文件列表:

+solver (0, 2018-06-15)
+solver\adadelta.m (1339, 2018-06-15)
+solver\adagrad.m (1661, 2018-06-15)
+solver\adam.m (2211, 2018-06-15)
+solver\rmsprop.m (1119, 2018-06-15)
basic-SVM_Indian_pines (0, 2018-06-15)
basic-SVM_Indian_pines\India_Main.m (5112, 2018-06-15)
basic-SVM_Indian_pines\Random_Basic_Svm_Indian_pines.m (4087, 2018-06-15)
basic-SVM_Indian_pines\Slina_Main.m (3906, 2018-06-15)
basic-SVM_Indian_pines\TrainAndTTestGet.m (1147, 2018-06-15)
basic-SVM_Indian_pines\assessment.m (4562, 2018-06-15)
basic-SVM_Indian_pines\classify.m (315, 2018-06-15)
basic-SVM_Indian_pines\kappa.m (7196, 2018-06-15)
cifar (0, 2018-06-15)
cifar\India_cnn_cifar.m (5421, 2018-06-15)
cifar\India_cnn_cifar_init.m (3279, 2018-06-15)
cifar\India_cnn_cifar_init_nin.m (5583, 2018-06-15)
cifar\KSC_cnn_cifar.m (5406, 2018-06-15)
cifar\KSC_cnn_cifar_init.m (3268, 2018-06-15)
cifar\KSC_cnn_cifar_nin.m (5568, 2018-06-15)
cifar\PaviaU_cnn_cifar.m (5430, 2018-06-15)
cifar\PaviaU_cnn_cifar_init.m (3278, 2018-06-15)
cifar\PaviaU_cnn_cifar_init1.m (3258, 2018-06-15)
cifar\PaviaU_cnn_cifar_nin.m (5587, 2018-06-15)
cifar\Pavia_cnn_cifar.m (5420, 2018-06-15)
cifar\Pavia_cnn_cifar_init.m (3249, 2018-06-15)
cifar\Pavia_cnn_cifar_nin.m (5586, 2018-06-15)
cifar\Salinas_cnn_cifar.m (5438, 2018-06-15)
cifar\Salinas_cnn_cifar_init.m (3279, 2018-06-15)
cifar\Salinas_cnn_cifar_init_nin.m (5577, 2018-06-15)
cifar\cnn_cifar.m (5337, 2018-06-15)
cifar\cnn_cifar_init.m (3286, 2018-06-15)
cifar\cnn_cifar_init_nin.m (5561, 2018-06-15)
cifar\untils (0, 2018-06-15)
cifar\untils\Hyperspectral_display.m (1221, 2018-06-15)
cifar\untils\Output_architecture.m (25, 2018-06-15)
cifar\untils\cifar_India_Datapreprocessing.m (4540, 2018-06-15)
cifar\untils\color_cifar.m (1384, 2018-06-15)
cifar\untils\gaosi.m (53, 2018-06-15)
... ...

# Fast-RCNN demo This folder contains an example implementation of Fast-RCNN [1] in MatConvNet. The example trains and test on the PASCAL VOC 2007 data. There are three entry-point scripts: * `fast_rcnn_demo.m`: runs the original Caffe model imported in MatConvNet. * `fast_rcnn_train.m`: trains a new model from scratch, using pre-computed proposals. * `fast_rcnn_evaluate.m`: evaluates the trained model. Note that the code does not ship with a proposal generation method, so proposals must be precomputed (using e.g. edge boxes or selective search windows). The `fast_rcnn_demo.m` code should run out of the box, downloading the model as needed. To test the training code using the first GPU on your system, use something like: run matlab/vl_setupnn addpath examples/fast_rcnn fast_rcnn_train('train',struct('gpus',1)) ; fast_rcnn_evaluate('gpu',1) ; ## References 1. *Fast R-CNN*, R. Girshick, International Conference on Computer Vision (ICCV), 2015.

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：