# torchvision-tinyimagenet
Dataset class for PyTorch and the TinyImageNet dataset.
# Installation
``` pip install tinyimagenet ```
# How to use
````
from tinyimagenet import TinyImageNet
from pathlib import Path
import logging
logging.basicConfig(level=logging.INFO)
split ="val"
dataset = TinyImageNet(Path("~/.torchvision/tinyimagenet/"),split=split)
n = len(dataset)
print(f"TinyImageNet, split {split}, has {n} samples.")
n_samples = 5
print(f"Showing info of {n_samples} samples...")
for i in range(0,n,n//n_samples):
image,klass = dataset[i]
print(f"Sample of class {klass:3d}, image {image}, words {dataset.idx_to_words[klass]}")
````
You can also check the [quickstart notebook](https://colab.research.google.com/drive/1FCDsDJg86mCjyeAWOxDW9iF49goWCx4j?usp=sharing) to peruse the dataset.
Finally, we also provide some example notebooks that use TinyImageNet with PyTorch models:
* [Evaluate a pretrained EfficientNet model](https://colab.research.google.com/github/facundoq/tinyimagenet/blob/main/Eval%20EfficientNet%20with%20TinyImageNet.ipynb#scrollTo=41aVk-yvEV-o)
* [Train a simple CNN on the dataset](
https://colab.research.google.com/github/facundoq/tinyimagenet/blob/main/Train%20basic%20CNN%20with%20TinyImageNet.ipynb#scrollTo=4CiA6z8reXYP)
* [Finetune an EfficientNet model pretrained on the full ImageNet to classify only the 200 classes of TinyImageNet](https://colab.research.google.com/github/facundoq/tinyimagenet/blob/main/Finetune%20EfficientNet%20with%20TinyImageNet.ipynb)
Raw data
{
"_id": null,
"home_page": "https://github.com/facundoq/tinyimagenet",
"name": "tinyimagenet",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "TinyImageNet ImageNet Dataset PyTorch torch torchvision",
"author": "Facundo Manuel Quiroga",
"author_email": "facundoq@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/1e/79/a9284fd961664d6c23a4f85ca6ee7db82273f37d61cd7317bab83e4b223f/tinyimagenet-0.9.9.tar.gz",
"platform": null,
"description": "# torchvision-tinyimagenet\nDataset class for PyTorch and the TinyImageNet dataset.\n\n# Installation\n\n``` pip install tinyimagenet ```\n\n# How to use\n````\nfrom tinyimagenet import TinyImageNet\nfrom pathlib import Path\nimport logging\n\nlogging.basicConfig(level=logging.INFO)\n\nsplit =\"val\"\ndataset = TinyImageNet(Path(\"~/.torchvision/tinyimagenet/\"),split=split)\nn = len(dataset)\nprint(f\"TinyImageNet, split {split}, has {n} samples.\")\nn_samples = 5\nprint(f\"Showing info of {n_samples} samples...\")\nfor i in range(0,n,n//n_samples):\n image,klass = dataset[i]\n print(f\"Sample of class {klass:3d}, image {image}, words {dataset.idx_to_words[klass]}\")\n````\n\nYou can also check the [quickstart notebook](https://colab.research.google.com/drive/1FCDsDJg86mCjyeAWOxDW9iF49goWCx4j?usp=sharing) to peruse the dataset.\n\nFinally, we also provide some example notebooks that use TinyImageNet with PyTorch models:\n\n* [Evaluate a pretrained EfficientNet model](https://colab.research.google.com/github/facundoq/tinyimagenet/blob/main/Eval%20EfficientNet%20with%20TinyImageNet.ipynb#scrollTo=41aVk-yvEV-o)\n* [Train a simple CNN on the dataset](\nhttps://colab.research.google.com/github/facundoq/tinyimagenet/blob/main/Train%20basic%20CNN%20with%20TinyImageNet.ipynb#scrollTo=4CiA6z8reXYP)\n* [Finetune an EfficientNet model pretrained on the full ImageNet to classify only the 200 classes of TinyImageNet](https://colab.research.google.com/github/facundoq/tinyimagenet/blob/main/Finetune%20EfficientNet%20with%20TinyImageNet.ipynb)\n\n\n",
"bugtrack_url": null,
"license": "",
"summary": "Dataset class for PyTorch and the TinyImageNet dataset, with automated download and extraction.",
"version": "0.9.9",
"project_urls": {
"Bug Tracker": "https://github.com/facundoq/tinyimagenet/issues",
"Documentation": "https://github.com/facundoq/tinyimagenet",
"Homepage": "https://github.com/facundoq/tinyimagenet",
"Source Code": "https://github.com/facundoq/tinyimagenet"
},
"split_keywords": [
"tinyimagenet",
"imagenet",
"dataset",
"pytorch",
"torch",
"torchvision"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "5d0791f5937864082de49f5c32d2d79983829d38a1b911f5e0dc719e8cf16eb1",
"md5": "d478384db7781856589d74fdf29825e0",
"sha256": "941c7d3b19cb2f3fa719799530745a3cc0e7095a1990f2f5be107d355ec359df"
},
"downloads": -1,
"filename": "tinyimagenet-0.9.9-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "d478384db7781856589d74fdf29825e0",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": ">=3.6",
"size": 9162,
"upload_time": "2023-12-26T23:06:03",
"upload_time_iso_8601": "2023-12-26T23:06:03.042122Z",
"url": "https://files.pythonhosted.org/packages/5d/07/91f5937864082de49f5c32d2d79983829d38a1b911f5e0dc719e8cf16eb1/tinyimagenet-0.9.9-py2.py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "1e79a9284fd961664d6c23a4f85ca6ee7db82273f37d61cd7317bab83e4b223f",
"md5": "90dd492af4bcc614cca0da96ead70b83",
"sha256": "bcbd21749abc63138fedf213501fd509c3e8495f2e78b8af5492338f876cc07a"
},
"downloads": -1,
"filename": "tinyimagenet-0.9.9.tar.gz",
"has_sig": false,
"md5_digest": "90dd492af4bcc614cca0da96ead70b83",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 11323,
"upload_time": "2023-12-26T23:06:04",
"upload_time_iso_8601": "2023-12-26T23:06:04.639950Z",
"url": "https://files.pythonhosted.org/packages/1e/79/a9284fd961664d6c23a4f85ca6ee7db82273f37d61cd7317bab83e4b223f/tinyimagenet-0.9.9.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-12-26 23:06:04",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "facundoq",
"github_project": "tinyimagenet",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "tinyimagenet"
}
JSON
