philferriere
commented
6 years ago @priyanka-chaudhary, weren't the 2014 versions of instances_valminusminival2014.json and instances_minival2014.json build by Ross Girshick and his team? That's the feeling I get from reading this README.md. I don't believe there's ever been an official release of these files.
May I suggest that you build your own versions for the 2017 dataset? If you go by the official COCO page, there is no additional image data but only new stuff annotations and new data splits:
2017 Update: The main change in 2017 is that instead of an 80K/40K train/val split, based on community feedback the split is now 115K/5K for train/val. The same exact images are used, and no new annotations for detection/keypoints are provided. However, new in 2017 are stuff annotations on 40K train images (subset of the full 115K train images from 2017) and 5K val images. Also, for testing, in 2017 the test set only has two splits (dev / challenge), instead of the four splits (dev / standard / reserve / challenge) used in previous years. Finally, new in 2017 we are releasing 120K unlabeled images from COCO that follow the same class distribution as the labeled images; this may be useful for semi-supervised learning on COCO.
Note: Annotations last updated 09/05/2017 (stuff annotations added). If you find any issues with the data please let us know!
Does this mean that instances_valminusminival2014.json and instances_minival2014.json files can be used with the 2017 dataset?
priyanka-chaudhary
LifeBeyondExpectations
aemilcar
CMCDragonkai
isalirezag
ayush1427
eshwarkamal
Hi,
I am trying to train for coco dataset. The command I am using is: python3 coco.py train --dataset=/home/mask-rcnn/Mask_RCNN-master/dataset-coco --model=coco --download=false --year=2017
The dataset is already downloaded before. I am getting "FileNotFoundError: [Errno 2] No such file or directory: '/home/mask-rcnn/Mask_RCNN-master/dataset-coco/annotations/instances_valminusminival2017.json' "
Can anyone please help? TIA. Please see the logs below.
Using TensorFlow backend. Command: train Model: coco Dataset: /home/mask-rcnn/Mask_RCNN-master/dataset-coco Year: 2017 Logs: /home/mask-rcnn/Mask_RCNN-master/logs Auto Download: True
Configurations: BACKBONE_SHAPES [[256 256] [128 128] [ 64 64] [ 32 32] [ 16 16]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 2 BBOX_STD_DEV [0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.7 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 2 IMAGE_MAX_DIM 1024 IMAGE_MIN_DIM 800 IMAGE_PADDING True IMAGE_SHAPE [1024 1024 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 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 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/Mask_RCNN-master/mask_rcnn_coco.h5 2018-01-11 17:09:33.070611: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA 2018-01-11 17:09:33.262017: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties: name: GeForce GTX TITAN X major: 5 minor: 2 memoryClockRate(GHz): 1.076 pciBusID: 0000:01:00.0 totalMemory: 11.91GiB freeMemory: 11.47GiB 2018-01-11 17:09:33.262044: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX TITAN X, pci bus id: 0000:01:00.0, compute capability: 5.2) Will use images in /home/mask-rcnn/Mask_RCNN-master/dataset-coco/train2017 Will use annotations in /home/mask-rcnn/Mask_RCNN-master/dataset-coco/annotations/instances_train2017.json loading annotations into memory... Done (t=12.45s) creating index... index created! Will use images in /home/mask-rcnn/Mask_RCNN-master/dataset-coco/val2017 Will use annotations in /home/mask-rcnn/Mask_RCNN-master/dataset-coco/annotations/instances_valminusminival2014.json loading annotations into memory... Traceback (most recent call last): File "coco.py", line 477, in
dataset_train.load_coco(args.dataset, "valminusminival", year=args.year, auto_download=args.download)
File "coco.py", line 108, in loadcoco
coco = COCO("{}/annotations/instances{}{}.json".format(dataset_dir, subset, year))
File "/usr/local/lib/python3.5/dist-packages/pycocotools/coco.py", line 79, in init
dataset = json.load(open(annotation_file, 'r'))
FileNotFoundError: [Errno 2] No such file or directory: '/home/mask-rcnn/Mask_RCNN-master/dataset-coco/annotations/instances_valminusminival2017.json'