search

datitran / raccoon_dataset

The dataset is used to train my own raccoon detector and I blogged about it on Medium
https://medium.com/towards-data-science/how-to-train-your-own-object-detector-with-tensorflows-object-detector-api-bec72ecfe1d9
MIT License
1.27k stars 977 forks source link

Error in tf.python_io.TFRecordWriter #84

Open rahulramesh3321 opened 5 years ago

rahulramesh3321 commented 5 years ago

Hi All,

While running the code writer = tf.python_io.TFRecordWriter(FLAGS.output_path) below are the errors occured :

writer = tf.python_io.TFRecordWriter(FLAGS.output_path) Traceback (most recent call last):

File "", line 1, in writer = tf.python_io.TFRecordWriter(FLAGS.output_path)

File "D:\anaconda\lib\site-packages\tensorflow\python\lib\io\tf_record.py", line 210, in init compat.as_bytes(path), options._as_record_writer_options(), status)

File "D:\anaconda\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 528, in exit c_api.TF_GetCode(self.status.status))

NotFoundError: Failed to create a NewWriteableFile: : The system cannot find the path specified. ; No such process

I believe this is respective to the location of my files. Below are the details of location of my files: 'C:/Users/1010141/Desktop/Object-Detection/Data/Train.csv' CSV file is 'C:/Users/1010141/Desktop/Object-Detection/Image/Train Images and excel file is kept C:\Users\1010141\Desktop\Object-Detection\ My scripts is kept C:\Users\1010141\Desktop\model\models-master\research Object_detection directory is kept D:\anaconda\pkgs\tensorflow-gpu-1.10.0-py36_0\Lib\site-packages\tensorflow * Tensorflow is kept.

Please help me .

pc2005 commented 5 years ago

Please check my solution in issue #41 and see if it helps.

patelalay231 commented 3 years ago

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