food-detection-yolov5🍔🍟🍗 Food analysis baseline with Theseus. Integrate object detection, image classification and multi-class semantic segmentation. 🍞🍖🍕
Stars: ✭ 68 (-40.35%)
Mobilenetv2.pytorch72.8% MobileNetV2 1.0 model on ImageNet and a spectrum of pre-trained MobileNetV2 models
Stars: ✭ 369 (+223.68%)
bayexBayesian Optimization in JAX
Stars: ✭ 24 (-78.95%)
MobilePose-PiMobilePose deployment for Raspberry Pi
Stars: ✭ 15 (-86.84%)
jaxdfA JAX-based research framework for writing differentiable numerical simulators with arbitrary discretizations
Stars: ✭ 50 (-56.14%)
MobilePoseLight-weight Single Person Pose Estimator
Stars: ✭ 588 (+415.79%)
madam👩 Pytorch and Jax code for the Madam optimiser.
Stars: ✭ 46 (-59.65%)
robustness-vitContains code for the paper "Vision Transformers are Robust Learners" (AAAI 2022).
Stars: ✭ 78 (-31.58%)
jaxfgFactor graphs and nonlinear optimization for JAX
Stars: ✭ 124 (+8.77%)
quarkdetQuarkDet lightweight object detection in PyTorch .Real-Time Object Detection on Mobile Devices.
Stars: ✭ 82 (-28.07%)
FlaxengineFlax Engine – multi-platform 3D game engine
Stars: ✭ 3,127 (+2642.98%)
Retinaface Tf2RetinaFace (Single-stage Dense Face Localisation in the Wild, 2019) implemented (ResNet50, MobileNetV2 trained on single GPU) in Tensorflow 2.0+. This is an unofficial implementation. With Colab.
Stars: ✭ 178 (+56.14%)
Msnhnet🔥 (yolov3 yolov4 yolov5 unet ...)A mini pytorch inference framework which inspired from darknet.
Stars: ✭ 357 (+213.16%)
EinopsDeep learning operations reinvented (for pytorch, tensorflow, jax and others)
Stars: ✭ 4,022 (+3428.07%)
Mobilenetv2A Keras implementation of MobileNetV2.
Stars: ✭ 277 (+142.98%)
Hypernsfw基于深度学习图片鉴黄 Caffe implementation of Not Suitable for Work (NSFW)
Stars: ✭ 143 (+25.44%)
flaxOptimizersA collection of optimizers, some arcane others well known, for Flax.
Stars: ✭ 21 (-81.58%)
GPJaxA didactic Gaussian process package for researchers in Jax.
Stars: ✭ 159 (+39.47%)
Face-Mask-Detection-PyTorchA real-time face mask detector based on computer vision and deep learning, created using Pytorch and OpenCV
Stars: ✭ 12 (-89.47%)
JaxComposable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Stars: ✭ 15,579 (+13565.79%)
Hbonet[ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions
Stars: ✭ 94 (-17.54%)
image embeddingsUsing efficientnet to provide embeddings for retrieval
Stars: ✭ 107 (-6.14%)
Mobilenet V2 Repository for "Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation".
Stars: ✭ 73 (-35.96%)
bigbrother-specsResearch and specification for Big Brother protocol
Stars: ✭ 13 (-88.6%)
ml-testing-acceleratorsTesting framework for Deep Learning models (Tensorflow and PyTorch) on Google Cloud hardware accelerators (TPU and GPU)
Stars: ✭ 45 (-60.53%)
ADAMADAM implements a collection of algorithms for calculating rigid-body dynamics in Jax, CasADi, PyTorch, and Numpy.
Stars: ✭ 51 (-55.26%)
FlaxFlax is a neural network library for JAX that is designed for flexibility.
Stars: ✭ 2,447 (+2046.49%)
TensornetsHigh level network definitions with pre-trained weights in TensorFlow
Stars: ✭ 982 (+761.4%)
AdanetFast and flexible AutoML with learning guarantees.
Stars: ✭ 3,340 (+2829.82%)
LightnetLightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Stars: ✭ 698 (+512.28%)
jax-cfdComputational Fluid Dynamics in JAX
Stars: ✭ 399 (+250%)
Stronger Yolo🔥Improve yolo with latest paper
Stars: ✭ 539 (+372.81%)
hftaBoost hardware utilization for ML training workloads via Inter-model Horizontal Fusion
Stars: ✭ 18 (-84.21%)
berserkerBerserker - BERt chineSE woRd toKenizER
Stars: ✭ 17 (-85.09%)
Deeplabv3plus PytorchDeepLabv3, DeepLabv3+ and pretrained weights on VOC & Cityscapes
Stars: ✭ 337 (+195.61%)
EfficientUNetPlusPlusDecoder architecture based on the UNet++. Combining residual bottlenecks with depthwise convolutions and attention mechanisms, it outperforms the UNet++ in a coronary artery segmentation task, while being significantly more computationally efficient.
Stars: ✭ 37 (-67.54%)
Thinc🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
Stars: ✭ 2,422 (+2024.56%)
RMNetRM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.
Stars: ✭ 129 (+13.16%)
TraxTrax — Deep Learning with Clear Code and Speed
Stars: ✭ 6,666 (+5747.37%)
FoolboxA Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
Stars: ✭ 2,108 (+1749.12%)
ShinRLShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives (Deep RL Workshop 2021)
Stars: ✭ 30 (-73.68%)
googlecodelabsTPU ile Yapay Sinir Ağlarınızı Çok Daha Hızlı Eğitin
Stars: ✭ 116 (+1.75%)
ghostnet.pytorch73.6% GhostNet 1.0x pre-trained model on ImageNet
Stars: ✭ 90 (-21.05%)
TPU-PosenetEdge TPU Accelerator / Multi-TPU / Multi-Model + Posenet/DeeplabV3/MobileNet-SSD + Python + Sync / Async + LaptopPC / RaspberryPi
Stars: ✭ 39 (-65.79%)