This is a project based on training a model using the dataset of images of digits from 0-9. The model is trained using CNN and the model accuracy is around 97.5%. The training data contains 4000 images for each digits. The prediction can be done directly using the tensor (image). This is a basic model based on a new approach for prediction and training from the images rather than using MNIST Dataset. All the details of the project is given below: https://drive.google.com/file/d/13oqVv5KX4eOB7XWrwOJ3KLA1UtALlyMF/view?usp=sharing
-
Notifications
You must be signed in to change notification settings - Fork 0
This is a project based on training a model using the dataset of images of digits from 0-9. The model is trained using CNN and the model accuracy is around 97.5%. The training data contains 4000 images for each digits. The prediction can be done directly using the tensor (image). This is a basic model based on a new approach for prediction and t…
namanjh/HandwrittenDigitTensor
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
This is a project based on training a model using the dataset of images of digits from 0-9. The model is trained using CNN and the model accuracy is around 97.5%. The training data contains 4000 images for each digits. The prediction can be done directly using the tensor (image). This is a basic model based on a new approach for prediction and t…
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published