keras faster r-cnn源代码解析（四）——ROI

一、利用ROI训练分类器

最后是ROI的生成了，在每个训练的epch循环中，核心代码如下：

 #输出：yield np.copy(x_img), [np.copy(y_rpn_cls), np.copy(y_rpn_regr)], img_data_aug
        #网络训练的输入是图片，和找到的最优的anchor，不是GTbox
        X, Y, img_data = next(data_gen_train)
        #
        loss_rpn = model_rpn.train_on_batch(X, Y)#Scalar training loss (if the model has a single output and no metrics) or list of scalars (if the model has multiple outputs and/or metrics). 
        write_log(callback, ['rpn_cls_loss', 'rpn_reg_loss'], loss_rpn, train_step)
        P_rpn = model_rpn.predict_on_batch(X)#获取预测的Y值，即[np.copy(y_rpn_cls), np.copy(y_rpn_regr)]
        #筛选出ROI,ROI指的是在feature map中合法box中具有最大概率包含物体的box，删除重叠率较高的box之后剩下来的box(xxx,4)
        R = roi_helpers.rpn_to_roi(P_rpn[0], P_rpn[1], C, K.image_dim_ordering(), use_regr=True, overlap_thresh=0.7, max_boxes=300)
        # note: calc_iou converts from (x1,y1,x2,y2) to (x,y,w,h) format
        #img_data，图片的信息，R候选ROI
        #输出：
        #X2：#选取的iou大于0.7的roi,这里用X2是为了和上面的X相区别，
        #Y1：对应的类别序号(1,xxx,21)，类别标签是one_hot
        #Y2:[np.array(y_class_regr_label),np.array(y_class_regr_coords)]包含对应的类别的标签和回归参数，类别标签是one_hot的
        #IoUs：用于调试的，没有用
        X2, Y1, Y2, IouS = roi_helpers.calc_iou(R, img_data, C, class_mapping)

        if X2 is None:
            rpn_accuracy_rpn_monitor.append(0)
            rpn_accuracy_for_epoch.append(0)
            continue

        # sampling positive/negative samples
        neg_samples = np.where(Y1[0, :, -1] == 1)#背景，最后一项代表背景分类
        pos_samples = np.where(Y1[0, :, -1] == 0)#非背景

        if len(neg_samples) > 0:
            neg_samples = neg_samples[0]
        else:
            neg_samples = []

        if len(pos_samples) > 0:
            pos_samples = pos_samples[0]
        else:
            pos_samples = []

        rpn_accuracy_rpn_monitor.append(len(pos_samples))
        rpn_accuracy_for_epoch.append((len(pos_samples)))

        if C.num_rois > 1:
            if len(pos_samples) < C.num_rois//2:#选取一些正例样本和一些反例样本，共300个，每类约150个
                selected_pos_samples = pos_samples.tolist()
            else:
                selected_pos_samples = np.random.choice(pos_samples, C.num_rois//2, replace=False).tolist()
            try:
                selected_neg_samples = np.random.choice(neg_samples, C.num_rois - len(selected_pos_samples), replace=False).tolist()
            except:
                selected_neg_samples = np.random.choice(neg_samples, C.num_rois - len(selected_pos_samples), replace=True).tolist()

            sel_samples = selected_pos_samples + selected_neg_samples
        else:
            # in the extreme case where num_rois = 1, we pick a random pos or neg sample
            selected_pos_samples = pos_samples.tolist()
            selected_neg_samples = neg_samples.tolist()
            if np.random.randint(0, 2):
                sel_samples = random.choice(neg_samples)
            else:
                sel_samples = random.choice(pos_samples)
        #X用于生成share_layers,X2是挑选出来的roi
        loss_class = model_classifier.train_on_batch([X, X2[:, sel_samples, :]], [Y1[:, sel_samples, :], Y2[:, sel_samples, :]])
        write_log(callback, ['detection_cls_loss', 'detection_reg_loss', 'detection_acc'], loss_class, train_step)
        train_step += 1

这里面有两个关键方法，rpn_to_roi和calc_iou࿰