Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

An awesome list of TensorFlow Lite models, samples, tutorials, tools and learning resources.

Books, Presentations, Workshops, Notebook Labs, and Model Zoo for Software Engineers and Data Scientists wanting to learn the TF.Keras Machine Learning framework

Unofficial implementation of MobileNetV3 architecture described in paper Searching for MobileNetV3.

🛠 Mask R-CNN Keras to Tensorflow and TFX models + Serving models using TFX GRPC & RESTAPI

Collection of different Unet Variant suchas VggUnet, ResUnet, DenseUnet, Unet. AttUnet, MobileNetUnet, NestedUNet, R2AttUNet, R2UNet, SEUnet, scSEUnet, Unet_Xception_ResNetBlock

Unofficial implementation of Octave Convolutions (OctConv) in TensorFlow / Keras.

基于tf.keras的多标签多分类模型

Transformer-based models implemented in tensorflow 2.x(using keras).

Simple stochastic weight averaging callback for Keras

YOLOv4 Implemented in Tensorflow 2.0. Convert YOLO v4 .weights to .pb and .tflite format for tensorflow and tensorflow lite.

A friendly python package for Keras Hyperparameters Tuning based only on NumPy and hyperopt.

Note for Aurélien Géron's 2019 book "Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition"

Fully supervised binary classification of skin lesions from dermatoscopic images using an ensemble of diverse CNN architectures (EfficientNet-B6, Inception-V3, SEResNeXt-101, SENet-154, DenseNet-169) with multi-scale input.

A variational autoencoder for volumetric shape generation

tensorflow.keras implementation of gradcam and gradcam++

Hierarchical probabilistic 3D U-Net, with attention mechanisms (—𝘈𝘵𝘵𝘦𝘯𝘵𝘪𝘰𝘯 𝘜-𝘕𝘦𝘵, 𝘚𝘌𝘙𝘦𝘴𝘕𝘦𝘵) and a nested decoder structure with deep supervision (—𝘜𝘕𝘦𝘵++). Built in TensorFlow 2.5. Configured for voxel-level clinically significant prostate cancer detection in multi-channel 3D bpMRI scans.

Pruning and other network surgery for trained TF.Keras models.

[Medical Image Analysis] Residual Aligner-based Network (RAN): Motion-Aware Structure for Coarse-to-fine Discontinuous Deformable Registration

Integrating Airbyte, Kafka, Airflow and MLflow on Azure Linux VMs within private network to continuously retrain LSTM Attention model with 1-minute stock prices and redeploy it on Azure ML AKS real-time inference endpoint behind serverless Azure API