def inference(val_func, inputs, data_dict):
image = data_dict['data']
ori_shape = image.shape
if config.eval_resize == False:
resized_img, scale = image, 1
else:
resized_img, scale = dataset.resize_img_by_short_and_max_size(
image, config.eval_image_short_size, config.eval_image_max_size)
height, width = resized_img.shape[0:2]
resized_img = resized_img.astype(np.float32) - config.image_mean
resized_img = np.ascontiguousarray(resized_img[:, :, [2, 1, 0]])
im_info = np.array([[height, width, scale, ori_shape[0], ori_shape[1], 0]],
dtype=np.float32)
feed_dict = {inputs[0]: resized_img[None, :, :, :], inputs[1]: im_info}
print('fd:\n', feed_dict)
#st = time.time()
_, scores, pred_boxes, rois = val_func(feed_dict=feed_dict)
#ed = time.time()
#print(ed -st)
boxes = rois[:, 1:5] / scale
if cfg.TEST.BBOX_REG:
pred_boxes = bbox_transform_inv(boxes, pred_boxes)
pred_boxes = clip_boxes(pred_boxes, ori_shape)
pred_boxes = pred_boxes.reshape(-1, config.num_classes, 4)
result_boxes = []
for j in range(1, config.num_classes):
inds = np.where(scores[:, j] > config.test_cls_threshold)[0]
cls_scores = scores[inds, j]
cls_bboxes = pred_boxes[inds, j, :]
cls_dets = np.hstack(
(cls_bboxes, cls_scores[:, np.newaxis])).astype(np.float32,
copy=False)
keep = nms(cls_dets, config.test_nms)
cls_dets = np.array(cls_dets[keep, :], dtype=np.float, copy=False)
for i in range(cls_dets.shape[0]):
db = cls_dets[i, :]
dbox = DetBox(db[0],
db[1],
db[2] - db[0],
db[3] - db[1],
tag=config.class_names[j],
score=db[-1])
result_boxes.append(dbox)
if len(result_boxes) > config.test_max_boxes_per_image:
result_boxes = sorted(
result_boxes, reverse=True, key=lambda t_res: t_res.score) \
[:config.test_max_boxes_per_image]
result_dict = data_dict.copy()
result_dict['result_boxes'] = result_boxes
return result_dict
def inference(val_func, inputs, data_dict):
image = data_dict['data']
ori_shape = image.shape
if config.eval_resize == False:
resized_img, scale = image, 1
else:
resized_img, scale = dataset.resize_img_by_short_and_max_size(
image, config.eval_image_short_size, config.eval_image_max_size)
height, width = resized_img.shape[0:2]
resized_img = resized_img.astype(np.float32) - config.image_mean
resized_img = np.ascontiguousarray(resized_img[:, :, [2, 1, 0]])
im_info = np.array(
[[height, width, scale, ori_shape[0], ori_shape[1], 0]],
dtype=np.float32)
feed_dict = {inputs[0]: resized_img[None, :, :, :], inputs[1]: im_info}
#st = time.time()
_, scores, pred_boxes, rois = val_func(feed_dict=feed_dict)
#ed = time.time()
#print(ed -st)
boxes = rois[:, 1:5] / scale
if cfg.TEST.BBOX_REG:
pred_boxes = bbox_transform_inv(boxes, pred_boxes)
pred_boxes = clip_boxes(pred_boxes, ori_shape)
pred_boxes = pred_boxes.reshape(-1, config.num_classes, 4)
result_boxes = []
for j in range(1, config.num_classes):
inds = np.where(scores[:, j] > config.test_cls_threshold)[0]
cls_scores = scores[inds, j]
cls_bboxes = pred_boxes[inds, j, :]
cls_dets = np.hstack((cls_bboxes, cls_scores[:, np.newaxis])).astype(
np.float32, copy=False)
keep = nms(cls_dets, config.test_nms)
cls_dets = np.array(cls_dets[keep, :], dtype=np.float, copy=False)
for i in range(cls_dets.shape[0]):
db = cls_dets[i, :]
dbox = DetBox(
db[0], db[1], db[2] - db[0], db[3] - db[1],
tag=config.class_names[j], score=db[-1])
result_boxes.append(dbox)
if len(result_boxes) > config.test_max_boxes_per_image:
result_boxes = sorted(
result_boxes, reverse=True, key=lambda t_res: t_res.score) \
[:config.test_max_boxes_per_image]
result_dict = data_dict.copy()
result_dict['result_boxes'] = result_boxes
return result_dict
def get_data(path):
image = cv2.imread(path, cv2.IMREAD_COLOR)
if config.eval_resize == False:
resized_img, scale = image, 1
else:
resized_img, scale = dataset.resize_img_by_short_and_max_size(
image, config.eval_image_short_size, config.eval_image_max_size)
original_height, original_width = image.shape[0:2]
height, width = resized_img.shape[0:2]
transposed_img = np.ascontiguousarray(resized_img.transpose(
2, 0, 1)[None, :, :, :],
dtype=np.float32)
im_info = np.array([height, width, scale, original_height, original_width],
dtype=np.float32)[None, :]
return image, transposed_img, im_info
def get_data(record, device):
data = dataset.val_dataset(record)
image, gt_boxes, ID = \
data['data'], data['boxes'], data['ID']
if config.eval_resize == False:
resized_img, scale = image, 1
else:
resized_img, scale = dataset.resize_img_by_short_and_max_size(
image, config.eval_image_short_size, config.eval_image_max_size)
original_height, original_width = image.shape[0:2]
height, width = resized_img.shape[0:2]
transposed_img = np.ascontiguousarray(resized_img.transpose(
2, 0, 1)[None, :, :, :],
dtype=np.float32)
im_info = np.array([height, width, scale, original_height, original_width],
dtype=np.float32)[None, :]
return transposed_img, gt_boxes, im_info, ID
def get_image_info(image, max_size=-1, short_size=-1):
if config.eval_resize == False:
resized_img, scale = image, 1
else:
max_size = config.eval_image_max_size if max_size < 1 else max_size
short_size = config.eval_image_short_size if short_size < 1 else short_size
resized_img, scale = dataset.resize_img_by_short_and_max_size(
image, short_size, max_size)
original_height, original_width = image.shape[0:2]
height, width = resized_img.shape[0:2]
transposed_img = np.ascontiguousarray(resized_img.transpose(
2, 0, 1)[None, :, :, :],
dtype=np.float32)
im_info = np.array([height, width, scale, original_height, original_width],
dtype=np.float32)
image = torch.Tensor(transposed_img).cuda(0)
im_info = torch.Tensor(im_info[None, :]).cuda(0)
return image, im_info
