zhouyuangan / flops-counter.pytorch
Flops counter for convolutional networks in pytorch framework
☆11Updated 4 years ago
Related projects: ⓘ
- Learning Data Augmentation Strategies for Object Detection in numpy☆55Updated 3 years ago
- ☆23Updated 5 years ago
- OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks☆26Updated 5 years ago
- ☆68Updated 5 years ago
- Dense Receptive Field For Object Detection☆25Updated 5 years ago
- simpledet和mmdetection源码阅读笔记☆27Updated 5 years ago
- Real-time generic object detection on mobile platforms is a crucial but challenging computer vision task. However, previous CNN-based det…☆26Updated 5 years ago
- 基于hrnet的backbone改进centernet☆21Updated 5 years ago
- ☆16Updated this week
- ☆13Updated this week
- RefineDet_API_for_pytorch C++☆27Updated 3 years ago
- ☆13Updated this week
- mmdetection源码解析☆38Updated 5 years ago
- Multi-class object detection pipeline—Single Shot MultiBox Detector (SSD) + YOLOv3 (real-time) + focal loss (RetinaNet) + Pascal VOC 2007…☆18Updated 6 years ago
- 实现常用的one-stage和two-stage目标检测网络 华为媒体研究院 图文Caption、OCR识别、图视文多模态理解与生成相关方向工作或实习欢迎咨询 15757172165 https://guanfuchen.github.io/media/hw_zhaopin…☆54Updated 5 years ago
- ☆29Updated this week
- PeleeNet in PyTorch☆40Updated 6 years ago
- ☆16Updated this week
- ☆13Updated 5 years ago
- Summary of object detection(modules&&improvements)☆51Updated 4 years ago
- SaccadeNet : mimic how human locate accurate bounding box☆28Updated 5 years ago
- Codes for paper: "IoU-Uniform R-CNN: Breaking Through the Limitations of RPN"☆51Updated 4 years ago
- A detect network with densenet inceptionv4 deformconv senet attention fpn snip soft-nms☆9Updated 6 years ago
- FCOS: Fully Convolutional One-Stage Object Detection.☆25Updated last year
- Try to implement deeplab v3+ on pytorch according to offical demo.☆42Updated 6 years ago
- mnist classify using center loss☆13Updated 6 years ago
- ☆23Updated 6 years ago
- ☆20Updated 5 years ago
- ☆37Updated 5 years ago
- Instance Segmentation, TensorMask☆51Updated 4 years ago