OSError: [Errno 107] Transport endpoint is not connected #1
-
|
I am referring your code for model training but getting below error, i have tried unmounting and again mounting google drive plus disconnecting and again connecting runtime but still having same error. Can you help us? ERROR:root:Internal Python error in the inspect module. ERROR:root:Internal Python error in the inspect module. Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): |
Beta Was this translation helpful? Give feedback.
Replies: 2 comments 6 replies
-
|
It looks like your folder structure on your google drive is wrong. The path to the images and training.csv and train.py should be /content/drive/MyDrive/TrainData. See https://github.com/robodhhb/Smart-Modelrailway-Cam/tree/main/20_Example_Training/20_Data for explanations. And always execute the jupyter notebook for training with this link: |
Beta Was this translation helpful? Give feedback.
-
|
Thank you for your valuable solution, it works for us but, when we use that tflite in our android application that time results are not getting and also bounding boxes and labels are not displaying on image in android application. Can you explain csv files contents in detail and Please help us for the same. Thank You! |
Beta Was this translation helpful? Give feedback.
-
|
I am sorry that I cannot help you because I use the model on a Raspberry Pi, not in an android app. But the following tutorial may help you: https://developers.google.com/codelabs/tflite-object-detection-android?hl=de#0 |
Beta Was this translation helpful? Give feedback.
-
|
No problem. Thank you so much for your valuable assistance. Your efforts have made a significant difference for us, and we are truly thankful for your kindness. |
Beta Was this translation helpful? Give feedback.
-
|
Hi, right now for model training, we are using 2000 images, we kept epoch 100 and batch size 8. But same above mention error is throwing. So is it because of epoches and batch size which we have changed??? Can you suggest us a solution for this?? or should we have to use limited images if yes then how much?? Export model to tflite-format Estimated count of arithmetic ops: 1.774 G ops, equivalently 0.887 G MACs Estimated count of arithmetic ops: 1.774 G ops, equivalently 0.887 G MACs ERROR:root:Internal Python error in the inspect module. ERROR:root:Internal Python error in the inspect module. Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): During handling of the above exception, another exception occurred: Traceback (most recent call last): |
Beta Was this translation helpful? Give feedback.
-
|
First I would check if you connect your google drive with the following statement: from google.colab import drive Then check if a reduced number of images and epochs (30-50) change something. If not you should create an issue here: |
Beta Was this translation helpful? Give feedback.
-
|
Thank You. We will check and update you. |
Beta Was this translation helpful? Give feedback.
-
|
Can you tell us how many maximum images we can use and how much epochs for same? Because we used 4000 images and 100 epochs for Model Training .Please suggest images count and epochs. Thank You!! |
Beta Was this translation helpful? Give feedback.
It looks like your folder structure on your google drive is wrong. The path to the images and training.csv and train.py should be /content/drive/MyDrive/TrainData. See https://github.com/robodhhb/Smart-Modelrailway-Cam/tree/main/20_Example_Training/20_Data for explanations. And always execute the jupyter notebook for training with this link:
Open Colab notebook trainSMRC.ipynb
Hope this helps
Detlef