This library can be used for any simple image classification problems, You only have to give the data path, #of epochs, and if you have any model that you created you can give that also (if none given the model if use it's own model).
- After importing the library create a object of it by providing the path of the data and other parameters.
- Then call the create_model function with the object.
- Then the library will starts to work starting with cleaning the data by checking for any unsupported or duplicated files and deleting them.
- After cleanig it will preprocessing the images and splits it to train/test/validation, and it also plots the images according to the classes
- The if no model is provided it will create it's own model for traning.
- And Starts to train for the #of epochs given (default=70).
- You can use the funtion plot_performance() to plot the model loss and accuracy growth.
- model_evaluation() function evaluate the model based on the test data.
- And you can use the function predict() to predict any new values.
- And to save the model use model_save() function
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
imoc-0.0.1.tar.gz
(4.9 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
imoc-0.0.1-py3-none-any.whl
(5.2 kB
view details)
File details
Details for the file imoc-0.0.1.tar.gz.
File metadata
- Download URL: imoc-0.0.1.tar.gz
- Upload date:
- Size: 4.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/4.0.2 CPython/3.10.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
37854cd8e371f08ec168f077837f4cabedba7e494a4aaedf340846e78ba486b6
|
|
| MD5 |
fb2cec66bcd80f2432f3d414e2a2f997
|
|
| BLAKE2b-256 |
55b09fe641d12bfc7bfb72dead07a6fb13fa247a3a6cc32a2905382afd2faaf2
|
File details
Details for the file imoc-0.0.1-py3-none-any.whl.
File metadata
- Download URL: imoc-0.0.1-py3-none-any.whl
- Upload date:
- Size: 5.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/4.0.2 CPython/3.10.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
673d3de717aa572f6b5636913b8c6247f629b158ea12bf8736d7a68d407694c8
|
|
| MD5 |
3d55d533b11c04d2fb07c36796ad6435
|
|
| BLAKE2b-256 |
0dfdeb066f4cb408034cd6378adb15a5e002c2a6acc8328905638da3ebd37f0b
|