145 Open source projects that are alternatives of or similar to efficientnet-jax

Benchmark for DeepLearning anomaly detection

Deep learning model to estimate the depth of image.

yolo3 implement by tensorflow， including mobilenet_v1, mobilenet_v2

Computer vision library for wildfire detection

LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)

Inspired 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.

Tensorflow 2 Faster-RCNN implementation from scratch supporting to the batch processing with MobileNetV2 and VGG16 backbones

No description or website provided.

caffe based mobilenet v2 deploy

No description or website provided.

Caffe Implementation of MobileNets V3

Hands on Imagenet training. Unofficial ModelZoo project on Pytorch. MobileNetV3 Top1 75.64🌟 GhostNet1.3x 75.78🌟

Tensorflow implementation for two new MobileNetV3 models!

⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

Implementation of EfficientNet model. Keras and TensorFlow Keras.

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

Google Brain AutoML

Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

More readable and flexible yolov5 with more backbone(resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer) and (cbam，dcn and so on), and tensorrt

Some parts of my code for the Computer Vision Kaggle Bengali AI Handwritten Grapheme Classification competition

Code for Video Deepfake Detection model from "Combining EfficientNet and Vision Transformers for Video Deepfake Detection" available on Arxiv and was submitted to ICIAP 2021.

A Gluon Implement of EfficientNet

Using deep learning models for image classification directly on the HoloLens 2.

detectron2 backbone: resnet18, efficientnet, hrnet, mobilenet v2, resnest, bifpn

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.