fishman2008 / stanford-cars-classification
Image classification on stanford-car dataset with high accuracy
☆16Updated 5 years ago
Related projects: ⓘ
- ☆56Updated 3 years ago
- Pytorch implementation of RetinaNet using EfficientNets as feature extractor or backbone network.☆40Updated 3 years ago
- iTASK - Intelligent Traffic Analysis Software Kit☆29Updated last year
- Classifying the Stanford Car dataset using ResNet 50☆25Updated last year
- FCOS (Fully Convolutional One-Stage Object Detection) implementation in Keras and Tensorflow☆64Updated 11 months ago
- For the Kaggle Competition on object detection with same name. 1) models used are DETR, EfficientDet, YOLOv5, RetinaNet, FasterRCNN. 2) E…☆11Updated 2 years ago
- multi-scale training in pytorch☆44Updated 4 years ago
- ATSS-EfficientDet implemented in PyTorch, outperforming the original EfficientDet. Weights are released.☆66Updated 4 years ago
- This repo primarily targets to help those who needs to compute anchors to customer dataset in object detection.☆80Updated 4 years ago
- [CVIU 2019] ASSD learns to highlight useful regions on the feature maps while suppressing the irrelevant information, thereby providing r…☆39Updated 2 years ago
- Porting https://github.com/marvis/pytorch-yolo2 to Python 3☆8Updated 6 years ago
- A simple utility programe to visualize pascal voc (format) dataset images with bounding boxes. Useful to check whether there is any error…☆23Updated 3 weeks ago
- For ICDAR 2019 Paper on End-to-end License Plate and Scene Text Recognition with multi-head attention models☆26Updated 3 years ago
- Inference Code for RetinaFace with MobileNet Backend in PyTorch☆44Updated 5 years ago
- Simple mmdetection CPU inference☆29Updated 3 years ago
- SAPD (Soft Anchor-Point Object Detection) implementation in Keras and Tensorflow☆94Updated last year
- Working with scale: 2nd place solution to Product Detection in Densely Packed Scenes☆48Updated 4 years ago
- This repo contains a minimalist implementation of centernet.☆55Updated 4 years ago
- Vehicle-Rear: A New Dataset to Explore Feature Fusion For Vehicle Identification Using Convolutional Neural Networks☆111Updated 3 years ago
- ☆35Updated 5 years ago
- Convert COCO annotations to xml format☆19Updated 3 years ago
- deep-learning losses playground☆29Updated 5 years ago
- see details in configs/retinanet_se154_fpn_1x.py☆38Updated 5 years ago
- Mosaic Data Augmentation in YOLOv4☆18Updated 4 years ago
- PyTorch Implementation for DR Loss☆110Updated 9 months ago
- This project is a kind of implementation of SpineNet(CVPR 2020) using mmdetection.☆96Updated 4 years ago
- Omni-Scale reID net in a containerised PyTorch version☆17Updated last month
- Detection masks on faces.☆29Updated 4 years ago
- Convert pre-trained classifier to object detector without training☆24Updated 3 years ago
- Bounding box augmentations for Pytorch☆121Updated 3 years ago