FastMaskRCNN
FastMaskRCNN copied to clipboard
CharlesShang
Mask RCNN in TensorFlow
In previous issues, I have seen models trained using 190K epochs ( https://drive.google.com/file/d/0BwVrmnQ5PwycT0p1Y0tLQV9UYUk/view?usp=sharing ) and 2500K epochs ( https://drive.google.com/open?id=0B0J4gcV0gfL4U1NadkllSndKbFk ) there is a model trained using 5000K epochs ( https://www.dropbox.com/s/k0vuldvzsxc18xu/coco_resnet50_model.ckpt-499999.zip?dl=0...
when I run :python download_and_convert_data.py `>> Converting image 23751/82783 shard 11 >> Converting image 23801/82783 shard 11 >> Converting image 23851/82783 shard 11 None Annotations data/coco/train2014/COCO_train2014_000000167118.jpg Traceback (most recent call...
`$ python setup.py build_ext --inplace Compiling _mask.pyx because it changed. [1/1] Cythonizing _mask.pyx running build_ext building '_mask' extension creating build creating build\temp.win-amd64-3.8 creating build\temp.win-amd64-3.8\Release creating build\temp.win-amd64-3.8\Release\common C:\Program Files (x86)\Microsoft Visual...
I add cython to the requirements to run "python setup.py build_ext --inplace"
Traceback (most recent call last): File "main.py", line 103, in tf.app.run() File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\platform\app.py", line 48, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "main.py", line 81, in main data_dir=FLAGS.data_dir) File "D:\DCGAN-tensorflow-master\model.py", line...
lanka@ubuntu:~/work/FastMaskRCNN$ python download_and_convert_data.py loading annotations into memory... Done (t=5.22s) creating index... index created! Traceback (most recent call last): File "download_and_convert_data.py", line 39, in tf.app.run() File "/home/lanka/.local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run...
Can anyone please help on how to proceed for implementing this architecture using the MobileNet architecture. We are having some issues in implementing SeparableConv2D layer in this model. We wanted...
There some errors when I run the download_and_convert_data.py. .................. File "libs/datasets/pycocotools/coco.py", line 79, in __init__ dataset = json.load(open(annotation_file, 'r')) IOError: [Errno 2] No such file or directory: 'data/coco/annotations/instances_train2014.json' I am...
i found a bug in "_add_to_tfrecord function of download_and_convert_data.py". it would be raise "float division by zero" if the train image numer less than num_shards ( default is 2500).
