Py-faster-rcnn: AssertionError: Path does not exist: ...py-faster-rcnn/data/coco/images/train2014/COCO_train2014_000000262145.jpg
So I got the data from mscoco website and created the coco/annotations folder in data but I got the following error. How do you expect to get the data if not from mscoco website?
mona@pascal:~/computer_vision/py-faster-rcnn/data$ mkdir coco
mona@pascal:~/computer_vision/py-faster-rcnn/data$ cd coco
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco$ mkdir annotations
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco$ cd annotations/
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ ls
captions_train2014.json captions_val2014.json instances_train2014.json instances_val2014.json person_keypoints_train2014.json person_keypoints_val2014.json
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ cd ../../..
mona@pascal:~/computer_vision/py-faster-rcnn$ tools/train_net.py \
> --gpu 0 \
> --solver ./models/coco/VGG16/faster_rcnn_end2end/solver.prototxt \
> --weights data/imagenet_models/VGG16.v2.caffemodel \
> --imdb coco_2014_train+coco_2014_valminusminival \
> --iters 490000 \
> --cfg ./experiments/cfgs/faster_rcnn_end2end.yml
Called with args:
Namespace(cfg_file='./experiments/cfgs/faster_rcnn_end2end.yml', gpu_id=0, imdb_name='coco_2014_train+coco_2014_valminusminival', max_iters=490000, pretrained_model='data/imagenet_models/VGG16.v2.caffemodel', randomize=False, set_cfgs=None, solver='./models/coco/VGG16/faster_rcnn_end2end/solver.prototxt')
Using config:
{'DATA_DIR': '/home/mona/computer_vision/py-faster-rcnn/data',
'DEDUP_BOXES': 0.0625,
'EPS': 1e-14,
'EXP_DIR': 'faster_rcnn_end2end',
'GPU_ID': 0,
'MATLAB': 'matlab',
'MODELS_DIR': '/home/mona/computer_vision/py-faster-rcnn/models/pascal_voc',
'PIXEL_MEANS': array([[[ 102.9801, 115.9465, 122.7717]]]),
'RNG_SEED': 3,
'ROOT_DIR': '/home/mona/computer_vision/py-faster-rcnn',
'TEST': {'BBOX_REG': True,mona@pascal:~/computer_vision/py-faster-rcnn/data$ mkdir coco
mona@pascal:~/computer_vision/py-faster-rcnn/data$ cd coco
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco$ mkdir annotations
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco$ cd annotations/
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ ls
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ ls
captions_train2014.json captions_val2014.json instances_train2014.json instances_val2014.json person_keypoints_train2014.json person_keypoints_val2014.json
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ cd ../../..
mona@pascal:~/computer_vision/py-faster-rcnn$ ls
caffe-fast-rcnn data experiments lib LICENSE models output README.md tools VOCdevkit VOCdevkit_08-Jun-2007.tar VOCtest_06-Nov-2007.tar VOCtrainval_06-Nov-2007.tar
mona@pascal:~/computer_vision/py-faster-rcnn$ tools/train_net.py \
> --gpu 0 \
> --solver ./models/coco/VGG16/faster_rcnn_end2end/solver.prototxt \
> --weights data/imagenet_models/VGG16.v2.caffemodel \
> --imdb coco_2014_train+coco_2014_valminusminival \
> --iters 490000 \
> --cfg ./experiments/cfgs/faster_rcnn_end2end.yml
Called with args:
Namespace(cfg_file='./experiments/cfgs/faster_rcnn_end2end.yml', gpu_id=0, imdb_name='coco_2014_train+coco_2014_valminusminival', max_iters=490000, pretrained_model='data/imagenet_models/VGG16.v2.caffemodel', randomize=False, set_cfgs=None, solver='./models/coco/VGG16/faster_rcnn_end2end/solver.prototxt')
Using config:
{'DATA_DIR': '/home/mona/computer_vision/py-faster-rcnn/data',
'DEDUP_BOXES': 0.0625,
'EPS': 1e-14,
'EXP_DIR': 'faster_rcnn_end2end',
'GPU_ID': 0,
'MATLAB': 'matlab',
'MODELS_DIR': '/home/mona/computer_vision/py-faster-rcnn/models/pascal_voc',
'PIXEL_MEANS': array([[[ 102.9801, 115.9465, 122.7717]]]),
'RNG_SEED': 3,
'ROOT_DIR': '/home/mona/computer_vision/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': True,
'BBOX_REG': True,
'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': '',
'SNAPSHOT_ITERS': 10000,
'USE_FLIPPED': True,
'USE_PREFETCH': False},
'USE_GPU_NMS': True}
loading annotations into memory...
Done (t=20.47s)
creating index...
index created!
Loaded dataset `coco_2014_train` for training
Set proposal method: gt
Appending horizontally-flipped training examples...
/usr/local/lib/python2.7/dist-packages/numpy/core/fromnumeric.py:2652: VisibleDeprecationWarning: `rank` is deprecated; use the `ndim` attribute or function instead. To find the rank of a matrix see `numpy.linalg.matrix_rank`.
VisibleDeprecationWarning)
wrote gt roidb to /home/mona/computer_vision/py-faster-rcnn/data/cache/coco_2014_train_gt_roidb.pkl
done
Preparing training data...
Traceback (most recent call last):
File "tools/train_net.py", line 104, in <module>
imdb, roidb = combined_roidb(args.imdb_name)
File "tools/train_net.py", line 69, in combined_roidb
roidbs = [get_roidb(s) for s in imdb_names.split('+')]
File "tools/train_net.py", line 66, in get_roidb
roidb = get_training_roidb(imdb)
File "/home/mona/computer_vision/py-famona@pascal:~/computer_vision/py-faster-rcnn/data$ mkdir coco
mona@pascal:~/computer_vision/py-faster-rcnn/data$ cd coco
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco$ mkdir annotations
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco$ cd annotations/
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ ls
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ ls
captions_train2014.json captions_val2014.json instances_train2014.json instances_val2014.json person_keypoints_train2014.json person_keypoints_val2014.json
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ cd ../../..
mona@pascal:~/computer_vision/py-faster-rcnn$ ls
caffe-fast-rcnn data experiments lib LICENSE models output README.md tools VOCdevkit VOCdevkit_08-Jun-2007.tar VOCtest_06-Nov-2007.tar VOCtrainval_06-Nov-2007.tar
mona@pascal:~/computer_vision/py-faster-rcnn$ tools/train_net.py \
> --gpu 0 \
> --solver ./models/coco/VGG16/faster_rcnn_end2end/solver.prototxt \
> --weights data/imagenet_models/VGG16.v2.caffemodel \
> --imdb coco_2014_train+coco_2014_valminusminival \
> --iters 490000 \
> --cfg ./experiments/cfgs/faster_rcnn_end2end.yml
Called with args:
Namespace(cfg_file='./experiments/cfgs/faster_rcnn_end2end.yml', gpu_id=0, imdb_name='coco_2014_train+coco_2014_valminusminival', max_iters=490000, pretrained_model='data/imagenet_models/VGG16.v2.caffemodel', randomize=False, set_cfgs=None, solver='./models/coco/VGG16/faster_rcnn_end2end/solver.prototxt')
Using config:
{'DATA_DIR': '/home/mona/computer_vision/py-faster-rcnn/data',
'DEDUP_BOXES': 0.0625,
'EPS': 1e-14,
'EXP_DIR': 'faster_rcnn_end2end',
'GPU_ID': 0,
'MATLAB': 'matlab',
'MODELS_DIR': '/home/mona/computer_vision/py-faster-rcnn/models/pascal_voc',
'PIXEL_MEANS': array([[[ 102.9801, 115.9465, 122.7717]]]),
'RNG_SEED': 3,
'ROOT_DIR': '/home/mona/computer_vision/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': True,
'BBOX_REG': True,
'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': '',
'SNAPSHOT_ITERS': 10000,
'USE_FLIPPED': True,
'USE_PREFETCH': False},
'USE_GPU_NMS': True}
loading annotations into memory...
Done (t=20.47s)
creating index...
index created!
Loaded dataset `coco_2014_train` for training
Set proposal method: gt
Appending horizontally-flipped training examples...
/usr/local/lib/python2.7/dist-packages/numpy/core/fromnumeric.py:2652: VisibleDeprecationWarning: `rank` is deprecated; use the `ndim` attribute or function instead. To find the rank of a matrix see `numpy.linalg.matrix_rank`.
VisibleDeprecationWarning)
wrote gt roidb to /home/mona/computer_vision/py-faster-rcnn/data/cache/coco_2014_train_gt_roidb.pkl
done
Preparing training data...
Traceback (most recent call last):
File "tools/train_net.py", line 104, in <module>
imdb, roidb = combined_roidb(args.imdb_name)
File "tools/train_net.py", line 69, in commona@pascal:~/computer_vision/py-faster-rcnn/data$ mkdir coco
mona@pascal:~/computer_vision/py-faster-rcnn/data$ cd coco
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco$ mkdir annotations
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco$ cd annotations/
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ ls
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ ls
captions_train2014.json captions_val2014.json instances_train2014.json instances_val2014.json person_keypoints_train2014.json person_keypoints_val2014.json
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ cd ../../..
mona@pascal:~/computer_vision/py-faster-rcnn$ ls
caffe-fast-rcnn data experiments lib LICENSE models output README.md tools VOCdevkit VOCdevkit_08-Jun-2007.tar VOCtest_06-Nov-2007.tar VOCtrainval_06-Nov-2007.tar
mona@pascal:~/computer_vision/py-faster-rcnn$ tools/train_net.py \
> --gpu 0 \
> --solver ./models/coco/VGG16/faster_rcnn_end2end/solver.prototxt \
> --weights data/imagenet_models/VGG16.v2.caffemodel \
> --imdb coco_2014_train+coco_2014_valminusminival \
> --iters 490000 \
> --cfg ./experiments/cfgs/faster_rcnn_end2end.yml
Called with args:
Namespace(cfg_file='./experiments/cfgs/faster_rcnn_end2end.yml', gpu_id=0, imdb_name='coco_2014_train+coco_2014_valminusminival', max_iters=490000, pretrained_model='data/imagenet_models/VGG16.v2.caffemodel', randomize=False, set_cfgs=None, solver='./models/coco/VGG16/faster_rcnn_end2end/solver.prototxt')
Using config:
{'DATA_DIR': '/home/mona/computer_vision/py-faster-rcnn/data',
'DEDUP_BOXES': 0.0625,
'EPS': 1e-14,
'EXP_DIR': 'faster_rcnn_end2end',
'GPU_ID': 0,
'MATLAB': 'matlab',
'MODELS_DIR': '/home/mona/computer_vision/py-faster-rcnn/models/pascal_voc',
'PIXEL_MEANS': array([[[ 102.9801, 115.9465, 122.7717]]]),
'RNG_SEED': 3,
'ROOT_DIR': '/home/mona/computer_vision/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': True,
'BBOX_REG': True,
'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': '',
'SNAPSHOT_ITERS': 10000,
'USE_FLIPPED': True,
'USE_PREFETCH': False},
'USE_GPU_NMS': True}
loading annotations into memory...
Done (t=20.47s)
creating index...mona@pascal:~/computer_vision/py-faster-rcnn/data$ mkdir coco
mona@pascal:~/computer_vision/py-faster-rcnn/data$ cd coco
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco$ mkdir annotations
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco$ cd annotations/
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ ls
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ ls
captions_train2014.json captions_val2014.json instances_train2014.json instances_val2014.json person_keypoints_train2014.json person_keypoints_val2014.json
mona@pascal:~/computer_vision/py-faster-rcnn/data/coco/annotations$ cd ../../..
mona@pascal:~/computer_vision/py-faster-rcnn$ ls
caffe-fast-rcnn data experiments lib LICENSE models output README.md tools VOCdevkit VOCdevkit_08-Jun-2007.tar VOCtest_06-Nov-2007.tar VOCtrainval_06-Nov-2007.tar
mona@pascal:~/computer_vision/py-faster-rcnn$ tools/train_net.py \
> --gpu 0 \
> --solver ./models/coco/VGG16/faster_rcnn_end2end/solver.prototxt \
> --weights data/imagenet_models/VGG16.v2.caffemodel \
> --imdb coco_2014_train+coco_2014_valminusminival \
> --iters 490000 \
> --cfg ./experiments/cfgs/faster_rcnn_end2end.yml
Called with args:
Namespace(cfg_file='./experiments/cfgs/faster_rcnn_end2end.yml', gpu_id=0, imdb_name='coco_2014_train+coco_2014_valminusminival', max_iters=490000, pretrained_model='data/imagenet_models/VGG16.v2.caffemodel', randomize=False, set_cfgs=None, solver='./models/coco/VGG16/faster_rcnn_end2end/solver.prototxt')
Using config:
{'DATA_DIR': '/home/mona/computer_vision/py-faster-rcnn/data',
'DEDUP_BOXES': 0.0625,
'EPS': 1e-14,
'EXP_DIR': 'faster_rcnn_end2end',
'GPU_ID': 0,
'MATLAB': 'matlab',
'MODELS_DIR': '/home/mona/computer_vision/py-faster-rcnn/models/pascal_voc',
'PIXEL_MEANS': array([[[ 102.9801, 115.9465, 122.7717]]]),
'RNG_SEED': 3,
'ROOT_DIR': '/home/mona/computer_vision/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': True,
'BBOX_REG': True,
'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': '',
'SNAPSHOT_ITERS': 10000,
'USE_FLIPPED': True,
'USE_PREFETCH': False},
'USE_GPU_NMS': True}
loading annotations into memory...
Done (t=20.47s)
creating index...
index created!
Loaded dataset `coco_2014_train` for training
Set proposal method: gt
Appending horizontally-flipped training examples...
/usr/local/lib/python2.7/dist-packages/numpy/core/fromnumeric.py:2652: VisibleDeprecationWarning: `rank` is deprecated; use the `ndim` attribute or function instead. To find the rank of a matrix see `numpy.linalg.matrix_rank`.
VisibleDeprecationWarning)
wrote gt roidb to /home/mona/computer_vision/py-faster-rcnn/data/cache/coco_2014_train_gt_roidb.pkl
done
Preparing training data...
Traceback (most recent call last):
File "tools/train_net.py", line 104, in <module>
imdb, roidb = combined_roidb(args.imdb_name)
File "tools/train_net.py", line 69, in combined_roidb
roidbs = [get_roidb(s) for s in imdb_names.split('+')]
File "tools/train_net.py", line 66, in get_roidb
roidb = get_training_roidb(imdb)
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/fast_rcnn/train.py", line 122, in get_training_roidb
rdl_roidb.prepare_roidb(imdb)
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/roi_data_layer/roidb.py", line 24, in prepare_roidb
for i in xrange(imdb.num_images)]
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/datasets/coco.py", line 107, in image_path_at
return self.image_path_from_index(self._image_index[i])
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/datasets/coco.py", line 120, in image_path_from_index
'Path does not exist: {}'.format(image_path)
AssertionError: Path does not exist: /home/mona/computer_vision/py-faster-rcnn/data/coco/images/train2014/COCO_train2014_000000262145.jpg
index created!
Loaded dataset `coco_2014_train` for training
Set proposal method: gt
Appending horizontally-flipped training examples...
/usr/local/lib/python2.7/dist-packages/numpy/core/fromnumeric.py:2652: VisibleDeprecationWarning: `rank` is deprecated; use the `ndim` attribute or function instead. To find the rank of a matrix see `numpy.linalg.matrix_rank`.
VisibleDeprecationWarning)
wrote gt roidb to /home/mona/computer_vision/py-faster-rcnn/data/cache/coco_2014_train_gt_roidb.pkl
done
Preparing training data...
Traceback (most recent call last):
File "tools/train_net.py", line 104, in <module>
imdb, roidb = combined_roidb(args.imdb_name)
File "tools/train_net.py", line 69, in combined_roidb
roidbs = [get_roidb(s) for s in imdb_names.split('+')]
File "tools/train_net.py", line 66, in get_roidb
roidb = get_training_roidb(imdb)
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/fast_rcnn/train.py", line 122, in get_training_roidb
rdl_roidb.prepare_roidb(imdb)
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/roi_data_layer/roidb.py", line 24, in prepare_roidb
for i in xrange(imdb.num_images)]
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/datasets/coco.py", line 107, in image_path_at
return self.image_path_from_index(self._image_index[i])
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/datasets/coco.py", line 120, in image_path_from_index
'Path does not exist: {}'.format(image_path)
AssertionError: Path does not exist: /home/mona/computer_vision/py-faster-rcnn/data/coco/images/train2014/COCO_train2014_000000262145.jpg
bined_roidb
roidbs = [get_roidb(s) for s in imdb_names.split('+')]
File "tools/train_net.py", line 66, in get_roidb
roidb = get_training_roidb(imdb)
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/fast_rcnn/train.py", line 122, in get_training_roidb
rdl_roidb.prepare_roidb(imdb)
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/roi_data_layer/roidb.py", line 24, in prepare_roidb
for i in xrange(imdb.num_images)]
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/datasets/coco.py", line 107, in image_path_at
return self.image_path_from_index(self._image_index[i])
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/datasets/coco.py", line 120, in image_path_from_index
'Path does not exist: {}'.format(image_path)
AssertionError: Path does not exist: /home/mona/computer_vision/py-faster-rcnn/data/coco/images/train2014/COCO_train2014_000000262145.jpg
ster-rcnn/tools/../lib/fast_rcnn/train.py", line 122, in get_training_roidb
rdl_roidb.prepare_roidb(imdb)
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/roi_data_layer/roidb.py", line 24, in prepare_roidb
for i in xrange(imdb.num_images)]
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/datasets/coco.py", line 107, in image_path_at
return self.image_path_from_index(self._image_index[i])
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/datasets/coco.py", line 120, in image_path_from_index
'Path does not exist: {}'.format(image_path)
AssertionError: Path does not exist: /home/mona/computer_vision/py-faster-rcnn/data/coco/images/train2014/COCO_train2014_000000262145.jpg
'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': True,
'BBOX_REG': True,
'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': '',
'SNAPSHOT_ITERS': 10000,
'USE_FLIPPED': True,
'USE_PREFETCH': False},
'USE_GPU_NMS': True}
loading annotations into memory...
Done (t=20.47s)
creating index...
index created!
Loaded dataset `coco_2014_train` for training
Set proposal method: gt
Appending horizontally-flipped training examples...
/usr/local/lib/python2.7/dist-packages/numpy/core/fromnumeric.py:2652: VisibleDeprecationWarning: `rank` is deprecated; use the `ndim` attribute or function instead. To find the rank of a matrix see `numpy.linalg.matrix_rank`.
VisibleDeprecationWarning)
wrote gt roidb to /home/mona/computer_vision/py-faster-rcnn/data/cache/coco_2014_train_gt_roidb.pkl
done
Preparing training data...
Traceback (most recent call last):
File "tools/train_net.py", line 104, in <module>
imdb, roidb = combined_roidb(args.imdb_name)
File "tools/train_net.py", line 69, in combined_roidb
roidbs = [get_roidb(s) for s in imdb_names.split('+')]
File "tools/train_net.py", line 66, in get_roidb
roidb = get_training_roidb(imdb)
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/fast_rcnn/train.py", line 122, in get_training_roidb
rdl_roidb.prepare_roidb(imdb)
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/roi_data_layer/roidb.py", line 24, in prepare_roidb
for i in xrange(imdb.num_images)]
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/datasets/coco.py", line 107, in image_path_at
return self.image_path_from_index(self._image_index[i])
File "/home/mona/computer_vision/py-faster-rcnn/tools/../lib/datasets/coco.py", line 120, in image_path_from_index
'Path does not exist: {}'.format(image_path)
AssertionError: Path does not exist: /home/mona/computer_vision/py-faster-rcnn/data/coco/images/train2014/COCO_train2014_000000262145.jpg
monajalal
All 4 comments
Are you certain that that path is correct, and that that image with that extension is there?
rtgoring
on 18 Oct 2016
As @rtgoring suggested, I'm assuming the file is there but with a PNG extension?
hgaiser
on 18 Oct 2016
In coco.py, line 116 ".jpg" is appended to the filename. If your using another extension, you must change the file extension.
rtgoring
on 18 Oct 2016
I had the same error, and it's because you don't have the dataset under the correct path. Your /path/to/coco/ should contain:
|- annotations/
|- common/
|- images/
|- license.txt
|- LuaAPI/
|- MatlabAPI/
|- PythonAPI/
|- README.txt
|- results/
where images contains:
|- test2014
|- train2014
|- val2014
|- test2015
|- test2017
|- train2017
|- unlabeled2017
|- val2017
These are the datasets that are downloaded from the cocodataset.org website.
and annotations contains:
|- captions_train2014.json
|- captions_val2017.json
|- instances_val2014.json
|- person_keypoints_train2017.json
|- captions_train2017.json
|- instances_train2014.json
|- instances_val2017.json
|- person_keypoints_val2014.json
|- captions_val2014.json
|- instances_train2017.json
|- person_keypoints_train2014.json
|_ person_keypoints_val2017.json
MartinPlantinga
on 13 Nov 2017
👍3
🎉1
Was this page helpful?
0 / 5 - 0 ratings
Related issues
boyentenbi
路
5Comments
Yakirbe
路
6Comments
monajalal
路
4Comments
forcecore
路
5Comments
monajalal
路
5Comments
Most helpful comment
I had the same error, and it's because you don't have the dataset under the correct path. Your /path/to/coco/ should contain:
|- annotations/
|- common/
|- images/
|- license.txt
|- LuaAPI/
|- MatlabAPI/
|- PythonAPI/
|- README.txt
|- results/
where images contains:
|- test2014
|- train2014
|- val2014
|- test2015
|- test2017
|- train2017
|- unlabeled2017
|- val2017
These are the datasets that are downloaded from the cocodataset.org website.
and annotations contains:
|- captions_train2014.json
|- captions_val2017.json
|- instances_val2014.json
|- person_keypoints_train2017.json
|- captions_train2017.json
|- instances_train2014.json
|- instances_val2017.json
|- person_keypoints_val2014.json
|- captions_val2014.json
|- instances_train2017.json
|- person_keypoints_train2014.json
|_ person_keypoints_val2017.json