實現Faster R-CNN的keras程式碼理解(三)
阿新 • • 發佈：2018-12-18
計算RPN網路的輸出值
函式為datagenerators.py中的calc_rpn():
輸入：配置檔案，增強後的圖片的資訊，圖片原寬，圖片原高，resize後的寬，resize後的高，網路最後輸出的卷積層的大小；
輸出：y_rpn_cls前半段是否包含物體，y_rpn_regr迴歸的梯度
流程如圖所示：
程式碼詳解：
def calc_rpn(C, img_data, width, height, resized_width, resized_height, img_length_calc_function): #downsacle預設是16，共享卷積層壓縮影象的倍數 downscale = float(C.rpn_stride) anchor_sizes = C.anchor_box_scales anchor_ratios = C.anchor_box_ratios num_anchors = len(anchor_sizes) * len(anchor_ratios) #計算最後一個卷積層輸出的feature map的大小 # calculate the output map size based on the network architecture (output_width, output_height) = img_length_calc_function(resized_width, resized_height) n_anchratios = len(anchor_ratios) # initialise empty output objectives y_rpn_overlap = np.zeros((output_height, output_width, num_anchors))#anchor是否與gta有overlap，且其IOU>0.7，overlap則為1反之則為0 y_is_box_valid = np.zeros((output_height, output_width, num_anchors))#anchor是否有效，有效則為1，反之為0 y_rpn_regr = np.zeros((output_height, output_width, num_anchors * 4))#返回的是與gta有overlap的anchor的梯度 num_bboxes = len(img_data['bboxes']) num_anchors_for_bbox = np.zeros(num_bboxes).astype(int)#返回與每一個gta有overlap的anchor的數量 best_anchor_for_bbox = -1*np.ones((num_bboxes, 4)).astype(int)#返回與每一個gta置信度最高的anchor的位置 best_iou_for_bbox = np.zeros(num_bboxes).astype(np.float32)#返回與每一個gta置信度最高的anchor的分數 best_x_for_bbox = np.zeros((num_bboxes, 4)).astype(int)#返回與每一個gta置信度最高的anchor的座標 best_dx_for_bbox = np.zeros((num_bboxes, 4)).astype(np.float32)#返回與每一個gta置信度最高的anchor的梯度 # get the GT box coordinates, and resize to account for image resizing #對resized後的圖片的bbox進行resize gta = np.zeros((num_bboxes, 4)) for bbox_num, bbox in enumerate(img_data['bboxes']): # get the GT box coordinates, and resize to account for image resizing gta[bbox_num, 0] = bbox['x1'] * (resized_width / float(width)) gta[bbox_num, 1] = bbox['x2'] * (resized_width / float(width)) gta[bbox_num, 2] = bbox['y1'] * (resized_height / float(height)) gta[bbox_num, 3] = bbox['y2'] * (resized_height / float(height)) # rpn ground truth ##迴圈每一個框，在feature map上的位置，並進行操作。返回y_rpn_cls與y_rpn_regr for anchor_size_idx in range(len(anchor_sizes)): for anchor_ratio_idx in range(n_anchratios): anchor_x = anchor_sizes[anchor_size_idx] * anchor_ratios[anchor_ratio_idx][0] anchor_y = anchor_sizes[anchor_size_idx] * anchor_ratios[anchor_ratio_idx][1] for ix in range(output_width): # x-coordinates of the current anchor box x1_anc = downscale * (ix + 0.5) - anchor_x / 2 x2_anc = downscale * (ix + 0.5) + anchor_x / 2 # ignore boxes that go across image boundaries if x1_anc < 0 or x2_anc > resized_width: continue for jy in range(output_height): # y-coordinates of the current anchor box y1_anc = downscale * (jy + 0.5) - anchor_y / 2 y2_anc = downscale * (jy + 0.5) + anchor_y / 2 # ignore boxes that go across image boundaries if y1_anc < 0 or y2_anc > resized_height: continue # bbox_type indicates whether an anchor should be a target bbox_type = 'neg' # this is the best IOU for the (x,y) coord and the current anchor # note that this is different from the best IOU for a GT bbox best_iou_for_loc = 0.0 #對每一個anchor找與其置信度最大的gta for bbox_num in range(num_bboxes): # get IOU of the current GT box and the current anchor box curr_iou = iou([gta[bbox_num, 0], gta[bbox_num, 2], gta[bbox_num, 1], gta[bbox_num, 3]], [x1_anc, y1_anc, x2_anc, y2_anc]) # calculate the regression targets if they will be needed ##找到與gta置信度最高的anchor的梯度 if curr_iou > best_iou_for_bbox[bbox_num] or curr_iou > C.rpn_max_overlap: cx = (gta[bbox_num, 0] + gta[bbox_num, 1]) / 2.0 cy = (gta[bbox_num, 2] + gta[bbox_num, 3]) / 2.0 cxa = (x1_anc + x2_anc)/2.0 cya = (y1_anc + y2_anc)/2.0 tx = (cx - cxa) / (x2_anc - x1_anc) ty = (cy - cya) / (y2_anc - y1_anc) tw = np.log((gta[bbox_num, 1] - gta[bbox_num, 0]) / (x2_anc - x1_anc)) th = np.log((gta[bbox_num, 3] - gta[bbox_num, 2]) / (y2_anc - y1_anc)) if img_data['bboxes'][bbox_num]['class'] != 'bg': ##找到與gta置信度最高的anchor的梯度 # all GT boxes should be mapped to an anchor box, so we keep track of which anchor box was best if curr_iou > best_iou_for_bbox[bbox_num]: best_anchor_for_bbox[bbox_num] = [jy, ix, anchor_ratio_idx, anchor_size_idx] best_iou_for_bbox[bbox_num] = curr_iou best_x_for_bbox[bbox_num,:] = [x1_anc, x2_anc, y1_anc, y2_anc] best_dx_for_bbox[bbox_num,:] = [tx, ty, tw, th] # we set the anchor to positive if the IOU is >0.7 (it does not matter if there was another better box, it just indicates overlap) if curr_iou > C.rpn_max_overlap: bbox_type = 'pos' num_anchors_for_bbox[bbox_num] += 1 # we update the regression layer target if this IOU is the best for the current (x,y) and anchor position if curr_iou > best_iou_for_loc: best_iou_for_loc = curr_iou best_regr = (tx, ty, tw, th) # if the IOU is >0.3 and <0.7, it is ambiguous and no included in the objective if C.rpn_min_overlap < curr_iou < C.rpn_max_overlap: # gray zone between neg and pos if bbox_type != 'pos': bbox_type = 'neutral' # turn on or off outputs depending on IOUs if bbox_type == 'neg': y_is_box_valid[jy, ix, anchor_ratio_idx + n_anchratios * anchor_size_idx] = 1 y_rpn_overlap[jy, ix, anchor_ratio_idx + n_anchratios * anchor_size_idx] = 0 elif bbox_type == 'neutral': y_is_box_valid[jy, ix, anchor_ratio_idx + n_anchratios * anchor_size_idx] = 0 y_rpn_overlap[jy, ix, anchor_ratio_idx + n_anchratios * anchor_size_idx] = 0 elif bbox_type == 'pos': y_is_box_valid[jy, ix, anchor_ratio_idx + n_anchratios * anchor_size_idx] = 1 y_rpn_overlap[jy, ix, anchor_ratio_idx + n_anchratios * anchor_size_idx] = 1 start = 4 * (anchor_ratio_idx + n_anchratios * anchor_size_idx) y_rpn_regr[jy, ix, start:start+4] = best_regr # we ensure that every bbox has at least one positive RPN region for idx in range(num_anchors_for_bbox.shape[0]): if num_anchors_for_bbox[idx] == 0: # no box with an IOU greater than zero ... if best_anchor_for_bbox[idx, 0] == -1: continue y_is_box_valid[ best_anchor_for_bbox[idx,0], best_anchor_for_bbox[idx,1], best_anchor_for_bbox[idx,2] + n_anchratios * best_anchor_for_bbox[idx,3]] = 1 y_rpn_overlap[ best_anchor_for_bbox[idx,0], best_anchor_for_bbox[idx,1], best_anchor_for_bbox[idx,2] + n_anchratios * best_anchor_for_bbox[idx,3]] = 1 start = 4 * (best_anchor_for_bbox[idx,2] + n_anchratios * best_anchor_for_bbox[idx,3]) y_rpn_regr[ best_anchor_for_bbox[idx,0], best_anchor_for_bbox[idx,1], start:start+4] = best_dx_for_bbox[idx, :] y_rpn_overlap = np.transpose(y_rpn_overlap, (2, 0, 1)) y_rpn_overlap = np.expand_dims(y_rpn_overlap, axis=0) y_is_box_valid = np.transpose(y_is_box_valid, (2, 0, 1)) y_is_box_valid = np.expand_dims(y_is_box_valid, axis=0) y_rpn_regr = np.transpose(y_rpn_regr, (2, 0, 1)) y_rpn_regr = np.expand_dims(y_rpn_regr, axis=0) pos_locs = np.where(np.logical_and(y_rpn_overlap[0, :, :, :] == 1, y_is_box_valid[0, :, :, :] == 1)) neg_locs = np.where(np.logical_and(y_rpn_overlap[0, :, :, :] == 0, y_is_box_valid[0, :, :, :] == 1)) num_pos = len(pos_locs[0]) # one issue is that the RPN has many more negative than positive regions, so we turn off some of the negative # regions. We also limit it to 256 regions. num_regions = 256 if len(pos_locs[0]) > num_regions/2: val_locs = random.sample(range(len(pos_locs[0])), len(pos_locs[0]) - num_regions/2) y_is_box_valid[0, pos_locs[0][val_locs], pos_locs[1][val_locs], pos_locs[2][val_locs]] = 0 num_pos = num_regions/2 if len(neg_locs[0]) + num_pos > num_regions: val_locs = random.sample(range(len(neg_locs[0])), len(neg_locs[0]) - num_pos) y_is_box_valid[0, neg_locs[0][val_locs], neg_locs[1][val_locs], neg_locs[2][val_locs]] = 0 y_rpn_cls = np.concatenate([y_is_box_valid, y_rpn_overlap], axis=1) y_rpn_regr = np.concatenate([np.repeat(y_rpn_overlap, 4, axis=1), y_rpn_regr], axis=1) return np.copy(y_rpn_cls), np.copy(y_rpn_regr)
參考部落格：