Showing 36 of 350 projects
A CNN-based captcha solver for Taiwan Railway booking website with a training set generator that mimics captcha style and uses data augmentation.
A transfer learning-based evaluation metric for Natural Language Generation that scores text fluency and meaning.
A TensorFlow implementation for generating semantically segmented bird's eye view images from multiple vehicle-mounted cameras using a Sim2Real deep learning approach.
TensorFlow implementation of character-aware neural language models using CNN, highway networks, and LSTM.
A scalable library for exploring, validating, and monitoring machine learning data, integrated with TensorFlow and TFX.
CNN visualization tool in TensorFlow
TensorFlow implementation of arbitrary order (≥2) Factorization Machines for classification and regression tasks.
TensorFlow binding for Apache Spark DataFrames, enabling TensorFlow program execution on Spark data.
NeuPy is a Tensorflow based python library for prototyping and building neural networks
A Siamese neural network for LiDAR-based loop closing and localization by predicting scan overlap and relative yaw angle.
ROS package implementing a deep reinforcement learning algorithm for dynamic obstacle avoidance in ground robots.
An open-source machine learning system for training autonomous RC cars using computer vision and neural networks.
TensorFlow port for AMD GPUs via ROCm, enabling machine learning on Radeon hardware.
Generates realistic handwriting using LSTM Mixture Density Networks implemented in TensorFlow.
A modular deep reinforcement learning framework for portfolio management, enabling algorithmic stock trading with DQN and DDPG agents.
A TensorFlow library for training, serving, and interpreting decision forest models like Random Forests and Gradient Boosted Trees.
Real-time object detection on Android using YOLO with TensorFlow, detecting 20 object classes from the Pascal VOC dataset.
A collection of TensorFlow practice exercises covering fundamental machine learning concepts from linear regression to CNNs.
Classify music genre from a 10-second audio stream using a convolutional neural network trained on mel-frequency spectrograms.
TensorFlow implementation of GAN-CLS algorithm for generating images from text descriptions using adversarial networks.
A quantization extension for Keras that provides drop-in replacement layers for creating quantized deep learning models in TensorFlow.
TensorFlow implementation of R-Net for machine reading comprehension on the SQuAD dataset.
A convolutional neural network model for real-time road-object segmentation from 3D LiDAR point clouds.
A TensorFlow-based image recognition system for captchas that works without image segmentation.
A web application that uses a CNN model to recognize handwritten Chinese characters from an online drawing canvas.
A U-Net implementation for brain tumor segmentation using the BRATS 2017 dataset with data augmentation and dice loss.
A unified deep learning and reinforcement learning framework supporting multiple backends and hardware platforms.
A TensorFlow library implementing constrained and interpretable lattice-based models with shape constraints like monotonicity and convexity.
A book teaching practical patterns for building scalable and reliable distributed machine learning systems using Kubernetes, TensorFlow, Kubeflow, and Argo Workflows.
A standalone reimplementation of TensorFlow for Ruby, supporting pure Ruby and OpenCL backends for machine learning.
A TensorFlow implementation of the neural style transfer algorithm that applies artistic styles to images.
A deep learning library for single-cell analysis of biological images, specializing in cell segmentation and tracking.
A deep learning toolkit for predicting regulatory activity, 3D genome folding, and mRNA half-life from DNA/RNA sequences.
An Android example project demonstrating TensorFlow integration for handwritten digit recognition using the MNIST dataset.
A toolkit that streamlines and automates the generation of model cards for machine learning models.
An AI-powered captcha solver using SimGAN to generate synthetic training data without manual labeling.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.