Depth estimationDeep learning model to estimate the depth of image.
Stars: ✭ 62 (-45.61%)
yolo3 tensorflowyolo3 implement by tensorflow, including mobilenet_v1, mobilenet_v2
Stars: ✭ 48 (-57.89%)
pyro-visionComputer vision library for wildfire detection
Stars: ✭ 33 (-71.05%)
LightNetLightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Stars: ✭ 710 (+522.81%)
Mask-YOLOInspired from Mask R-CNN to build a multi-task learning, two-branch architecture: one branch based on YOLOv2 for object detection, the other branch for instance segmentation. Simply tested on Rice and Shapes. MobileNet supported.
Stars: ✭ 100 (-12.28%)
tf-faster-rcnnTensorflow 2 Faster-RCNN implementation from scratch supporting to the batch processing with MobileNetV2 and VGG16 backbones
Stars: ✭ 88 (-22.81%)
ModelZoo.pytorchHands on Imagenet training. Unofficial ModelZoo project on Pytorch. MobileNetV3 Top1 75.64🌟 GhostNet1.3x 75.78🌟
Stars: ✭ 42 (-63.16%)
MobileNetV3-TFTensorflow implementation for two new MobileNetV3 models!
Stars: ✭ 25 (-78.07%)
Nanodet⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
Stars: ✭ 3,640 (+3092.98%)
EfficientnetImplementation of EfficientNet model. Keras and TensorFlow Keras.
Stars: ✭ 1,920 (+1584.21%)
Yet Another Efficientdet PytorchThe pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.
Stars: ✭ 4,945 (+4237.72%)
AutomlGoogle Brain AutoML
Stars: ✭ 4,795 (+4106.14%)
Segmentation modelsSegmentation models with pretrained backbones. Keras and TensorFlow Keras.
Stars: ✭ 3,575 (+3035.96%)
flexible-yolov5More readable and flexible yolov5 with more backbone(resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer) and (cbam,dcn and so on), and tensorrt
Stars: ✭ 282 (+147.37%)
detectron2 backbonedetectron2 backbone: resnet18, efficientnet, hrnet, mobilenet v2, resnest, bifpn
Stars: ✭ 171 (+50%)
Ensemble-of-Multi-Scale-CNN-for-Dermatoscopy-ClassificationFully 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.
Stars: ✭ 25 (-78.07%)