Mask_rcnn: OSError: Unable to open file

[JohnWnx]

Hi, I'm able to run a training session, can anyone advise?

Thanks.

(MASKR) john@john-H270N-WIFI:~/Mask_RCNN$ sudo python3 samples/coco/coco.py train --dataset=/path/to/coco/ --model=coco
Using TensorFlow backend.
Command: train
Model: coco
Dataset: /path/to/coco/
Year: 2014
Logs: /home/logs
Auto Download: False

Configurations:
BACKBONE resnet101
BACKBONE_STRIDES [4, 8, 16, 32, 64]
BATCH_SIZE 2
BBOX_STD_DEV [0.1 0.1 0.2 0.2]
COMPUTE_BACKBONE_SHAPE None
DETECTION_MAX_INSTANCES 100
DETECTION_MIN_CONFIDENCE 0.7
DETECTION_NMS_THRESHOLD 0.3
FPN_CLASSIF_FC_LAYERS_SIZE 1024
GPU_COUNT 1
GRADIENT_CLIP_NORM 5.0
IMAGES_PER_GPU 2
IMAGE_MAX_DIM 1024
IMAGE_META_SIZE 93
IMAGE_MIN_DIM 800
IMAGE_MIN_SCALE 0
IMAGE_RESIZE_MODE square
IMAGE_SHAPE [1024 1024 3]
LEARNING_MOMENTUM 0.9
LEARNING_RATE 0.001
LOSS_WEIGHTS {'mrcnn_mask_loss': 1.0, 'rpn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'rpn_bbox_loss': 1.0}
MASK_POOL_SIZE 14
MASK_SHAPE [28, 28]
MAX_GT_INSTANCES 100
MEAN_PIXEL [123.7 116.8 103.9]
MINI_MASK_SHAPE (56, 56)
NAME coco
NUM_CLASSES 81
POOL_SIZE 7
POST_NMS_ROIS_INFERENCE 1000
POST_NMS_ROIS_TRAINING 2000
ROI_POSITIVE_RATIO 0.33
RPN_ANCHOR_RATIOS [0.5, 1, 2]
RPN_ANCHOR_SCALES (32, 64, 128, 256, 512)
RPN_ANCHOR_STRIDE 1
RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2]
RPN_NMS_THRESHOLD 0.7
RPN_TRAIN_ANCHORS_PER_IMAGE 256
STEPS_PER_EPOCH 1000
TOP_DOWN_PYRAMID_SIZE 256
TRAIN_BN False
TRAIN_ROIS_PER_IMAGE 200
USE_MINI_MASK True
USE_RPN_ROIS True
VALIDATION_STEPS 50
WEIGHT_DECAY 0.0001

Loading weights /home/mask_rcnn_coco.h5
Traceback (most recent call last):
File "samples/coco/coco.py", line 474, in
model.load_weights(model_path, by_name=True)
File "/home/john/Mask_RCNN/samples/coco/mrcnn/model.py", line 2123, in load_weights
f = h5py.File(filepath, mode='r')
File "/home/john/.local/lib/python3.5/site-packages/h5py/_hl/files.py", line 312, in __init__
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/home/john/.local/lib/python3.5/site-packages/h5py/_hl/files.py", line 142, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
OSError: Unable to open file (unable to open file: name = '/home/mask_rcnn_coco.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

[rbavery]

You have Auto Download: False set. Have you checked that the weights file
has been downloaded and are you correctly setting the path to that weights
file?

Ryan Avery
Graduate Student, WAVES Lab
Department of Geography
University of California, Santa Barbara

http://caylor.eri.ucsb.edu/people/avery/
http://caylor.eri.ucsb.edu/people/avery/

On Sat, Jul 14, 2018 at 4:59 PM, JohnWnx [e-mail] wrote:

Hi, I'm able to run a training session, can anyone advise?

Thanks.

(MASKR) john@john-H270N-WIFI:~/Mask_RCNN$ sudo python3
samples/coco/coco.py train --dataset=/path/to/coco/ --model=coco
Using TensorFlow backend.
Command: train
Model: coco
Dataset: /path/to/coco/
Year: 2014
Logs: /home/logs
Auto Download: False

Configurations:
BACKBONE resnet101
BACKBONE_STRIDES [4, 8, 16, 32, 64]
BATCH_SIZE 2
BBOX_STD_DEV [0.1 0.1 0.2 0.2]
COMPUTE_BACKBONE_SHAPE None
DETECTION_MAX_INSTANCES 100
DETECTION_MIN_CONFIDENCE 0.7
DETECTION_NMS_THRESHOLD 0.3
FPN_CLASSIF_FC_LAYERS_SIZE 1024
GPU_COUNT 1
GRADIENT_CLIP_NORM 5.0
IMAGES_PER_GPU 2
IMAGE_MAX_DIM 1024
IMAGE_META_SIZE 93
IMAGE_MIN_DIM 800
IMAGE_MIN_SCALE 0
IMAGE_RESIZE_MODE square
IMAGE_SHAPE [1024 1024 3]
LEARNING_MOMENTUM 0.9
LEARNING_RATE 0.001
LOSS_WEIGHTS {'mrcnn_mask_loss': 1.0, 'rpn_class_loss': 1.0,
'mrcnn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'rpn_bbox_loss': 1.0}
MASK_POOL_SIZE 14
MASK_SHAPE [28, 28]
MAX_GT_INSTANCES 100
MEAN_PIXEL [123.7 116.8 103.9]
MINI_MASK_SHAPE (56, 56)
NAME coco
NUM_CLASSES 81
POOL_SIZE 7
POST_NMS_ROIS_INFERENCE 1000
POST_NMS_ROIS_TRAINING 2000
ROI_POSITIVE_RATIO 0.33
RPN_ANCHOR_RATIOS [0.5, 1, 2]
RPN_ANCHOR_SCALES (32, 64, 128, 256, 512)
RPN_ANCHOR_STRIDE 1
RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2]
RPN_NMS_THRESHOLD 0.7
RPN_TRAIN_ANCHORS_PER_IMAGE 256
STEPS_PER_EPOCH 1000
TOP_DOWN_PYRAMID_SIZE 256
TRAIN_BN False
TRAIN_ROIS_PER_IMAGE 200
USE_MINI_MASK True
USE_RPN_ROIS True
VALIDATION_STEPS 50
WEIGHT_DECAY 0.0001

Loading weights /home/mask_rcnn_coco.h5
Traceback (most recent call last):
File "samples/coco/coco.py", line 474, in
model.load_weights(model_path, by_name=True)
File "/home/john/Mask_RCNN/samples/coco/mrcnn/model.py", line 2123, in
load_weights
f = h5py.File(filepath, mode='r')
File "/home/john/.local/lib/python3.5/site-packages/h5py/_hl/files.py",
line 312, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/home/john/.local/lib/python3.5/site-packages/h5py/_hl/files.py",
line 142, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
OSError: Unable to open file (unable to open file: name =
'/home/mask_rcnn_coco.h5', errno = 2, error message = 'No such file or
directory', flags = 0, o_flags = 0)

—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
https://github.com/matterport/Mask_RCNN/issues/778, or mute the thread
https://github.com/notifications/unsubscribe-auth/AVOkCdBahYHpqA-89kPaYgeoCVEGqPIaks5uGlvPgaJpZM4VQAKG
.

[JohnWnx]

@rbavery I have set dataset path to my downloaded train images from MSCOCO dataset and weights path to mask_rcnn_coco.h5
However, I'm still getting the error:
OSError: Unable to open file (unable to open file: name = '/home/john/MASK_RCNN/mask_rcnn_coco.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

Configurations:
BACKBONE resnet101
BACKBONE_STRIDES [4, 8, 16, 32, 64]
BATCH_SIZE 2
BBOX_STD_DEV [0.1 0.1 0.2 0.2]
COMPUTE_BACKBONE_SHAPE None
DETECTION_MAX_INSTANCES 100
DETECTION_MIN_CONFIDENCE 0.7
DETECTION_NMS_THRESHOLD 0.3
FPN_CLASSIF_FC_LAYERS_SIZE 1024
GPU_COUNT 1
GRADIENT_CLIP_NORM 5.0
IMAGES_PER_GPU 2
IMAGE_MAX_DIM 1024
IMAGE_META_SIZE 93
IMAGE_MIN_DIM 800
IMAGE_MIN_SCALE 0
IMAGE_RESIZE_MODE square
IMAGE_SHAPE [1024 1024 3]
LEARNING_MOMENTUM 0.9
LEARNING_RATE 0.001
LOSS_WEIGHTS {'mrcnn_class_loss': 1.0, 'mrcnn_mask_loss': 1.0, 'rpn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'rpn_bbox_loss': 1.0}
MASK_POOL_SIZE 14
MASK_SHAPE [28, 28]
MAX_GT_INSTANCES 100
MEAN_PIXEL [123.7 116.8 103.9]
MINI_MASK_SHAPE (56, 56)
NAME coco
NUM_CLASSES 81
POOL_SIZE 7
POST_NMS_ROIS_INFERENCE 1000
POST_NMS_ROIS_TRAINING 2000
ROI_POSITIVE_RATIO 0.33
RPN_ANCHOR_RATIOS [0.5, 1, 2]
RPN_ANCHOR_SCALES (32, 64, 128, 256, 512)
RPN_ANCHOR_STRIDE 1
RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2]
RPN_NMS_THRESHOLD 0.7
RPN_TRAIN_ANCHORS_PER_IMAGE 256
STEPS_PER_EPOCH 1000
TOP_DOWN_PYRAMID_SIZE 256
TRAIN_BN False
TRAIN_ROIS_PER_IMAGE 200
USE_MINI_MASK True
USE_RPN_ROIS True
VALIDATION_STEPS 50
WEIGHT_DECAY 0.0001

Loading weights /home/john/MASK_RCNN/mask_rcnn_coco.h5
Traceback (most recent call last):
File "samples/coco/coco.py", line 474, in
model.load_weights(model_path, by_name=True)
File "/home/john/Mask_RCNN/samples/coco/mrcnn/model.py", line 2123, in load_weights
f = h5py.File(filepath, mode='r')
File "/home/john/.local/lib/python3.5/site-packages/h5py/_hl/files.py", line 312, in __init__
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/home/john/.local/lib/python3.5/site-packages/h5py/_hl/files.py", line 142, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
OSError: Unable to open file (unable to open file: name = '/home/john/MASK_RCNN/mask_rcnn_coco.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

[rbavery]

Change MASK_RCNN to Mask_RCNN when you specify the model path.
Capitalization needs to match.

On Sun, Jul 15, 2018, 1:44 AM JohnWnx [e-mail] wrote:

@rbavery https://github.com/rbavery I have set dataset path to my
downloaded train images from MSCOCO dataset and weights path to
mask_rcnn_coco.h5
However, I'm still getting the error:
OSError: Unable to open file (unable to open file: name =
'/home/john/MASK_RCNN/mask_rcnn_coco.h5', errno = 2, error message = 'No
such file or directory', flags = 0, o_flags = 0)

[image: image]
https://user-images.githubusercontent.com/40804580/42730893-769cca3a-8834-11e8-9819-47c6b07d343d.png

[image: image]
https://user-images.githubusercontent.com/40804580/42730912-028dd3c2-8835-11e8-9138-e466c47f962c.png

Configurations:
BACKBONE resnet101
BACKBONE_STRIDES [4, 8, 16, 32, 64]
BATCH_SIZE 2
BBOX_STD_DEV [0.1 0.1 0.2 0.2]
COMPUTE_BACKBONE_SHAPE None
DETECTION_MAX_INSTANCES 100
DETECTION_MIN_CONFIDENCE 0.7
DETECTION_NMS_THRESHOLD 0.3
FPN_CLASSIF_FC_LAYERS_SIZE 1024
GPU_COUNT 1
GRADIENT_CLIP_NORM 5.0
IMAGES_PER_GPU 2
IMAGE_MAX_DIM 1024
IMAGE_META_SIZE 93
IMAGE_MIN_DIM 800
IMAGE_MIN_SCALE 0
IMAGE_RESIZE_MODE square
IMAGE_SHAPE [1024 1024 3]
LEARNING_MOMENTUM 0.9
LEARNING_RATE 0.001
LOSS_WEIGHTS {'mrcnn_class_loss': 1.0, 'mrcnn_mask_loss': 1.0,
'rpn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'rpn_bbox_loss': 1.0}
MASK_POOL_SIZE 14
MASK_SHAPE [28, 28]
MAX_GT_INSTANCES 100
MEAN_PIXEL [123.7 116.8 103.9]
MINI_MASK_SHAPE (56, 56)
NAME coco
NUM_CLASSES 81
POOL_SIZE 7
POST_NMS_ROIS_INFERENCE 1000
POST_NMS_ROIS_TRAINING 2000
ROI_POSITIVE_RATIO 0.33
RPN_ANCHOR_RATIOS [0.5, 1, 2]
RPN_ANCHOR_SCALES (32, 64, 128, 256, 512)
RPN_ANCHOR_STRIDE 1
RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2]
RPN_NMS_THRESHOLD 0.7
RPN_TRAIN_ANCHORS_PER_IMAGE 256
STEPS_PER_EPOCH 1000
TOP_DOWN_PYRAMID_SIZE 256
TRAIN_BN False
TRAIN_ROIS_PER_IMAGE 200
USE_MINI_MASK True
USE_RPN_ROIS True
VALIDATION_STEPS 50
WEIGHT_DECAY 0.0001

Loading weights /home/john/MASK_RCNN/mask_rcnn_coco.h5
Traceback (most recent call last):
File "samples/coco/coco.py", line 474, in
model.load_weights(model_path, by_name=True)
File "/home/john/Mask_RCNN/samples/coco/mrcnn/model.py", line 2123, in
load_weights
f = h5py.File(filepath, mode='r')
File "/home/john/.local/lib/python3.5/site-packages/h5py/_hl/files.py",
line 312, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/home/john/.local/lib/python3.5/site-packages/h5py/_hl/files.py",
line 142, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
OSError: Unable to open file (unable to open file: name =
'/home/john/MASK_RCNN/mask_rcnn_coco.h5', errno = 2, error message = 'No
such file or directory', flags = 0, o_flags = 0)

—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
https://github.com/matterport/Mask_RCNN/issues/778#issuecomment-405068988,
or mute the thread
https://github.com/notifications/unsubscribe-auth/AVOkCabjq4sYkbZ7apNrH71apiO3-Kz_ks5uGtbVgaJpZM4VQAKG
.

[ccpwcn]

I am running it on Windows and am getting almost the same error but mine is not able to look for the coco model. This is the error:
error: the following arguments are required: --weights.
Can anyone please provide the balloon.py that they successfully ran on their system. I think it is some kind of linking error.
Thanks

It does not support windows system.

[artisvirat]

Sorry for the late reply. Thanks for your insight @ccpwcn. I have already run the model successfully and yes it does support windows. The error had nothing to do with that. Thanks Anyway

[RaXephon]

@artisvirat Sorry I'm a newbie. Could you tell me what steps you followed to get it to work?

[artisvirat]

@RaXephon Hey sorry for the late reply. Where do you need help to make it work?

[akkshita]

i getting this error while running nucleus.py

/workspace/Mask_RCNN-master (1)/Mask_RCNN-master/datasets/nucleus
/workspace/Mask_RCNN-master (1)/Mask_RCNN-master
Loading weights ./mask_rcnn_nucleus.h5

---

OSError Traceback (most recent call last)
in
10 # Load weights
11 print("Loading weights ", weights_path)
---> 12 model.load_weights(weights_path, by_name=True)

/workspace/Mask_RCNN-master (1)/Mask_RCNN-master/mrcnn/model.py in load_weights(self, filepath, by_name, exclude)
2113 if h5py is None:
2114 raise ImportError('load_weights requires h5py.')
-> 2115 f = h5py.File(filepath, mode='r')
2116 if 'layer_names' not in f.attrs and 'model_weights' in f:
2117 f = f['model_weights']

/usr/local/lib/python3.5/dist-packages/h5py/_hl/files.py in __init__(self, name, mode, driver, libver, userblock_size, swmr, rdcc_nslots, rdcc_nbytes, rdcc_w0, track_order, **kwds)
392 fid = make_fid(name, mode, userblock_size,
393 fapl, fcpl=make_fcpl(track_order=track_order),
--> 394 swmr=swmr)
395
396 if swmr_support:

/usr/local/lib/python3.5/dist-packages/h5py/_hl/files.py in make_fid(name, mode, userblock_size, fapl, fcpl, swmr)
168 if swmr and swmr_support:
169 flags |= h5f.ACC_SWMR_READ
--> 170 fid = h5f.open(name, flags, fapl=fapl)
171 elif mode == 'r+':
172 fid = h5f.open(name, h5f.ACC_RDWR, fapl=fapl)

h5py/_objects.pyx in h5py._objects.with_phil.wrapper()

h5py/_objects.pyx in h5py._objects.with_phil.wrapper()

h5py/h5f.pyx in h5py.h5f.open()

OSError: Unable to open file (unable to open file: name = './mask_rcnn_nucleus.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

[Fish-Dongying]

i getting this error while running nucleus.py

/workspace/Mask_RCNN-master (1)/Mask_RCNN-master/datasets/nucleus
/workspace/Mask_RCNN-master (1)/Mask_RCNN-master
Loading weights ./mask_rcnn_nucleus.h5

OSError Traceback (most recent call last)
in
10 # Load weights
11 print("Loading weights ", weights_path)
---> 12 model.load_weights(weights_path, by_name=True)

/workspace/Mask_RCNN-master (1)/Mask_RCNN-master/mrcnn/model.py in load_weights(self, filepath, by_name, exclude)
2113 if h5py is None:
2114 raise ImportError('load_weights requires h5py.')
-> 2115 f = h5py.File(filepath, mode='r')
2116 if 'layer_names' not in f.attrs and 'model_weights' in f:
2117 f = f['model_weights']

/usr/local/lib/python3.5/dist-packages/h5py/_hl/files.py in init(self, name, mode, driver, libver, userblock_size, swmr, rdcc_nslots, rdcc_nbytes, rdcc_w0, track_order, **kwds)
392 fid = make_fid(name, mode, userblock_size,
393 fapl, fcpl=make_fcpl(track_order=track_order),
--> 394 swmr=swmr)
395
396 if swmr_support:

/usr/local/lib/python3.5/dist-packages/h5py/_hl/files.py in make_fid(name, mode, userblock_size, fapl, fcpl, swmr)
168 if swmr and swmr_support:
169 flags |= h5f.ACC_SWMR_READ
--> 170 fid = h5f.open(name, flags, fapl=fapl)
171 elif mode == 'r+':
172 fid = h5f.open(name, h5f.ACC_RDWR, fapl=fapl)

h5py/_objects.pyx in h5py._objects.with_phil.wrapper()

h5py/_objects.pyx in h5py._objects.with_phil.wrapper()

h5py/h5f.pyx in h5py.h5f.open()

OSError: Unable to open file (unable to open file: name = './mask_rcnn_nucleus.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

Hi, I'm able to run a training session, can anyone advise?

Thanks.

(MASKR) john@john-H270N-WIFI:~/Mask_RCNN$ sudo python3 samples/coco/coco.py train --dataset=/path/to/coco/ --model=coco
Using TensorFlow backend.
Command: train
Model: coco
Dataset: /path/to/coco/
Year: 2014
Logs: /home/logs
Auto Download: False

Configurations:
BACKBONE resnet101
BACKBONE_STRIDES [4, 8, 16, 32, 64]
BATCH_SIZE 2
BBOX_STD_DEV [0.1 0.1 0.2 0.2]
COMPUTE_BACKBONE_SHAPE None
DETECTION_MAX_INSTANCES 100
DETECTION_MIN_CONFIDENCE 0.7
DETECTION_NMS_THRESHOLD 0.3
FPN_CLASSIF_FC_LAYERS_SIZE 1024
GPU_COUNT 1
GRADIENT_CLIP_NORM 5.0
IMAGES_PER_GPU 2
IMAGE_MAX_DIM 1024
IMAGE_META_SIZE 93
IMAGE_MIN_DIM 800
IMAGE_MIN_SCALE 0
IMAGE_RESIZE_MODE square
IMAGE_SHAPE [1024 1024 3]
LEARNING_MOMENTUM 0.9
LEARNING_RATE 0.001
LOSS_WEIGHTS {'mrcnn_mask_loss': 1.0, 'rpn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'rpn_bbox_loss': 1.0}
MASK_POOL_SIZE 14
MASK_SHAPE [28, 28]
MAX_GT_INSTANCES 100
MEAN_PIXEL [123.7 116.8 103.9]
MINI_MASK_SHAPE (56, 56)
NAME coco
NUM_CLASSES 81
POOL_SIZE 7
POST_NMS_ROIS_INFERENCE 1000
POST_NMS_ROIS_TRAINING 2000
ROI_POSITIVE_RATIO 0.33
RPN_ANCHOR_RATIOS [0.5, 1, 2]
RPN_ANCHOR_SCALES (32, 64, 128, 256, 512)
RPN_ANCHOR_STRIDE 1
RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2]
RPN_NMS_THRESHOLD 0.7
RPN_TRAIN_ANCHORS_PER_IMAGE 256
STEPS_PER_EPOCH 1000
TOP_DOWN_PYRAMID_SIZE 256
TRAIN_BN False
TRAIN_ROIS_PER_IMAGE 200
USE_MINI_MASK True
USE_RPN_ROIS True
VALIDATION_STEPS 50
WEIGHT_DECAY 0.0001

Loading weights /home/mask_rcnn_coco.h5
Traceback (most recent call last):
File "samples/coco/coco.py", line 474, in
model.load_weights(model_path, by_name=True)
File "/home/john/Mask_RCNN/samples/coco/mrcnn/model.py", line 2123, in load_weights
f = h5py.File(filepath, mode='r')
File "/home/john/.local/lib/python3.5/site-packages/h5py/_hl/files.py", line 312, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/home/john/.local/lib/python3.5/site-packages/h5py/_hl/files.py", line 142, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
OSError: Unable to open file (unable to open file: name = '/home/mask_rcnn_coco.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

I meet the same probolem. Could you please tell what you do to solve this problem？Thank you very much!

[Akash481]

I faced the same issue. Instead of just putting the file name, I replaced it with the full directory address. Worked for me.