This project modifies, trains and implements RegNetX-200MF for image classification of a modified variant of ImageNet.
-
Updated
Aug 16, 2021 - Python
This project modifies, trains and implements RegNetX-200MF for image classification of a modified variant of ImageNet.
Optimizing DNN Operators on Mobile GPUs
RegNet (Designing Network Design Spaces) implementation in TensorFlow-2 with pretrained weights.
Train the RegNet classifier model using Tensorflow on Colab.
This repository holds the downstream task of Face Mask Classification performed on Self Currated Custom Dataset with various State of the Art deep learning models like ViT, BeIT, DeIT, LeViT, ConvNeXt, VGG16, EfficientNetV2, RegNet and MobileNetV3.
Implementation of RegNet (Tensorflow)
Deployment of 3D-Detection and Tracking pipeline in simulation based on rosbags and real-time.
A pytorch implement of RegNet (Designing Netowrk design spaces). Original paper link: https://arxiv.org/pdf/2003.13678.pdf
Classification wearing face mask or not
This project uses PyTorch to classify bone fractures. As well as fine-tuning some famous CNN architectures (like VGG 19, MobileNetV3, RegNet,...), we designed our own architecture. Additionally, we used Transformer architectures (such as Vision Transformer and Swin Transformer). This dataset is Bone Fracture Multi-Region X-ray, available on Kaggle.
An image registration method using convolutional neural network features.
Here is an implementation of DeepLabv3+ in PyTorch(1.7). It supports many backbones and datasets.
A PyTorch-based Python library with UNet architecture and multiple backbones for Image Semantic Segmentation.
PyTorch-style and human-readable RegNet with a spectrum of pre-trained models
Multi-label classification based on timm.
Pytorch implementation of network design paradigm described in the paper "Designing Network Design Spaces"
A tensorflow2 implementation of some basic CNNs(MobileNetV1/V2/V3, EfficientNet, ResNeXt, InceptionV4, InceptionResNetV1/V2, SENet, SqueezeNet, DenseNet, ShuffleNetV2, ResNet).
Add a description, image, and links to the regnet topic page so that developers can more easily learn about it.
To associate your repository with the regnet topic, visit your repo's landing page and select "manage topics."