Repository: paraschopra/one-network-many-uses
Branch: master
Commit: ba4aee2a7797
Files: 4
Total size: 167.1 MB
Directory structure:
gitextract_eqq7ydyo/
├── README.md
├── four-in-one-network.ipynb
└── models/
├── epochs_40_loss_2_841_v6.pth
└── inception_epochs_40.pth
================================================
FILE CONTENTS
================================================
================================================
FILE: README.md
================================================
# One neural network, many uses
Jupyter notebook corresponding to tutorial: [One neural network network, many uses: image captioning, image search, similar images and similar words using one model ](https://towardsdatascience.com/one-neural-network-many-uses-build-image-search-image-captioning-similar-words-and-similar-1e22080ce73d)
Requires following packages:
- PyTorch
- Numpy
- Matplotlib
## Dataset NOT included (please download separately)
To follow along, you'll need to download the Flickr8K dataset. Fill [this form](https://forms.illinois.edu/sec/1713398) and you'll receive a download link on your email. (There's also a [direct link to download the 1GB Flickr8K dataset](https://github.com/jbrownlee/Datasets/releases/download/Flickr8k/Flickr8k_Dataset.zip), though not sure how long it'll stay like that). Extract the zip file in the 'Flicker8k_Dataset' folder in the same directory as your notebook. You'll also need to download captions [from here](http://cs.stanford.edu/people/karpathy/deepimagesent/caption_datasets.zip). Extract captions in the folder 'caption_datasets'.
## Example performance
Image caption example:
Similar words example
Similar images example
Image search example
Made by [@paraschopra](https://twitter.com/paraschopra)
MIT License.
================================================
FILE: four-in-one-network.ipynb
================================================
[File too large to display: 42.9 MB]
================================================
FILE: models/epochs_40_loss_2_841_v6.pth
================================================
[File too large to display: 25.8 MB]
================================================
FILE: models/inception_epochs_40.pth
================================================
[File too large to display: 98.4 MB]
gitextract_eqq7ydyo/
├── README.md
├── four-in-one-network.ipynb
└── models/
├── epochs_40_loss_2_841_v6.pth
└── inception_epochs_40.pth
Condensed preview — 4 files, each showing path, character count, and a content snippet. Download the .json file or copy for the full structured content (2K chars).
[
{
"path": "README.md",
"chars": 1709,
"preview": "# One neural network, many uses\n\nJupyter notebook corresponding to tutorial: [One neural network network, many uses: ima"
}
]
// ... and 3 more files (download for full content)
About this extraction
This page contains the full source code of the paraschopra/one-network-many-uses GitHub repository, extracted and formatted as plain text for AI agents and large language models (LLMs). The extraction includes 4 files (167.1 MB), approximately 686 tokens. Use this with OpenClaw, Claude, ChatGPT, Cursor, Windsurf, or any other AI tool that accepts text input. You can copy the full output to your clipboard or download it as a .txt file.
Extracted by GitExtract — free GitHub repo to text converter for AI. Built by Nikandr Surkov.