Google Brain AutoML
-
Updated
Apr 2, 2024 - Jupyter Notebook
Google Brain AutoML
PyTorch implementation of EfficientNetV2 family
Multi-backbone, Prune, Quantization, KD
EfficientNetV2 implementation using PyTorch
self defined efficientnetV2 according to official version. Including converted ImageNet/21K/21k-ft1k weights.
EfficientNetV2 pytorch (pytorch lightning) implementation with pretrained model
Pytorch EfficientNetV2 EfficientNetV1 with pretrained weights
PyTorch and TensorFlow/Keras image models with automatic weight conversions and equal API/implementations - Vision Transformer (ViT), ResNetV2, EfficientNetV2, NeRF, SegFormer, MixTransformer, (planned...) DeepLabV3+, ConvNeXtV2, YOLO, etc.
This GitHub repository contains instructions for downloading and utilizing the AI4Food-NutritionDB food image database, as well as different food recognition systems based on Xception and EfficientNetV2 architectures.
Real Time Detection of Anomalous Activity From Videos (mainly crime actvity). Images of the video is trained using AutoEncoder to get the imtermediate feature representation of image & applied svm model for the bag of such features to detect the anomaly & LSTM to detect the type of Anomaly.
An Android App recreating the Simon Says game. Uses MediaPipe to run an LLM on device
EfficientNetV2 based PaDiM
Pytorch implementation of efficientnet v2 backbone with detectron2 for object detection (Just for fun)
花分类,使用VGGNet、GoogLeNet、ResNet、DenseNet、EfficientNet和数据集中80%的数据训练识别模型,并对剩下20%的数据集进行测试
Source codes of team TikTorch (1st place solution) for track 2 and 3 of the SHREC2023 Challenge
EfficientNetV2: Smaller Models and Faster Training. PyTorch Implementation of EfficientNetV2 Family
DeepLabV3+ Implementation using TensorFlow 2
Implementation of EfficientNetV2 model in TensorFlow 2 Keras.
PLANT DISEASE DETECTION USING CNN
Add a description, image, and links to the efficientnetv2 topic page so that developers can more easily learn about it.
To associate your repository with the efficientnetv2 topic, visit your repo's landing page and select "manage topics."