_SHA1 = '6a92790b1c2a301c6e7ddef645dca1f53ea97ac2'

example_dirname = os.path.abspath(os.path.dirname(__file__))
caffe_dirname = os.path.abspath(os.path.join(example_dirname, '../..'))
training_dirname = os.path.join(caffe_dirname, 'data/flickr_style')

def download_image(args_tuple):
"For use with multiprocessing map. Returns filename on fail."
try:
url, filename = args_tuple
if not os.path.exists(filename):
urllib.urlretrieve(url, filename)
with open(filename) as f:
assert hashlib.sha1(f.read()).hexdigest() != MISSING_IMAGE_SHA1
test_read_image = io.imread(filename)
return True
except KeyboardInterrupt:
raise Exception()  # multiprocessing doesn't catch keyboard exceptions
except:
return False

def mydownload_image(args_tuple):
"For use with multiprocessing map. Returns filename on fail."
try:
url, filename = args_tuple
if not os.path.exists(filename):
urllib.urlretrieve(url, filename)
with open(filename) as f:
assert hashlib.sha1(f.read()).hexdigest() != MISSING_IMAGE_SHA1
test_read_image = io.imread(filename)
return True
except KeyboardInterrupt:
raise Exception()  # multiprocessing doesn't catch keyboard exceptions
except:
return False

if __name__ == '__main__':
parser = argparse.ArgumentParser(
description='Download a subset of Flickr Style to a directory')
parser.add_argument(
'-s', '--seed', type=int, default=0,
help="random seed")
parser.add_argument(
'-i', '--images', type=int, default=-1,
help="number of images to use (-1 for all [default])",
)
parser.add_argument(
'-w', '--workers', type=int, default=-1,
help="num workers used to download images. -x uses (all - x) cores [-1 default]."
)
parser.add_argument(
'-l', '--labels', type=int, default=0,
help="if set to a positive value, only sample images from the first number of labels."
)

args = parser.parse_args()
np.random.seed(args.seed)
# Read data, shuffle order, and subsample.
csv_filename = os.path.join(example_dirname, 'flickr_style.csv.gz')
df = pd.read_csv(csv_filename, index_col=0, compression='gzip')
df = df.iloc[np.random.permutation(df.shape[0])]
if args.labels > 0:
df = df.loc[df['label'] < args.labels]
if args.images > 0 and args.images < df.shape[0]:
df = df.iloc[:args.images]

# Make directory for images and get local filenames.
if training_dirname is None:
training_dirname = os.path.join(caffe_dirname, 'data/flickr_style')
images_dirname = os.path.join(training_dirname, 'images')
if not os.path.exists(images_dirname):
os.makedirs(images_dirname)
df['image_filename'] = [
os.path.join(images_dirname, _.split('/')[-1]) for _ in df['image_url']
]

# Download images.
num_workers = args.workers
if num_workers <= 0:
num_workers = multiprocessing.cpu_count() + num_workers
print('Downloading {} images with {} workers...'.format(
df.shape[0], num_workers))
#pool = multiprocessing.Pool(processes=num_workers)
map_args = zip(df['image_url'], df['image_filename'])
#results = pool.map(download_image, map_args)
socket.setdefaulttimeout(6)
results = []
for item in map_args:
value = mydownload_image(item)
results.append(value)
if value == False:
print 'Flase'
else:
print '1'
# Only keep rows with valid images, and write out training file lists.
print len(results)
df = df[results]
for split in ['train', 'test']:
split_df = df[df['_split'] == split]
filename = os.path.join(training_dirname, '{}.txt'.format(split))
split_df[['image_filename', 'label']].to_csv(
filename, sep=' ', header=None, index=None)
print('Writing train/val for {} successfully downloaded images.'.format(
df.shape[0]))

修改主要有以下几点：

1、#!/usr/bin/env python3 使用python3

2、

#pool = multiprocessing.Pool(processes=num_workers)
map_args = zip(df['image_url'], df['image_filename'])
#results = pool.map(download_image, map_args)
socket.setdefaulttimeout(6)
results = []
for item in map_args:
value = mydownload_image(item)
results.append(value)
if value == False:
print 'Flase'
else:
print '1'
# Only keep rows with valid images, and write out training file lists.
print len(results)

只使用单线程下载，不使用多线程，多进程下载。并且，设定连接的超时时间为6s,socket.setdefaulttimeout(6)。

经过上述改进，就可以把数据下载下来。

===================================================================================================

2、

在运行命令：

./build/tools/caffe train -solver models/finetune_flickr_style/solver.prototxt -weights models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel

时遇到错误：

Failed to parse NetParameter file: models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel

出错的原因是我们传入的数据bvlc_reference_caffenet.caffemodel 并不是二进制的。

原因：因为我是在win7下，把bvlc_reference_caffenet.caffemodel下载下来，再使用winSCP传输到服务器上，直接在服务器上使用wget下载，速度太慢了，但是在传输的过程中winSCP就把bvlc_reference_caffenet.caffemodel的格式给篡改了,导致bvlc_reference_caffenet.caffemodel不是二进制的。

解决方案，把winSCP的传输格式设置成二进制，那么就可以解决这个问题。

详情见博客:http://blog.chinaunix.net/uid-20332519-id-5585964.html