搜索资源列表
fast-rcnn-master
- Fast Region-based Convolutional Networks for object detection. Fast R-CNN** is a fast framework for object detection with deep ConvNets. Fast R-CNN - trains state-of-the-art models, like VGG16, 9x faster than traditional R-CNN and 3x faster than
py-faster-rcnn-master
- This an article on the depth of learning R-CNN article code, only for white learning-This is an article on the depth of learning R-CNN article code, only for white learning
mscnn-master
- MSCNN多尺度rcnn的目标检测代码，可以实现多尺度的目标检测，具有多尺度的感受野(MSCNN multi-scale RCNN target detection code)
cascadeCNN_license_plate_detection-master
- 很好的一个车牌检测程序,检测率很高，快速卷积神经网络SoftwareMatlab R2016b Matlab R2016b(plate lisence detectionMatlab lesson design for vehicle detection and recognition. Using cifar-10Net to training a RCNN, and finetune AlexNet to classify. Thanks to Cars Dataset : http:/
mask rcnn
- 跑通的Mask rcnn图像检测，深度神经网络人工智能，检测准确度高(Deep neural network High detection accuracy, including trained data)
fast-rcnn-master
- Fast R-CNN是在R-CNN的基础上进行的改进，大致框架是一致的。总体而言，Fast R-CNN相对于R-CNN而言，主要提出了三个改进策略： 1. 提出了RoIPooling，避免了对提取的region proposals进行缩放到224x224，然后经过pre-trained CNN进行检测的步骤，加速了整个网络的learning与inference过程，这个是巨大的改进，并且RoIPooling是可导的，因此使得整个网络可以实现end-to-end learning，这个可以认为是