当我尝试运行py-faster-rcnn时跟随Github中的README.md： ./experiments/scripts/faster_rcnn_alt_opt.sh 0 VGG_CNN_M_1024 pascal_voc
它像这样停留在舞台上： 断言错误：路径不存在：/home/jiaxin/py-faster-rcnn/data/VOCdevkit2007/VOC2007/ImageSets/Main/trainval.txt
+ set -e
+ export PYTHONUNBUFFERED=True
+ PYTHONUNBUFFERED=True
+ GPU_ID=0
+ NET=VGG_CNN_M_1024
+ NET_lc=vgg_cnn_m_1024
+ DATASET=pascal_voc
+ array=($@)
+ len=3
+ EXTRA_ARGS=
+ EXTRA_ARGS_SLUG=
+ case $DATASET in
+ TRAIN_IMDB=voc_2007_trainval
+ TEST_IMDB=voc_2007_test
+ PT_DIR=pascal_voc
+ ITERS=40000
++ date +%Y-%m-%d_%H-%M-%S
+ LOG=experiments/logs/faster_rcnn_alt_opt_VGG_CNN_M_1024_.txt.2016-07-30_19-36-05
+ exec
++ tee -a experiments/logs/faster_rcnn_alt_opt_VGG_CNN_M_1024_.txt.2016-07-30_19-36-05
+ echo Logging output to experiments/logs/faster_rcnn_alt_opt_VGG_CNN_M_1024_.txt.2016-07-30_19-36-05
Logging output to experiments/logs/faster_rcnn_alt_opt_VGG_CNN_M_1024_.txt.2016-07-30_19-36-05
+ ./tools/train_faster_rcnn_alt_opt.py --gpu 0 --net_name VGG_CNN_M_1024 --weights data/imagenet_models/VGG_CNN_M_1024.v2.caffemodel --imdb voc_2007_trainval --cfg experiments/cfgs/faster_rcnn_alt_opt.yml
Called with args:
Namespace(cfg_file='experiments/cfgs/faster_rcnn_alt_opt.yml', gpu_id=0, imdb_name='voc_2007_trainval', net_name='VGG_CNN_M_1024', pretrained_model='data/imagenet_models/VGG_CNN_M_1024.v2.caffemodel', set_cfgs=None)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Stage 1 RPN, init from ImageNet model
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Init model: data/imagenet_models/VGG_CNN_M_1024.v2.caffemodel
Using config:
{'DATA_DIR': '/home/jiaxin/py-faster-rcnn/data',
'DEDUP_BOXES': 0.0625,
'EPS': 1e-14,
'EXP_DIR': 'faster_rcnn_alt_opt',
'GPU_ID': 0,
'MATLAB': 'matlab',
'MODELS_DIR': '/home/jiaxin/py-faster-rcnn/models/pascal_voc',
'PIXEL_MEANS': array([[[ 102.9801, 115.9465, 122.7717]]]),
'RNG_SEED': 3,
'ROOT_DIR': '/home/jiaxin/py-faster-rcnn',
'TEST': {'BBOX_REG': True,
'HAS_RPN': True,
'MAX_SIZE': 1000,
'NMS': 0.3,
'PROPOSAL_METHOD': 'selective_search',
'RPN_MIN_SIZE': 16,
'RPN_NMS_THRESH': 0.7,
'RPN_POST_NMS_TOP_N': 300,
'RPN_PRE_NMS_TOP_N': 6000,
'SCALES': [600],
'SVM': False},
'TRAIN': {'ASPECT_GROUPING': True,
'BATCH_SIZE': 128,
'BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0],
'BBOX_NORMALIZE_MEANS': [0.0, 0.0, 0.0, 0.0],
'BBOX_NORMALIZE_STDS': [0.1, 0.1, 0.2, 0.2],
'BBOX_NORMALIZE_TARGETS': True,
'BBOX_NORMALIZE_TARGETS_PRECOMPUTED': False,
'BBOX_REG': False,
'BBOX_THRESH': 0.5,
'BG_THRESH_HI': 0.5,
'BG_THRESH_LO': 0.0,
'FG_FRACTION': 0.25,
'FG_THRESH': 0.5,
'HAS_RPN': True,
'IMS_PER_BATCH': 1,
'MAX_SIZE': 1000,
'PROPOSAL_METHOD': 'gt',
'RPN_BATCHSIZE': 256,
'RPN_BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0],
'RPN_CLOBBER_POSITIVES': False,
'RPN_FG_FRACTION': 0.5,
'RPN_MIN_SIZE': 16,
'RPN_NEGATIVE_OVERLAP': 0.3,
'RPN_NMS_THRESH': 0.7,
'RPN_POSITIVE_OVERLAP': 0.7,
'RPN_POSITIVE_WEIGHT': -1.0,
'RPN_POST_NMS_TOP_N': 2000,
'RPN_PRE_NMS_TOP_N': 12000,
'SCALES': [600],
'SNAPSHOT_INFIX': 'stage1',
'SNAPSHOT_ITERS': 10000,
'USE_FLIPPED': True,
'USE_PREFETCH': False},
'USE_GPU_NMS': True}
Process Process-1:
Traceback (most recent call last):
File "/usr/lib/python2.7/multiprocessing/process.py", line 258, in _bootstrap
self.run()
File "/usr/lib/python2.7/multiprocessing/process.py", line 114, in run
self._target(*self._args, **self._kwargs)
File "./tools/train_faster_rcnn_alt_opt.py", line 122, in train_rpn
roidb, imdb = get_roidb(imdb_name)
File "./tools/train_faster_rcnn_alt_opt.py", line 61, in get_roidb
imdb = get_imdb(imdb_name)
File "/home/jiaxin/py-faster-rcnn/tools/../lib/datasets/factory.py", line 38, in get_imdb
return __sets[name]()
File "/home/jiaxin/py-faster-rcnn/tools/../lib/datasets/factory.py", line 20, in <lambda>
__sets[name] = (lambda split=split, year=year: pascal_voc(split, year))
File "/home/jiaxin/py-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 38, in __init__
self._image_index = self._load_image_set_index()
File "/home/jiaxin/py-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 82, in _load_image_set_index
'Path does not exist: {}'.format(image_set_file)
AssertionError: Path does not exist: /home/jiaxin/py-faster-rcnn/data/VOCdevkit2007/VOC2007/ImageSets/Main/trainval.txt
我该怎么办？我在构建符号链接之前检查了trainval.txt文件，它存在。我不知道在构建符号链接后发生了什么，我不能再打开这个文件了。
我改变了我的命令： ./experiments/scripts/faster_rcnn_alt_opt.sh 0 VGG_CNN_M_1024 pascal_voc - 设置EXP_DIR foobar RNG_SEED 42 TRAIN.SCALES“[400,500,600,700]”
再次遇到另一个AssertionError：
我该怎么办？请帮我！
答案 0 :(得分：0)
我刚用Google搜索了第二个错误的解决方案。积分来自@faschinj https://github.com/rbgirshick/py-faster-rcnn/issues/132。
确保逗号后面没有空格，否则它们会被解析为单独的参数，如TRAIN.SCALES“[400,500,600,700]”
答案 1 :(得分：0)
我认为这是符号链接的错误。我的解决方案是首先删除文件夹'data'中的符号链接'VOCdevkit2007'。然后将文件夹'VOCdevkit'复制到'data'文件夹中，并将其重命名为'VOCdevkit2007'。
答案 2 :(得分：0)
在创建符号链接时，使用
ln -s ./VOCdevkit ./VOCdevkit2007
代替
ln -s $VOCdevkit VOCdevkit2007
因为作者可能创建了变量$VOCdevkit，而我们没有创建。然后ln命令将VOCdevkit2007链接到自身：
'./VOCdevkit2007' -> 'VOCdevkit2007'