No such file or directory while running generate_tfrecord.py

[adityaksai]

Hello, I have followed the tensorflow object detection API installation by following the below demo

https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10.

I am getting this problem while running the line---

python generate_tfrecord.py --csv_input=images\train_labels.csv --image_dir=images\train --output_path=train.record

Error:

(tf_gpu) C:\Tensorflow1\models\research\object_detection>python generate_tfrecord.py --csv_input=images\train_labels.csv --image_dir=images\train --output_path=train.record WARNING: Logging before flag parsing goes to stderr. W0927 00:55:20.335181 15036 deprecation_wrapper.py:119] From generate_tfrecord.py:121: The name tf.app.run is deprecated. Please use tf.compat.v1.app.run instead.

W0927 00:55:20.341163 15036 deprecation_wrapper.py:119] From generate_tfrecord.py:107: The name tf.python_io.TFRecordWriter is deprecated. Please use tf.io.TFRecordWriter instead.

W0927 00:55:20.512737 15036 deprecation_wrapper.py:119] From generate_tfrecord.py:66: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.

Traceback (most recent call last): File "generate_tfrecord.py", line 121, in tf.app.run() File "C:\Users\Aditya\Anaconda3\envs\tf_gpu\lib\site-packages\tensorflow\python\platform\app.py", line 40, in run _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef) File "C:\Users\Aditya\Anaconda3\envs\tf_gpu\lib\site-packages\absl\app.py", line 300, in run _run_main(main, args) File "C:\Users\Aditya\Anaconda3\envs\tf_gpu\lib\site-packages\absl\app.py", line 251, in _run_main sys.exit(main(argv)) File "generate_tfrecord.py", line 112, in main tf_example = create_tf_example(group, path) File "generate_tfrecord.py", line 67, in create_tf_example encoded_jpg = fid.read() File "C:\Users\Aditya\Anaconda3\envs\tf_gpu\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 122, in read self._preread_check() File "C:\Users\Aditya\Anaconda3\envs\tf_gpu\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 84, in _preread_check compat.as_bytes(self.__name), 1024 * 512) tensorflow.python.framework.errors_impl.NotFoundError: NewRandomAccessFile failed to Create/Open: C:\Tensorflow1\models\research\object_detection\images\train\img000000.jpg : The system cannot find the file specified. ; No such file or directory

Solution 1: I have changed the xml to csv file by adding the .jpg extension.

I want to use it for my own dataset.

I am able to run the model for single class like models/research/object_detection/images/train/class1 models/research/object_detection/images/test/class1

I want to extend it to my multi class dataset. Folder structure: models/research/object_detection/images/train/class1 models/research/object_detection/images/train/class2 models/research/object_detection/images/train/class3

models/research/object_detection/images/test/class1 models/research/object_detection/images/test/class2 models/research/object_detection/images/test/class3

train_labels.csv file contains

filename,width,height,class,xmin,ymin,xmax,ymax img000000.jpg,640,480,auto,21,114,77,193 img000001.jpg,640,480,auto,332,10,504,229 img000000.jpg,640,480,bus,322,356,334,371 img000001.jpg,640,480,bus,341,357,351,370 img000002.jpg,5500,3667,car,2516,1933,2819,2422

Any help is much appreciated. Thank you in advance .