CNV_2305

def im_list_to_blob(ims):将图像转换成blob（np.ndarray）def im_list_to_blob(ims): """Convert a list of images into a network input. Assumes images are already prepared (means subtracted, BGR order

定义了一个 ProposalLayer 类， 在rpn_test.pt中会用到。class ProposalLayer(caffe.Layer): """ Outputs object detection proposals by applying estimated bounding-box transformations to a set of regular boxes

定义了一个类：class SolverWrapperclass SolverWrapper(object): """A simple wrapper around Caffe's solver. This wrapper gives us control over he snapshotting process, which we use to unnormalize

主要定义了一个pascal_voc类，在类的内部定义了它的一些属性和方法。def _init_(self, image_set, year, devkit_path=None) 构造器方法def __init__(self, image_set, year, devkit_path=None): imdb.__init__(self, 'voc_' + year + '_'

1. roidb是一个列表，列表元素为字典2. prepare_roidb 函数def prepare_roidb(imdb): """Enrich the imdb's roidb by adding some derived quantities that are useful for training. This function precomputes the m

def merge_roidbs(a, b) 类imdb的静态方法，将a b两个roidb归并为一个roidb@staticmethod def merge_roidbs(a, b): assert len(a) == len(b) for i in xrange(len(a)): # boxes 采用vstack

def get_roidb(imdb_name, rpn_file=None):def get_roidb(imdb_name, rpn_file=None): imdb = get_imdb(imdb_name) #返回一个pascal_voc类对象 print 'Loaded dataset `{:s}` for training'.format(imdb.name)

class AnchorTargetLayer(caffe.Layer): """ Assign anchors to ground-truth targets. Produces anchor classification labels and bounding-box regression targets. """ def setup(self, botto

def _sample_rois(roidb, fg_rois_per_image, rois_per_image, num_classes) 在 def get_minibatch(roidb, num_classes) 中调用此函数，传进来的实参为单张图像的roidb ，该函数主要功能是随机组合sample of RoIs， 来生成前景样本和背景样本。def _sample_rois(

主要定义了一个 ROIPoolingLayer 类ROIPoolingLayer的受保护数据成员有：int channels_;int height_;int width_;int pooled_height_; // pooling后的特征图的height_int pooled_width_; // pooling后的特征图的width_Dtype spatial_scale_; //

def setup(self, bottom, top)方法： 该方法主要是在创建RoIDataLayer的时候调用。结合_caffe.cpp里面.def("setup", &Layer::LayerSetUp)，个人猜测（水平有限），setup(self, bottom, top)应该还是调用底层的Layer::LayerSetUp方法，同时bottom, top也分别对应着：const vec

该模块的功能主要是生成rpn proposals。 + cv2.imread读取的图像的存储格式为H W K，且三通道的顺序为BGR + PIL.Image.open读取图片的存储格式为：W H (此时的数据为PIL库的某种对象)，且三通道顺序为RGB 但是，当转换为np.array的时候，存储格式将H W K,常用的代码段为：def load_image(self, idx):