Object-Detection icon indicating copy to clipboard operation
Object-Detection copied to clipboard

retrining

Open PrakharPrashantSingh opened this issue 2 years ago • 0 comments

At the time of retraining i am facing writing permisiion error, i even restrated my anaconda prompt into admin mode. Please have a look and suggest me a way out:

(pixel) C:\PixelLib>python pixellibCustom01.py 2022-04-13 01:39:24.790589: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudart64_101.dll'; dlerror: cudart64_101.dll not found 2022-04-13 01:39:24.790767: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. There are 285 listed files in folder train. Converting labelme annotations to COCO format: 100%|█████████████████████████████████| 285/285 [00:02<00:00, 98.62it/s] 04/13/2022 01:39:30 - INFO - labelme2coco - Converted annotations in COCO format is exported to C:\PixelLib\customModel\train.json\dataset.json Traceback (most recent call last): File "pixellibCustom01.py", line 14, in vis_img.load_dataset("customModel") File "C:\PixelLib\pixellib\custom_train_init_.py", line 68, in load_dataset self.dataset_train.load_data(save_json_path1, labelme_folder1) File "C:\PixelLib\pixellib\custom_train_init_.py", line 175, in load_data json_file = open(annotation_json) PermissionError: [Errno 13] Permission denied: 'C:\PixelLib\customModel\train.json'

thanks

PrakharPrashantSingh avatar Apr 12 '22 20:04 PrakharPrashantSingh