Skip to main content

Image classification with pretrained models in Pytorch

Project description

# Image classification with pretrained models in Pytorch

Use pretrained models to train your data.

## Installation

`sh pip install image-classification-pytorch `

## ✨ Quick start

`sh import image_classification_pytorch as icp ` `sh # Images of each class in its own folder with the class name. # Examples of folders: homer_simpson, bart_simpson etc. from google.colab import drive drive.mount('/content/gdrive') !unzip -q /content/gdrive/My\ Drive/datasets/image_classification_pytorch/data_simpsons.zip -d train ` `sh # add model tf_efficientnet_b4_ns = {'model_type': 'tf_efficientnet_b4_ns', 'im_size': 380, 'im_size_test': 380, 'batch_size': 8, 'mean': [0.485, 0.456, 0.406], 'std': [0.229, 0.224, 0.225]} models = [tf_efficientnet_b4_ns] ` `sh # create trainer trainer = ICPTrainer(models=models, data_dir='data_simpsons') # start training trainer.fit_test() `

## Colab Quick start [image_classification_pytorch_get_started.ipynb](https://colab.research.google.com/drive/1M7oJDizCOrFTDJz0CaDy-ClvDMUvmlnv?usp=sharing)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

image_classification_pytorch-0.0.10.tar.gz (6.0 kB view details)

Uploaded Source

File details

Details for the file image_classification_pytorch-0.0.10.tar.gz.

File metadata

  • Download URL: image_classification_pytorch-0.0.10.tar.gz
  • Upload date:
  • Size: 6.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.8.5

File hashes

Hashes for image_classification_pytorch-0.0.10.tar.gz
Algorithm Hash digest
SHA256 73696029a2ce571802d98266b838a342c1ed4d3ef4bfd2d806fbb8792b2b52f3
MD5 df98e71cbc48584e0ba2bacecf293e00
BLAKE2b-256 d0c3b3658457a52decf909e86359b8e1e63833f663780d412f519cb4d8d6090f

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page