def _test_one_sentence(test_arguments, sentence, rois, rcnn, this_sentence_len, info):
roi_num = rois.shape[0]
ridx = np.zeros(roi_num).astype(int)
original_predict_cls_score, predict_target_bbox = rcnn(sentence, rois, ridx)
predict_cls_score = F.softmax(original_predict_cls_score, dim=1).data.cpu().numpy() # softmax score for each row
argmax_softmax = np.argmax(predict_cls_score, axis=1)
if test_arguments.loss_weight_lambda == 0:
predict_bbox = rois
write_result(predict_bbox, argmax_softmax, np.max(predict_cls_score, axis=1),
test_arguments.result_output, info['gt_str'], None, None, 'TOI')
else:
predict_target_bbox = predict_target_bbox.data.cpu().numpy()
if test_arguments.normalize:
predict_target_bbox = denorm(predict_target_bbox, test_arguments)
if test_arguments.dx_compute_method == "left_boundary":
predict_bbox = lb_reg_to_bbox(this_sentence_len, predict_target_bbox, rois)
else:
predict_bbox = reg_to_bbox(this_sentence_len, predict_target_bbox, rois)
new_predict_bbox = np.zeros(
(predict_bbox.shape[1], predict_bbox.shape[0])) # only select the meaningful bbox regression.
for i in range(predict_bbox.shape[1]): # for n region
new_predict_bbox[i, :] = predict_bbox[:, i, argmax_softmax[i]]
write_result(int_bbox(new_predict_bbox, this_sentence_len).astype(np.int32), argmax_softmax,
np.max(predict_cls_score, axis=1),
test_arguments.result_output, info['gt_str'], None, None, 'TOI')
predict_bbox, rois, predict_cls_score = check_regression(new_predict_bbox, rois,
original_predict_cls_score.data.cpu().numpy(),
this_sentence_len)
write_result(predict_bbox.astype(np.int32), np.argmax(predict_cls_score, axis=1),
np.max(predict_cls_score, axis=1),
test_arguments.result_output, info['gt_str'], None, None, 'after check LR')
result_bbox = []
result_cls = []
drop_bbox = []
drop_cls = []
original_roi_ls = []
c_score_ls = []
if len(predict_bbox) > 0:
# if True:
argmax_softmax = np.argmax(predict_cls_score, axis=1)
# predict_bbox, argmax_softmax = select_meaningful_bbox_regression(predict_bbox, predict_cls_score)
score_indexes = score_filter(predict_cls_score, score_th=test_arguments.score_threshold)
predict_bbox = predict_bbox[score_indexes, :]
argmax_softmax = argmax_softmax[score_indexes]
predict_cls_score = predict_cls_score[score_indexes]
rois = rois[score_indexes]
write_result(predict_bbox.astype(np.int32), argmax_softmax, np.max(predict_cls_score, axis=1),
test_arguments.result_output, info['gt_str'], None, None, 'after filter')
for c in range(1, classes_num + 1):
cls_index = np.where(argmax_softmax == c)
if len(cls_index[0]) == 0: # this cls type is empty
continue
c_cls_score = predict_cls_score[cls_index[0], c]
c_bboxs = predict_bbox[cls_index[0], :]
original_roi = rois[np.where(argmax_softmax == c)[0], :]
boxes, _boxes, roi, c_score = non_maximum_suppression_fusion(c_cls_score, c_bboxs, original_roi,
iou_threshold=test_arguments.th_nms_iou,
score_threshold=test_arguments.score_threshold,
info=info)
result_bbox.extend(boxes)
drop_bbox.extend(_boxes)
original_roi_ls.extend(roi)
c_score_ls.extend(c_score)
result_cls.extend([c] * len(boxes)) # print the predict result of this sentence.
drop_cls.extend([c] * len(_boxes))
return np.array(result_bbox), np.array(result_cls), np.array(drop_bbox), np.array(drop_cls), np.array(
original_roi_ls), np.array(c_score_ls)
def _test_one_sentence(file, test_arguments, sentence, rois, rcnn, fold_index,
this_sentence_len, info):
roi_num = rois.shape[0]
ridx = np.zeros(roi_num).astype(int)
pred_cls_score, pred_tbbox = rcnn(sentence, rois, ridx)
pred_cls_score = F.softmax(
pred_cls_score, dim=1).data.cpu().numpy() # softmax score for each row
pred_tbbox = pred_tbbox.data.cpu().numpy()
if test_arguments.normalize:
pred_tbbox = denorm(pred_tbbox, fold_index, test_arguments)
if test_arguments.dx_compute_method == "left_boundary":
pred_bbox = lb_reg_to_bbox(this_sentence_len, pred_tbbox, rois)
else:
pred_bbox = reg_to_bbox(this_sentence_len, pred_tbbox, rois)
original_pred_bbox = pred_bbox.copy()
pred_bbox, argmax_softmax = select_meaningful_bbox_regression(
pred_bbox, pred_cls_score)
# rs =
output_bbox = pred_bbox.T.copy()
output_result_cls = np.argmax(pred_cls_score, axis=1).copy()
int_bbox(output_bbox, len(info["gt_str"]))
if test_arguments.output_flow:
output_file_result(file, output_bbox, output_result_cls, rois, info,
np.max(pred_cls_score, axis=1))
# if test_arguments.output_flow:
# output_detect_result(result_bbox, result_cls, original_rois, info, scores)
# pred bbox shape is 2 * n_roi
result_bbox = []
result_cls = []
drop_bbox = []
drop_cls = []
original_roi_ls = []
c_score_ls = []
for c in range(1, classes_num + 1):
cls_index = np.where(argmax_softmax == c)
if len(cls_index[0]) == 0: # this cls type is empty
continue
c_cls_score = pred_cls_score[cls_index[0], c]
c_bboxs = pred_bbox[:, cls_index[0]].T
original_roi = rois[np.where(argmax_softmax == c)[0], :]
boxes, _boxes, roi, c_score = non_maximum_suppression(
c_cls_score,
c_bboxs,
original_roi,
iou_threshold=test_arguments.th_nms_iou,
score_threshold=test_arguments.score_threshold,
info=info)
result_bbox.extend(boxes)
drop_bbox.extend(_boxes)
original_roi_ls.extend(roi)
c_score_ls.extend(c_score)
result_cls.extend(
[c] * len(boxes)) # print the predict result of this sentence.
drop_cls.extend([c] * len(_boxes))
return np.array(result_bbox), np.array(result_cls), np.array(
drop_bbox), np.array(drop_cls), np.array(original_roi_ls), np.array(
c_score_ls)
def _test_one_sentence(file_before, test_arguments, sentence, rois, rcnn, fold_index, this_sentence_len,
info):
roi_num = rois.shape[0]
ridx = np.zeros(roi_num).astype(int)
if roi_num != 0: # 候选框数量不为0
original_pred_cls_score, pred_tbbox = rcnn(sentence, rois, ridx)
pred_cls_score = F.softmax(original_pred_cls_score, dim=1).data.cpu().numpy() # softmax score for each row
argmax_softmax = np.argmax(pred_cls_score, axis=1) # 预测类型
if test_arguments.loss_weight_lambda == 0:
pred_bbox = rois
write_result(pred_bbox, argmax_softmax, np.max(pred_cls_score, axis=1),
test_arguments.result_output, info['gt_str'], None, None, 'TOI') # 输出TOI
else: # LR模型需要对候选框进行回归
pred_tbbox = pred_tbbox.data.cpu().numpy()
if test_arguments.normalize:
pred_tbbox = denorm(pred_tbbox, fold_index, test_arguments)
if test_arguments.dx_compute_method == "left_boundary":
pred_bbox = lb_reg_to_bbox(this_sentence_len, pred_tbbox, rois)
else:
pred_bbox = reg_to_bbox(this_sentence_len, pred_tbbox, rois)
new_pred_bbox = np.zeros(
(pred_bbox.shape[1], pred_bbox.shape[0])) # only select the meaningful bbox regression.
for i in range(pred_bbox.shape[1]): # for n region
new_pred_bbox[i, :] = pred_bbox[:, i, argmax_softmax[i]]
write_result(int_bbox(new_pred_bbox, this_sentence_len).astype(np.int32), argmax_softmax,
np.max(pred_cls_score, axis=1),
test_arguments.result_output, info['gt_str'], None, None, 'TOI') # 输出TOI
# 去除回归过大的候选框，输出结果
pred_bbox, rois, pred_cls_score = check_regression(new_pred_bbox, rois,
original_pred_cls_score.data.cpu().numpy(),
this_sentence_len, test_arguments.th_train_iou)
write_result(pred_bbox.astype(np.int32), np.argmax(pred_cls_score, axis=1), np.max(pred_cls_score, axis=1),
test_arguments.result_output, info['gt_str'], None, None, 'after check LR')
else:
pred_bbox = np.array([])
result_bbox = []
result_cls = []
drop_bbox = []
drop_cls = []
original_roi_ls = []
c_score_ls = []
if len(pred_bbox) > 0:
# if True:
argmax_softmax = np.argmax(pred_cls_score, axis=1) # 各种处理过后，重新判断预测类型
# pred_bbox, argmax_softmax = select_meaningful_bbox_regression(pred_bbox, pred_cls_score)
# filter去除得分小于s_th的候选框，输出结果
score_indexs = score_filter(pred_cls_score, score_th=test_arguments.score_threshold)
pred_bbox = pred_bbox[score_indexs, :]
argmax_softmax = argmax_softmax[score_indexs]
pred_cls_score = pred_cls_score[score_indexs]
rois = rois[score_indexs]
write_result(pred_bbox.astype(np.int32), argmax_softmax, np.max(pred_cls_score, axis=1),
test_arguments.result_output, info['gt_str'], None, None, 'after filter')
# output_bbox = pred_bbox.T.copy()
# output_result_cls = np.argmax(pred_cls_score, axis=1).copy()
# int_bbox(output_bbox, len(info["gt_str"]))
# output_file_result(file_before, output_bbox, output_result_cls, rois, info, np.max(pred_cls_score, axis=1))
# if test_arguments.output_flow:
# output_detect_result(output_bbox, output_result_cls, rois, info, np.max(pred_cls_score, axis=1))
#
# if test_arguments.output_flow:
# output_detect_result(result_bbox, result_cls, original_rois, info, scores)
# pred bbox shape is 2 * n_roi
# 按照类型进行nms： mix、length、score
for c in range(1, classes_num + 1):
cls_index = np.where(argmax_softmax == c)
if len(cls_index[0]) == 0: # this cls type is empty
continue
c_cls_score = pred_cls_score[cls_index[0], c]
c_bboxs = pred_bbox[cls_index[0], :]
original_roi = rois[np.where(argmax_softmax == c)[0], :]
if c == 1 or c == 7:
boxes, _boxes, roi, c_score = non_maximum_suppression_mix(c_cls_score, c_bboxs, original_roi,
iou_threshold=test_arguments.th_nms_iou,
score_threshold=test_arguments.score_threshold,
info=info)
else:
boxes, _boxes, roi, c_score = non_maximum_suppression_mix(c_cls_score, c_bboxs, original_roi,
iou_threshold=test_arguments.th_nms_iou,
score_threshold=test_arguments.score_threshold,
info=info)
result_bbox.extend(boxes)
drop_bbox.extend(_boxes)
original_roi_ls.extend(roi)
c_score_ls.extend(c_score)
result_cls.extend([c] * len(boxes)) # print the predict result of this sentence.
drop_cls.extend([c] * len(_boxes))
# output_file_result(file_after, result_bbox, result_cls, original_roi_ls, info, np.max(pred_cls_score, axis=1))
return np.array(result_bbox), np.array(result_cls), np.array(drop_bbox), np.array(drop_cls), np.array(
original_roi_ls), np.array(c_score_ls)
def _test_one_sentence_all_regression(test_arguments, sentence, rois, rcnn,
fold_index, this_sentence_len, info):
roi_num = rois.shape[0]
ridx = np.zeros(roi_num).astype(int)
pred_cls_score, pred_tbbox = rcnn(sentence, rois, ridx)
pred_cls_score = F.softmax(
pred_cls_score, dim=1).data.cpu().numpy() # softmax score for each row
pred_tbbox = pred_tbbox.data.cpu().numpy()
if test_arguments.normalize:
pred_tbbox = denorm(pred_tbbox, fold_index, test_arguments)
if test_arguments.dx_compute_method == "left_boundary":
pred_bbox = lb_reg_to_bbox(this_sentence_len, pred_tbbox, rois)
else:
pred_bbox = reg_to_bbox(this_sentence_len, pred_tbbox, rois)
result_bbox = []
result_cls = []
drop_bbox = []
drop_cls = []
original_roi_ls = []
c_score_ls = []
for c in range(1, classes_num + 1):
c_cls_score = pred_cls_score[:, c]
c_bboxs = pred_bbox[:, :, c].T
boxes, _boxes, roi, c_score = non_maximum_suppression_all_regression(
c_cls_score,
c_bboxs,
rois.copy(),
iou_threshold=test_arguments.th_nms_iou,
score_threshold=test_arguments.score_threshold,
info=info)
result_bbox.extend(boxes)
drop_bbox.extend(_boxes)
original_roi_ls.extend(roi)
c_score_ls.extend(c_score)
result_cls.extend(
[c] * len(boxes)) # print the predict result of this sentence.
drop_cls.extend([c] * len(_boxes))
if len(
result_cls
) == 0: # if the sentence without detecting anything!, we will lower the score criterion
lower_than_th_count[0] += 1
drop_bbox = []
drop_cls = []
for c in range(1, classes_num + 1):
c_sc = pred_cls_score[:, c]
c_bboxs = pred_bbox[:, :, c].T
boxes, _boxes, roi, c_score = non_maximum_suppression(
c_sc,
c_bboxs,
rois.copy(),
iou_threshold=test_arguments.th_nms_iou,
score_threshold=test_arguments.score_threshold / 6,
info=info)
result_bbox.extend(boxes)
drop_bbox.extend(_boxes)
original_roi_ls.extend(roi)
c_score_ls.extend(c_score)
result_cls.extend([c] * len(boxes))
drop_cls.extend([c] * len(_boxes))
# result_bbox = result_bbox[:1]
# result_cls = result_cls[:1]
# drop_bbox += result_bbox[1:]
# drop_cls += result_cls[1:]
# original_roi_ls = original_roi_ls[:1]
# c_score_ls = c_score_ls[:1]
return np.array(result_bbox), np.array(result_cls), np.array(
drop_bbox), np.array(drop_cls), np.array(original_roi_ls), np.array(
c_score_ls)