Explore the Keras-Seedlings dataset, featuring segmented images of weed and crop seedlings for machine learning classification.

Counts Keras

## Overview

Counts Keras is a dataset for object detection tasks - it contains Counts Keras annotations for 457 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [MIT license](https://creativecommons.org/licenses/MIT).

Valorant Keras

## Overview

Valorant Keras is a dataset for object detection tasks - it contains Enemy annotations for 2,662 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

manuel-yao/pokemon-keras-community dataset hosted on Hugging Face and contributed by the HF Datasets community

Access the EfficientNet Keras Dataset for offline use, featuring applications, full weights, and source code. Perfect for deep learning competitions and AI projects without internet access.

Keras scripts for creating a simplified denoising diffusion model as well as a trained model ready for reuse. Diffusion models are obviously very popular when it comes to generative AI and since I wanted to try out some ideas and wanted to know exactly what was going on I decided to create a few script for experimentation. I thought it might be helpful to some (including myself) if I shared the files, so here they are. Feel free to use them in any way you want! 😀

The files are:

diffusion_model_small_output.keras - The model trained on a car dataset

**train_autobot.py **- Script for training the model on a dataset. In my tests I needed at least to train on 1 million batches (a batch consisting of 10 versions with various noise intensities of the same input image) in order to get decent results.

test_autobot.py - Script for testing the keras model. Be aware it takes some time to load the large model!

model_output_test.jpg - A test output (the result from a run of the test script)

I have experimented with various model architectures but obviously not exhausted all possibilities. The model architecture is probably overly large for simple datasets and can probably be slimmed down. There appear to be some mode collapse appearing so further experimentation with model architectures, input augmentation and especially loss functions will probably be beneficial.

Looking forward to seeing your feedback! 😀

Context

So I was trying to use a VGG19 pretrained model with Keras but the Docker instance couldn't download the model file. There's an open ticket for this issue here: https://github.com/Kaggle/docker-python/issues/73

Content

Just starting off with VGG16 and VGG19 for now. If this works, I'll upload some more. The weights for the full vgg16 and vgg19 files were too large to upload as a single files. I tried uploading them in parts but there wasn't enough room to extract them in the working directory.

Here's an example on how to use the model files:

keras_models_dir = "../input/keras-models"

model = applications.VGG16(include_top=False, weights=None) model.load_weights('%s/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5' % keras_models_dir)

Here's some more examples on how to use it: https://www.kaggle.com/ekkus93/keras-models-as-datasets-test

Acknowledgements

I downloaded the files from here: https://github.com/fchollet/deep-learning-models

Inspiration

I just wanted try out something with the Dogs vs Cats dataset and VGG19.

Keras

## Overview

Keras is a dataset for classification tasks - it contains Ripe annotations for 240 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Context

CIFAR-10 is the excellent Dataset for many Image processing experiments.

Content

Usage instructions

in Keras

from os import listdir, makedirs
from os.path import join, exists, expanduser

cache_dir = expanduser(join('~', '.keras'))
if not exists(cache_dir):
  makedirs(cache_dir)
datasets_dir = join(cache_dir, 'datasets') # /cifar-10-batches-py
if not exists(datasets_dir):
  makedirs(datasets_dir)

# If you have multiple input datasets, change the below cp command accordingly, typically:
# !cp ../input/cifar10-python/cifar-10-python.tar.gz ~/.keras/datasets/
!cp ../input/cifar-10-python.tar.gz ~/.keras/datasets/
!ln -s ~/.keras/datasets/cifar-10-python.tar.gz ~/.keras/datasets/cifar-10-batches-py.tar.gz
!tar xzvf ~/.keras/datasets/cifar-10-python.tar.gz -C ~/.keras/datasets/

general Python 3

def unpickle(file):
  import pickle
  with open(file, 'rb') as fo:
    dict = pickle.load(fo, encoding='bytes')
  return dict

!tar xzvf ../input/cifar-10-python.tar.gz

then see section "Dataset layout" in https://www.cs.toronto.edu/~kriz/cifar.html for details

Acknowledgements

Downloaded directly from here:

https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz

See description: https://www.cs.toronto.edu/~kriz/cifar.html

Inspiration

Your data will be in front of the world's largest data science community. What questions do you want to see answered?

Samples in this benchmark were generated by RELAI using the following data source(s): Data Source Name: keras Documentation Data Source Link: https://keras.io/ Data Source License: https://github.com/keras-team/keras/blob/master/LICENSE Data Source Authors: Observable AI Benchmarks by Data Agents © 2025 RELAI.AI. Licensed under CC BY 4.0. Source: https://relai.ai

Classify video clips with natural scenes of actions performed by people visible in the videos.

See the UCF101 Dataset web page: https://www.crcv.ucf.edu/data/UCF101.php#Results_on_UCF101

This example datasets consists of the 5 most numerous video from the UCF101 dataset. For the top 10 version see: https://doi.org/10.5281/zenodo.7882861 .

Based on this code: https://keras.io/examples/vision/video_classification/ (needs to be updated, if has not yet been already; see the issue: https://github.com/keras-team/keras-io/issues/1342).

Testing if data can be downloaded from figshare with `wget`, see: https://github.com/mojaveazure/angsd-wrapper/issues/10

For generating the subset, see this notebook: https://colab.research.google.com/github/sayakpaul/Action-Recognition-in-TensorFlow/blob/main/Data_Preparation_UCF101.ipynb -- however, it also needs to be adjusted (if has not yet been already - then I will post a link to the notebook here or elsewhere, e.g., in the corrected notebook with Keras example).

I would like to thank Sayak Paul for contacting me about his example at Keras documentation being out of date.

Cite this dataset as:

Soomro, K., Zamir, A. R., & Shah, M. (2012). UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402. https://doi.org/10.48550/arXiv.1212.0402

To download the dataset via the command line, please use:

wget -q https://zenodo.org/record/7924745/files/ucf101_top5.tar.gz -O ucf101_top5.tar.gz
tar xf ucf101_top5.tar.gz

Dataset description

This dataset was used to fine-tune this model

  Demo

You can try with this demo

  Intended uses & limitations

Image of Akita dog - A famous and cute dog of Japan

Dataset

This dataset was created by Rajnish Singh

Released under Data files © Original Authors

Contents

Dataset description

This dataset was used to fine-tune this model

  Demo

You can try with this demo

  Intended uses & limitations

Image of Hokusai artist

A complete list of live websites using the keras-js technology, compiled through global website indexing conducted by WebTechSurvey.

The dataset consists of CT brain scans with cancer, tumor, and aneurysm. Each scan represents a detailed image of a patient's brain taken using CT (Computed Tomography).

Dataset

This dataset was created by EtherY

Contents

The logos have been resized to a uniform shape of 70x70 to make it less demanding on computational resources and model complexity when training. Though the original files can be found on one of my github repos, the link can be found below. GitHub Repo. The code used to mine and process the data can also be found on the repo.

Original Data Source: Fake/Real Logo Detection Dataset

Holds images and other artifacts for https://github.com/sayakpaul/keras-xla-benchmarks.

TensorFlow, PyTorch, and Keras Framework Dataset: StackOverflow & GitHub

  Dataset Overview

This dataset contains a collection of questions, answers, and code snippets related to the TensorFlow, PyTorch, and Keras frameworks, sourced from StackOverflow and GitHub repositories. It provides a comprehensive resource for researchers, practitioners, and developers interested in analyzing and enhancing their understanding of these popular machine learning frameworks.… See the full description on the dataset page: https://huggingface.co/datasets/Eren5717/DPL_issues.