zhaoweicai/mscnn
A Caffe-based multi-scale convolutional neural network for fast object detection targeting autonomous driving applications.

Velocity · 7d
+0.1
★ / day
Trend
→steady
star history
MS-CNN is a unified multi-scale object detection framework based on deep convolutional networks. It combines an object proposal sub-network with an object detection sub-network that can be trained end-to-end together. Built on the Caffe deep learning framework with CUDA and cuDNN support for GPU acceleration.