DavidLandup0 / deepvision
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.
☆35Updated last year
Related projects ⓘ
Alternatives and complementary repositories for deepvision
- A Keras implementation of hybrid efficientnet swin transformer model.☆33Updated last year
- This repository demonstrates how to use TensorFlow based SegFormer model in 🤗 transformers package.☆30Updated 2 years ago
- Implementation of Deep Orthogonal Fusion of Local and Global Features in TensorFlow 2☆25Updated last year
- ResNet-RS models rewritten in Tensorflow / Keras functional API.☆27Updated last year
- Includes PyTorch -> Keras model porting code for DeiT models with fine-tuning and inference notebooks.☆41Updated 2 years ago
- Tensorflow 2.0 Implementation of GCViT: Global Context Vision Transformer☆27Updated 10 months ago
- ☆24Updated 2 years ago
- A Detection Toolbox for Tensorflow2☆56Updated last year
- Heatmap Learner Convolutional Neural Network for Object Counting and Localization☆42Updated 9 months ago
- TensorFlow2.x implementation of RetinaNet☆40Updated 3 years ago
- Adds timm pretrained backbone to pytorch's FasterRcnn model☆12Updated 9 months ago
- ☆16Updated last year
- Code for our paper CPPE - 5 (Medical Personal Protective Equipment), a new challenging object detection dataset☆67Updated 2 months ago
- Unofficial implementation of "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" (https://arxiv.org/abs/2103.14030)☆65Updated 3 years ago
- Includes PyTorch -> Keras model porting code for ConvNeXt family of models with fine-tuning and inference notebooks.☆100Updated 2 years ago
- Converting Instance segmentation labels in COCO format to YOLOv5-seg☆13Updated last year
- Implementation of RegNetY in TensorFlow 2☆20Updated last year
- Implementation of Swin Transformers in TensorFlow along with converted pre-trained models, code for off-the-shelf classification and fine…☆56Updated 2 years ago
- Building a maskrcnn from scratch using tensorflow and keras☆50Updated 3 years ago
- This repository shows how to train a custom detection model with the TFOD API, optimize it with TFLite, and perform inference with the op…☆31Updated 3 years ago
- Implements RNNPool and SoftPool for CNNs.☆14Updated 3 years ago
- Keras Implementation of Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)☆95Updated 4 years ago
- A Tensorflow implementation of Deep Lab V3 Plus from scratch.☆22Updated 4 years ago
- Python scripts performing object detection using the YOLOv6 model in ONNX.☆93Updated 2 years ago
- Tensorflow implementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformer☆97Updated 3 years ago
- A personal implementation of YOLOv5 (v6.0)☆47Updated last year
- A clean, modular implementation of the Yolov7 model family, which uses the official pretrained weights, with utilities for training the m…☆116Updated 9 months ago
- Vision Transformers for image classification, image segmentation, and object detection.☆43Updated last month
- Implementation of CaiT models in TensorFlow and ImageNet-1k checkpoints. Includes code for inference and fine-tuning.☆12Updated last year
- PyTorch Lightning based training of Semantic Segmentation models☆38Updated last year