AlicIA
Usage: alicia [OPTIONS] COMMAND [ARGS]... A CLI to download, create, modify, train, test, predict and compare an image classifiers. Supporting mostly all torch-vision neural networks and datasets. This will also identify cute 🐱 or a fierce 🐶, also flowers or what type of 🏘️ you should be. Options: -v, --verbose -g, --gpu --version Show the version and exit. --help Show this message and exit. Commands: compare Compare the info, accuracy, and step speed two (or more by... create Creates a new model for a given architecture. download Download a MNIST dataset with PyTorch and split it into... info Display information about a model architecture. modify Changes the hyper parameters of a model. predict Predict images using a pre trained model, for a given folder... test Test a pre trained model. train Train a given architecture with a data directory containing a...
View a FashionMNIST demo
Install and usage
pip install alicia alicia --help
If you just want to see a quick showcase of the tool, download and run showcase.sh https://github.com/aemonge/alicia/raw/main/docs/showcase.sh
Features
To see the full list of features, and option please refer to alicia –help
- Download common torchvision datasets (tested with the following):
MNIST
FashionMNIST
Flowers102
EMNIST
StanfordCars
KMNIST and CIFAR10
Select different transforms to train.
- Train, test and predict using different custom-made and torch-vision models:
SqueezeNet
AlexNet
MNASNet
Get information about each model.
Compare models training speed, accuracy, and meta information.
View test prediction results in the console, or with matplotlib.
Adds the network training history log, to the model. To enhance the info and compare.
Supports pre-trained models, with weights settings.
Automatically set the input size based on the image resolution.
References
Useful links found and used while developing this
1 maintainer
Metadata
1 maintainer
Release files for alicia 0.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| alicia-0.3.0.tar.gz | 30.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| alicia-0.3.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 77.0 kB
Release files / alicia-0.3.0.tar.gz
| Download URL | alicia-0.3.0.tar.gz |
|---|---|
| Size | 30.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c2af413b124d047e1beb09c012a09fd1ce3758932e99a3e946a501267cd48a92
|
|
BLAKE2b-256 checksum How to use checksums |
295fd8d58871ad5af7cb473fc2569e89573f50f400991bc898630200dd17314c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.4.0 CPython/3.10.8 Linux/5.13.0-valve36-1-neptune
|
Release files / alicia-0.3.0-py3-none-any.whl
| Download URL | alicia-0.3.0-py3-none-any.whl |
|---|---|
| Size | 46.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
104249008fcdc47003f56c13479817526a0b86e641a36e078ac7f71cbc9a1bc2
|
|
BLAKE2b-256 checksum How to use checksums |
d0cc13485720fa69cd976cc36945f7c4ea8f8eaecb8dfb4b43bd79ed0c3b6797
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.4.0 CPython/3.10.8 Linux/5.13.0-valve36-1-neptune
|
