class SingleShotDetectorTest(object):
def __init__(self, configer):
self.configer = configer
self.blob_helper = BlobHelper(configer)
self.det_visualizer = DetVisualizer(configer)
self.det_parser = DetParser(configer)
self.det_model_manager = DetModelManager(configer)
self.det_data_loader = DataLoader(configer)
self.ssd_priorbox_layer = SSDPriorBoxLayer(configer)
self.ssd_target_generator = SSDTargetGenerator(configer)
self.device = torch.device(
'cpu' if self.configer.get('gpu') is None else 'cuda')
self.det_net = None
self._init_model()
def _init_model(self):
self.det_net = self.det_model_manager.object_detector()
self.det_net = RunnerHelper.load_net(self, self.det_net)
self.det_net.eval()
def __test_img(self, image_path, json_path, raw_path, vis_path):
Log.info('Image Path: {}'.format(image_path))
img = ImageHelper.read_image(
image_path,
tool=self.configer.get('data', 'image_tool'),
mode=self.configer.get('data', 'input_mode'))
ori_img_bgr = ImageHelper.get_cv2_bgr(img,
mode=self.configer.get(
'data', 'input_mode'))
inputs = self.blob_helper.make_input(img,
input_size=self.configer.get(
'test', 'input_size'),
scale=1.0)
with torch.no_grad():
feat_list, bbox, cls = self.det_net(inputs)
batch_detections = self.decode(
bbox, cls,
self.ssd_priorbox_layer(feat_list,
self.configer.get('test', 'input_size')),
self.configer, [inputs.size(3), inputs.size(2)])
json_dict = self.__get_info_tree(
batch_detections[0], ori_img_bgr,
[inputs.size(3), inputs.size(2)])
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
cv2.imwrite(vis_path, image_canvas)
cv2.imwrite(raw_path, ori_img_bgr)
Log.info('Json Path: {}'.format(json_path))
JsonHelper.save_file(json_dict, json_path)
return json_dict
@staticmethod
def decode(bbox, conf, default_boxes, configer, input_size):
loc = bbox
if configer.get('phase') != 'debug':
conf = F.softmax(conf, dim=-1)
default_boxes = default_boxes.unsqueeze(0).repeat(loc.size(0), 1,
1).to(bbox.device)
variances = [0.1, 0.2]
wh = torch.exp(loc[:, :, 2:] * variances[1]) * default_boxes[:, :, 2:]
cxcy = loc[:, :, :2] * variances[
0] * default_boxes[:, :, 2:] + default_boxes[:, :, :2]
boxes = torch.cat([cxcy - wh / 2, cxcy + wh / 2], 2) # [b, 8732,4]
batch_size, num_priors, _ = boxes.size()
boxes = boxes.unsqueeze(2).repeat(1, 1,
configer.get('data', 'num_classes'),
1)
boxes = boxes.contiguous().view(boxes.size(0), -1, 4)
# clip bounding box
boxes[:, :, 0::2] = boxes[:, :, 0::2].clamp(min=0,
max=input_size[0] - 1)
boxes[:, :, 1::2] = boxes[:, :, 1::2].clamp(min=0,
max=input_size[1] - 1)
labels = torch.Tensor([
i for i in range(configer.get('data', 'num_classes'))
]).to(boxes.device)
labels = labels.view(1, 1, -1,
1).repeat(batch_size, num_priors, 1,
1).contiguous().view(batch_size, -1, 1)
max_conf = conf.contiguous().view(batch_size, -1, 1)
# max_conf, labels = conf.max(2, keepdim=True) # [b, 8732,1]
predictions = torch.cat((boxes, max_conf.float(), labels.float()), 2)
output = [None for _ in range(len(predictions))]
for image_i, image_pred in enumerate(predictions):
ids = labels[image_i].squeeze(1).nonzero().contiguous().view(-1, )
if ids.numel() == 0:
continue
valid_preds = image_pred[ids]
_, order = valid_preds[:, 4].sort(0, descending=True)
order = order[:configer.get('nms', 'pre_nms')]
valid_preds = valid_preds[order]
valid_preds = valid_preds[
valid_preds[:, 4] > configer.get('res', 'val_conf_thre')]
if valid_preds.numel() == 0:
continue
valid_preds = DetHelper.cls_nms(
valid_preds[:, :6],
labels=valid_preds[:, 5],
max_threshold=configer.get('nms', 'max_threshold'),
cls_keep_num=configer.get('res', 'cls_keep_num'))
_, order = valid_preds[:, 4].sort(0, descending=True)
order = order[:configer.get('res', 'max_per_image')]
output[image_i] = valid_preds[order]
return output
def __get_info_tree(self, detections, image_raw, input_size):
height, width, _ = image_raw.shape
in_width, in_height = input_size
json_dict = dict()
object_list = list()
if detections is not None:
for x1, y1, x2, y2, conf, cls_pred in detections:
object_dict = dict()
xmin = x1.cpu().item() / in_width * width
ymin = y1.cpu().item() / in_height * height
xmax = x2.cpu().item() / in_width * width
ymax = y2.cpu().item() / in_height * height
object_dict['bbox'] = [xmin, ymin, xmax, ymax]
object_dict['label'] = int(cls_pred.cpu().item()) - 1
object_dict['score'] = float('%.2f' % conf.cpu().item())
object_list.append(object_dict)
json_dict['objects'] = object_list
return json_dict
def debug(self, vis_dir):
count = 0
for i, data_dict in enumerate(self.det_data_loader.get_trainloader()):
inputs = data_dict['img']
batch_gt_bboxes = data_dict['bboxes']
batch_gt_labels = data_dict['labels']
input_size = [inputs.size(3), inputs.size(2)]
feat_list = list()
for stride in self.configer.get('network', 'stride_list'):
feat_list.append(
torch.zeros((inputs.size(0), 1, input_size[1] // stride,
input_size[0] // stride)))
bboxes, labels = self.ssd_target_generator(feat_list,
batch_gt_bboxes,
batch_gt_labels,
input_size)
eye_matrix = torch.eye(self.configer.get('data', 'num_classes'))
labels_target = eye_matrix[labels.view(-1)].view(
inputs.size(0), -1, self.configer.get('data', 'num_classes'))
batch_detections = self.decode(
bboxes, labels_target,
self.ssd_priorbox_layer(feat_list, input_size), self.configer,
input_size)
for j in range(inputs.size(0)):
count = count + 1
if count > 20:
exit(1)
ori_img_bgr = self.blob_helper.tensor2bgr(inputs[j])
self.det_visualizer.vis_default_bboxes(
ori_img_bgr,
self.ssd_priorbox_layer(feat_list, input_size), labels[j])
json_dict = self.__get_info_tree(batch_detections[j],
ori_img_bgr, input_size)
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
cv2.imwrite(
os.path.join(vis_dir, '{}_{}_vis.png'.format(i, j)),
image_canvas)
cv2.imshow('main', image_canvas)
cv2.waitKey()
class FCNSegmentorTest(object):
def __init__(self, configer):
self.configer = configer
self.blob_helper = BlobHelper(configer)
self.seg_visualizer = SegVisualizer(configer)
self.seg_parser = SegParser(configer)
self.seg_model_manager = SegModelManager(configer)
self.seg_data_loader = DataLoader(configer)
self.device = torch.device('cpu' if self.configer.get('gpu') is None else 'cuda')
self.seg_net = None
self._init_model()
def _init_model(self):
self.seg_net = self.seg_model_manager.semantic_segmentor()
self.seg_net = RunnerHelper.load_net(self, self.seg_net)
self.seg_net.eval()
def _get_blob(self, ori_image, scale=None):
assert scale is not None
image = None
if self.configer.exists('test', 'input_size'):
image = self.blob_helper.make_input(image=ori_image,
input_size=self.configer.get('test', 'input_size'),
scale=scale)
elif self.configer.exists('test', 'min_side_length') and not self.configer.exists('test', 'max_side_length'):
image = self.blob_helper.make_input(image=ori_image,
min_side_length=self.configer.get('test', 'min_side_length'),
scale=scale)
elif not self.configer.exists('test', 'min_side_length') and self.configer.exists('test', 'max_side_length'):
image = self.blob_helper.make_input(image=ori_image,
max_side_length=self.configer.get('test', 'max_side_length'),
scale=scale)
elif self.configer.exists('test', 'min_side_length') and self.configer.exists('test', 'max_side_length'):
image = self.blob_helper.make_input(image=ori_image,
min_side_length=self.configer.get('test', 'min_side_length'),
max_side_length=self.configer.get('test', 'max_side_length'),
scale=scale)
else:
Log.error('Test setting error')
exit(1)
b, c, h, w = image.size()
border_hw = [h, w]
if self.configer.exists('test', 'fit_stride'):
stride = self.configer.get('test', 'fit_stride')
pad_w = 0 if (w % stride == 0) else stride - (w % stride) # right
pad_h = 0 if (h % stride == 0) else stride - (h % stride) # down
expand_image = torch.zeros((b, c, h + pad_h, w + pad_w)).to(image.device)
expand_image[:, :, 0:h, 0:w] = image
image = expand_image
return image, border_hw
def test_img(self, image_path, label_path, vis_path, raw_path):
Log.info('Image Path: {}'.format(image_path))
ori_image = ImageHelper.read_image(image_path,
tool=self.configer.get('data', 'image_tool'),
mode=self.configer.get('data', 'input_mode'))
total_logits = None
if self.configer.get('test', 'mode') == 'ss_test':
total_logits = self.ss_test(ori_image)
elif self.configer.get('test', 'mode') == 'sscrop_test':
total_logits = self.sscrop_test(ori_image)
elif self.configer.get('test', 'mode') == 'ms_test':
total_logits = self.ms_test(ori_image)
elif self.configer.get('test', 'mode') == 'mscrop_test':
total_logits = self.mscrop_test(ori_image)
else:
Log.error('Invalid test mode:{}'.format(self.configer.get('test', 'mode')))
exit(1)
label_map = np.argmax(total_logits, axis=-1)
label_img = np.array(label_map, dtype=np.uint8)
ori_img_bgr = ImageHelper.get_cv2_bgr(ori_image, mode=self.configer.get('data', 'input_mode'))
image_canvas = self.seg_parser.colorize(label_img, image_canvas=ori_img_bgr)
ImageHelper.save(image_canvas, save_path=vis_path)
ImageHelper.save(ori_image, save_path=raw_path)
if self.configer.exists('data', 'label_list'):
label_img = self.__relabel(label_img)
if self.configer.exists('data', 'reduce_zero_label') and self.configer.get('data', 'reduce_zero_label'):
label_img = label_img + 1
label_img = label_img.astype(np.uint8)
label_img = Image.fromarray(label_img, 'P')
Log.info('Label Path: {}'.format(label_path))
ImageHelper.save(label_img, label_path)
def ss_test(self, ori_image):
ori_width, ori_height = ImageHelper.get_size(ori_image)
total_logits = np.zeros((ori_height, ori_width, self.configer.get('data', 'num_classes')), np.float32)
image, border_hw = self._get_blob(ori_image, scale=1.0)
results = self._predict(image)
results = cv2.resize(results[:border_hw[0], :border_hw[1]],
(ori_width, ori_height), interpolation=cv2.INTER_CUBIC)
total_logits += results
return total_logits
def sscrop_test(self, ori_image):
ori_width, ori_height = ImageHelper.get_size(ori_image)
total_logits = np.zeros((ori_height, ori_width, self.configer.get('data', 'num_classes')), np.float32)
image, _ = self._get_blob(ori_image, scale=1.0)
crop_size = self.configer.get('test', 'crop_size')
if image.size()[3] > crop_size[0] and image.size()[2] > crop_size[1]:
results = self._crop_predict(image, crop_size)
else:
results = self._predict(image)
results = cv2.resize(results, (ori_width, ori_height), interpolation=cv2.INTER_CUBIC)
total_logits += results
return total_logits
def mscrop_test(self, ori_image):
ori_width, ori_height = ImageHelper.get_size(ori_image)
total_logits = np.zeros((ori_height, ori_width, self.configer.get('data', 'num_classes')), np.float32)
for scale in self.configer.get('test', 'scale_search'):
image, _ = self._get_blob(ori_image, scale=scale)
crop_size = self.configer.get('test', 'crop_size')
if image.size()[3] > crop_size[0] and image.size()[2] > crop_size[1]:
results = self._crop_predict(image, crop_size)
else:
results = self._predict(image)
results = cv2.resize(results, (ori_width, ori_height), interpolation=cv2.INTER_CUBIC)
total_logits += results
return total_logits
def ms_test(self, ori_image):
ori_width, ori_height = ImageHelper.get_size(ori_image)
total_logits = np.zeros((ori_height, ori_width, self.configer.get('data', 'num_classes')), np.float32)
for scale in self.configer.get('test', 'scale_search'):
image, border_hw = self._get_blob(ori_image, scale=scale)
results = self._predict(image)
results = cv2.resize(results[:border_hw[0], :border_hw[1]],
(ori_width, ori_height), interpolation=cv2.INTER_CUBIC)
total_logits += results
if self.configer.get('data', 'image_tool') == 'cv2':
mirror_image = cv2.flip(ori_image, 1)
else:
mirror_image = ori_image.transpose(Image.FLIP_LEFT_RIGHT)
image, border_hw = self._get_blob(mirror_image, scale=1.0)
results = self._predict(image)
results = results[:border_hw[0], :border_hw[1]]
results = cv2.resize(results[:, ::-1], (ori_width, ori_height), interpolation=cv2.INTER_CUBIC)
total_logits += results
return total_logits
def _crop_predict(self, image, crop_size):
height, width = image.size()[2:]
np_image = image.squeeze(0).permute(1, 2, 0).cpu().numpy()
height_starts = self._decide_intersection(height, crop_size[1])
width_starts = self._decide_intersection(width, crop_size[0])
split_crops = []
for height in height_starts:
for width in width_starts:
image_crop = np_image[height:height + crop_size[1], width:width + crop_size[0]]
split_crops.append(image_crop[np.newaxis, :])
split_crops = np.concatenate(split_crops, axis=0) # (n, crop_image_size, crop_image_size, 3)
inputs = torch.from_numpy(split_crops).permute(0, 3, 1, 2).to(self.device)
with torch.no_grad():
results = self.seg_net.forward(inputs)
results = results[-1].permute(0, 2, 3, 1).cpu().numpy()
reassemble = np.zeros((np_image.shape[0], np_image.shape[1], results.shape[-1]), np.float32)
index = 0
for height in height_starts:
for width in width_starts:
reassemble[height:height+crop_size[1], width:width+crop_size[0]] += results[index]
index += 1
return reassemble
def _decide_intersection(self, total_length, crop_length):
stride = int(crop_length * self.configer.get('test', 'crop_stride_ratio')) # set the stride as the paper do
times = (total_length - crop_length) // stride + 1
cropped_starting = []
for i in range(times):
cropped_starting.append(stride*i)
if total_length - cropped_starting[-1] > crop_length:
cropped_starting.append(total_length - crop_length) # must cover the total image
return cropped_starting
def _predict(self, inputs):
with torch.no_grad():
results = self.seg_net.forward(inputs)
results = results[-1].squeeze(0).permute(1, 2, 0).cpu().numpy()
return results
def __relabel(self, label_map):
height, width = label_map.shape
label_dst = np.zeros((height, width), dtype=np.uint8)
for i in range(self.configer.get('data', 'num_classes')):
label_dst[label_map == i] = self.configer.get('data', 'label_list')[i]
label_dst = np.array(label_dst, dtype=np.uint8)
return label_dst
def debug(self, vis_dir):
count = 0
for i, data_dict in enumerate(self.seg_data_loader.get_trainloader()):
inputs = data_dict['img']
targets = data_dict['labelmap']
for j in range(inputs.size(0)):
count = count + 1
if count > 20:
exit(1)
image_bgr = self.blob_helper.tensor2bgr(inputs[j])
label_map = targets[j].numpy()
image_canvas = self.seg_parser.colorize(label_map, image_canvas=image_bgr)
cv2.imwrite(os.path.join(vis_dir, '{}_{}_vis.png'.format(i, j)), image_canvas)
cv2.imshow('main', image_canvas)
cv2.waitKey()
class YOLOv3Test(object):
def __init__(self, configer):
self.configer = configer
self.blob_helper = BlobHelper(configer)
self.det_visualizer = DetVisualizer(configer)
self.det_parser = DetParser(configer)
self.det_model_manager = ModelManager(configer)
self.det_data_loader = DataLoader(configer)
self.yolo_target_generator = YOLOTargetGenerator(configer)
self.yolo_detection_layer = YOLODetectionLayer(configer)
self.device = torch.device(
'cpu' if self.configer.get('gpu') is None else 'cuda')
self.det_net = None
self._init_model()
def _init_model(self):
self.det_net = self.det_model_manager.object_detector()
self.det_net = RunnerHelper.load_net(self, self.det_net)
self.det_net.eval()
def __test_img(self, image_path, json_path, raw_path, vis_path):
Log.info('Image Path: {}'.format(image_path))
img = ImageHelper.read_image(
image_path,
tool=self.configer.get('data', 'image_tool'),
mode=self.configer.get('data', 'input_mode'))
ori_img_bgr = ImageHelper.get_cv2_bgr(img,
mode=self.configer.get(
'data', 'input_mode'))
inputs = self.blob_helper.make_input(img,
input_size=self.configer.get(
'data', 'input_size'),
scale=1.0)
with torch.no_grad():
inputs = inputs.unsqueeze(0).to(self.device)
_, _, detections = self.det_net(inputs)
batch_detections = self.decode(detections, self.configer)
json_dict = self.__get_info_tree(batch_detections[0], ori_img_bgr)
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
ImageHelper.save(ori_img_bgr, raw_path)
ImageHelper.save(image_canvas, vis_path)
Log.info('Json Path: {}'.format(json_path))
JsonHelper.save_file(json_dict, json_path)
return json_dict
@staticmethod
def decode(batch_pred_bboxes, configer, input_size):
box_corner = batch_pred_bboxes.new(batch_pred_bboxes.shape)
box_corner[:, :,
0] = batch_pred_bboxes[:, :,
0] - batch_pred_bboxes[:, :, 2] / 2
box_corner[:, :,
1] = batch_pred_bboxes[:, :,
1] - batch_pred_bboxes[:, :, 3] / 2
box_corner[:, :,
2] = batch_pred_bboxes[:, :,
0] + batch_pred_bboxes[:, :, 2] / 2
box_corner[:, :,
3] = batch_pred_bboxes[:, :,
1] + batch_pred_bboxes[:, :, 3] / 2
# clip bounding box
box_corner[:, :, 0::2] = box_corner[:, :, 0::2].clamp(min=0, max=1.0)
box_corner[:, :, 1::2] = box_corner[:, :, 1::2].clamp(min=0, max=1.0)
batch_pred_bboxes[:, :, :4] = box_corner[:, :, :4]
batch_pred_bboxes[:, :, 0::2] *= input_size[0]
batch_pred_bboxes[:, :, 1::2] *= input_size[1]
output = [None for _ in range(len(batch_pred_bboxes))]
for image_i, image_pred in enumerate(batch_pred_bboxes):
# Filter out confidence scores below threshold
conf_mask = (image_pred[:, 4] > configer.get(
'res', 'val_conf_thre')).squeeze()
image_pred = image_pred[conf_mask]
# If none are remaining => process next image
if image_pred.numel() == 0:
continue
# Get score and class with highest confidence
class_conf, class_pred = torch.max(
image_pred[:, 5:5 + configer.get('data', 'num_classes')],
1,
keepdim=True)
# Detections ordered as (x1, y1, x2, y2, obj_conf, class_conf, class_pred)
detections = torch.cat(
(image_pred[:, :5], class_conf.float(), class_pred.float()), 1)
output[image_i] = DetHelper.cls_nms(detections,
labels=class_pred.squeeze(1),
max_threshold=configer.get(
'res',
'nms')['max_threshold'])
return output
def __get_info_tree(self, detections, image_raw, input_size):
height, width, _ = image_raw.shape
json_dict = dict()
object_list = list()
if detections is not None:
for x1, y1, x2, y2, conf, cls_conf, cls_pred in detections:
object_dict = dict()
xmin = x1.cpu().item() / input_size[0] * width
ymin = y1.cpu().item() / input_size[1] * height
xmax = x2.cpu().item() / input_size[0] * width
ymax = y2.cpu().item() / input_size[1] * height
object_dict['bbox'] = [xmin, ymin, xmax, ymax]
object_dict['label'] = int(cls_pred.cpu().item())
object_dict['score'] = float('%.2f' % conf.cpu().item())
object_list.append(object_dict)
json_dict['objects'] = object_list
return json_dict
def debug(self, vis_dir):
count = 0
for i, data_dict in enumerate(self.det_data_loader.get_trainloader()):
inputs = data_dict['img']
batch_gt_bboxes = data_dict['bboxes']
batch_gt_labels = data_dict['labels']
input_size = [inputs.size(3), inputs.size(2)]
feat_list = list()
for stride in self.configer.get('network', 'stride_list'):
feat_list.append(
torch.zeros((inputs.size(0), 1, input_size[1] // stride,
input_size[0] // stride)))
targets, _, _ = self.yolo_target_generator(feat_list,
batch_gt_bboxes,
batch_gt_labels,
input_size)
targets = targets.to(self.device)
anchors_list = self.configer.get('gt', 'anchors_list')
output_list = list()
be_c = 0
for f_index, anchors in enumerate(anchors_list):
feat_stride = self.configer.get('network',
'stride_list')[f_index]
fm_size = [
int(round(border / feat_stride)) for border in input_size
]
num_c = len(anchors) * fm_size[0] * fm_size[1]
output_list.append(
targets[:, be_c:be_c + num_c].contiguous().view(
targets.size(0), len(anchors), fm_size[1], fm_size[0],
-1).permute(0, 1, 4, 2, 3).contiguous().view(
targets.size(0), -1, fm_size[1], fm_size[0]))
be_c += num_c
batch_detections = self.decode(
self.yolo_detection_layer(output_list)[2], self.configer,
input_size)
for j in range(inputs.size(0)):
count = count + 1
if count > 20:
exit(1)
ori_img_bgr = self.blob_helper.tensor2bgr(inputs[j])
json_dict = self.__get_info_tree(batch_detections[j],
ori_img_bgr, input_size)
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('vis', 'obj_threshold'))
cv2.imwrite(
os.path.join(vis_dir, '{}_{}_vis.png'.format(i, j)),
image_canvas)
cv2.imshow('main', image_canvas)
cv2.waitKey()
class FastRCNNTest(object):
def __init__(self, configer):
self.configer = configer
self.blob_helper = BlobHelper(configer)
self.det_visualizer = DetVisualizer(configer)
self.det_parser = DetParser(configer)
self.det_model_manager = DetModelManager(configer)
self.det_data_loader = DetDataLoader(configer)
self.roi_sampler = FRRoiSampleLayer(configer)
self.module_utilizer = ModuleUtilizer(configer)
self.rpn_target_generator = RPNTargetGenerator(configer)
self.fr_priorbox_layer = FRPriorBoxLayer(configer)
self.fr_roi_generator = FRRoiGenerator(configer)
self.data_transformer = DataTransformer(configer)
self.device = torch.device(
'cpu' if self.configer.get('gpu') is None else 'cuda')
self.det_net = None
self._init_model()
def _init_model(self):
self.det_net = self.det_model_manager.object_detector()
self.det_net = self.module_utilizer.load_net(self.det_net)
self.det_net.eval()
def __test_img(self, image_path, json_path, raw_path, vis_path):
Log.info('Image Path: {}'.format(image_path))
img = ImageHelper.read_image(
image_path,
tool=self.configer.get('data', 'image_tool'),
mode=self.configer.get('data', 'input_mode'))
ori_img_bgr = ImageHelper.get_cv2_bgr(img,
mode=self.configer.get(
'data', 'input_mode'))
img, scale = BoundResize()(img)
inputs = self.blob_helper.make_input(img, scale=1.0)
with torch.no_grad():
# Forward pass.
test_group = self.det_net(inputs, scale)
test_indices_and_rois, test_roi_locs, test_roi_scores, test_rois_num = test_group
batch_detections = self.decode(test_roi_locs, test_roi_scores,
test_indices_and_rois,
test_rois_num, self.configer,
ImageHelper.get_size(img))
json_dict = self.__get_info_tree(batch_detections[0],
ori_img_bgr,
scale=scale)
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('vis', 'conf_threshold'))
cv2.imwrite(vis_path, image_canvas)
cv2.imwrite(raw_path, ori_img_bgr)
Log.info('Json Path: {}'.format(json_path))
JsonHelper.save_file(json_dict, json_path)
return json_dict
@staticmethod
def decode(roi_locs, roi_scores, indices_and_rois, test_rois_num, configer,
input_size):
roi_locs = roi_locs.cpu()
roi_scores = roi_scores.cpu()
indices_and_rois = indices_and_rois.cpu()
num_classes = configer.get('data', 'num_classes')
mean = torch.Tensor(configer.get(
'roi', 'loc_normalize_mean')).repeat(num_classes)[None]
std = torch.Tensor(configer.get(
'roi', 'loc_normalize_std')).repeat(num_classes)[None]
mean = mean.to(roi_locs.device)
std = std.to(roi_locs.device)
roi_locs = (roi_locs * std + mean)
roi_locs = roi_locs.contiguous().view(-1, num_classes, 4)
# roi_locs = roi_locs[:,:, [1, 0, 3, 2]]
rois = indices_and_rois[:, 1:]
rois = rois.contiguous().view(-1, 1, 4).expand_as(roi_locs)
wh = torch.exp(roi_locs[:, :, 2:]) * (rois[:, :, 2:] - rois[:, :, :2])
cxcy = roi_locs[:, :, :2] * (rois[:, :, 2:] - rois[:, :, :2]) + (
rois[:, :, :2] + rois[:, :, 2:]) / 2
dst_bbox = torch.cat([cxcy - wh / 2, cxcy + wh / 2], 2) # [b, 8732,4]
# clip bounding box
dst_bbox[:, :, 0::2] = (dst_bbox[:, :,
0::2]).clamp(min=0,
max=input_size[0] - 1)
dst_bbox[:, :, 1::2] = (dst_bbox[:, :,
1::2]).clamp(min=0,
max=input_size[1] - 1)
if configer.get('phase') != 'debug':
cls_prob = F.softmax(roi_scores, dim=1)
else:
cls_prob = roi_scores
cls_label = torch.LongTensor([i for i in range(num_classes)])\
.contiguous().view(1, num_classes).repeat(indices_and_rois.size(0), 1)
output = [None for _ in range(test_rois_num.size(0))]
start_index = 0
for i in range(test_rois_num.size(0)):
# batch_index = (indices_and_rois[:, 0] == i).nonzero().contiguous().view(-1,)
# tmp_dst_bbox = dst_bbox[batch_index]
# tmp_cls_prob = cls_prob[batch_index]
# tmp_cls_label = cls_label[batch_index]
tmp_dst_bbox = dst_bbox[start_index:start_index + test_rois_num[i]]
tmp_cls_prob = cls_prob[start_index:start_index + test_rois_num[i]]
tmp_cls_label = cls_label[start_index:start_index +
test_rois_num[i]]
start_index += test_rois_num[i]
mask = (tmp_cls_prob > configer.get(
'vis', 'conf_threshold')) & (tmp_cls_label > 0)
tmp_dst_bbox = tmp_dst_bbox[mask].contiguous().view(-1, 4)
if tmp_dst_bbox.numel() == 0:
continue
tmp_cls_prob = tmp_cls_prob[mask].contiguous().view(
-1, ).unsqueeze(1)
tmp_cls_label = tmp_cls_label[mask].contiguous().view(
-1, ).unsqueeze(1)
valid_preds = torch.cat(
(tmp_dst_bbox, tmp_cls_prob.float(), tmp_cls_label.float()), 1)
keep = DetHelper.cls_nms(valid_preds[:, :4],
scores=valid_preds[:, 4],
labels=valid_preds[:, 5],
nms_threshold=configer.get(
'nms', 'overlap_threshold'),
iou_mode=configer.get('nms', 'mode'))
output[i] = valid_preds[keep]
return output
def __make_tensor(self, gt_bboxes, gt_labels):
len_arr = [gt_labels[i].numel() for i in range(len(gt_bboxes))]
batch_maxlen = max(max(len_arr), 1)
target_bboxes = torch.zeros((len(gt_bboxes), batch_maxlen, 4)).float()
target_labels = torch.zeros((len(gt_bboxes), batch_maxlen)).long()
for i in range(len(gt_bboxes)):
target_bboxes[i, :len_arr[i], :] = gt_bboxes[i]
target_labels[i, :len_arr[i]] = gt_labels[i]
target_bboxes_num = torch.Tensor(len_arr).long()
return target_bboxes, target_bboxes_num, target_labels
def __get_info_tree(self, detections, image_raw, scale=1.0):
height, width, _ = image_raw.shape
json_dict = dict()
object_list = list()
if detections is not None:
for x1, y1, x2, y2, conf, cls_pred in detections:
object_dict = dict()
xmin = min(x1.cpu().item() / scale, width - 1)
ymin = min(y1.cpu().item() / scale, height - 1)
xmax = min(x2.cpu().item() / scale, width - 1)
ymax = min(y2.cpu().item() / scale, height - 1)
object_dict['bbox'] = [xmin, ymin, xmax, ymax]
object_dict['label'] = int(cls_pred.cpu().item()) - 1
object_dict['score'] = float('%.2f' % conf.cpu().item())
object_list.append(object_dict)
json_dict['objects'] = object_list
return json_dict
def test(self):
base_dir = os.path.join(self.configer.get('project_dir'),
'val/results/det',
self.configer.get('dataset'))
test_img = self.configer.get('test_img')
test_dir = self.configer.get('test_dir')
if test_img is None and test_dir is None:
Log.error('test_img & test_dir not exists.')
exit(1)
if test_img is not None and test_dir is not None:
Log.error('Either test_img or test_dir.')
exit(1)
if test_img is not None:
base_dir = os.path.join(base_dir, 'test_img')
filename = test_img.rstrip().split('/')[-1]
json_path = os.path.join(
base_dir, 'json',
'{}.json'.format('.'.join(filename.split('.')[:-1])))
raw_path = os.path.join(base_dir, 'raw', filename)
vis_path = os.path.join(
base_dir, 'vis',
'{}_vis.png'.format('.'.join(filename.split('.')[:-1])))
FileHelper.make_dirs(json_path, is_file=True)
FileHelper.make_dirs(raw_path, is_file=True)
FileHelper.make_dirs(vis_path, is_file=True)
self.__test_img(test_img, json_path, raw_path, vis_path)
else:
base_dir = os.path.join(base_dir, 'test_dir',
test_dir.rstrip('/').split('/')[-1])
FileHelper.make_dirs(base_dir)
for filename in FileHelper.list_dir(test_dir):
image_path = os.path.join(test_dir, filename)
json_path = os.path.join(
base_dir, 'json',
'{}.json'.format('.'.join(filename.split('.')[:-1])))
raw_path = os.path.join(base_dir, 'raw', filename)
vis_path = os.path.join(
base_dir, 'vis',
'{}_vis.png'.format('.'.join(filename.split('.')[:-1])))
FileHelper.make_dirs(json_path, is_file=True)
FileHelper.make_dirs(raw_path, is_file=True)
FileHelper.make_dirs(vis_path, is_file=True)
self.__test_img(image_path, json_path, raw_path, vis_path)
def debug(self):
base_dir = os.path.join(self.configer.get('project_dir'),
'vis/results/det',
self.configer.get('dataset'), 'debug')
if not os.path.exists(base_dir):
os.makedirs(base_dir)
count = 0
for i, data_dict in enumerate(self.det_data_loader.get_trainloader()):
img_scale = data_dict['imgscale']
inputs = data_dict['img']
batch_gt_bboxes = data_dict['bboxes']
# batch_gt_bboxes = ResizeBoxes()(inputs, data_dict['bboxes'])
batch_gt_labels = data_dict['labels']
input_size = [inputs.size(3), inputs.size(2)]
feat_list = list()
for stride in self.configer.get('rpn', 'stride_list'):
feat_list.append(
torch.zeros((inputs.size(0), 1, input_size[1] // stride,
input_size[0] // stride)))
gt_rpn_locs, gt_rpn_labels = self.rpn_target_generator(
feat_list, batch_gt_bboxes, input_size)
eye_matrix = torch.eye(2)
gt_rpn_labels[gt_rpn_labels == -1] = 0
gt_rpn_scores = eye_matrix[gt_rpn_labels.view(-1)].view(
inputs.size(0), -1, 2)
test_indices_and_rois, _ = self.fr_roi_generator(
feat_list, gt_rpn_locs, gt_rpn_scores,
self.configer.get('rpn', 'n_test_pre_nms'),
self.configer.get('rpn', 'n_test_post_nms'), input_size,
img_scale)
gt_bboxes, gt_nums, gt_labels = self.__make_tensor(
batch_gt_bboxes, batch_gt_labels)
sample_rois, gt_roi_locs, gt_roi_labels = self.roi_sampler(
test_indices_and_rois, gt_bboxes, gt_nums, gt_labels,
input_size)
self.det_visualizer.vis_rois(inputs,
sample_rois[gt_roi_labels > 0])
gt_cls_roi_locs = torch.zeros(
(gt_roi_locs.size(0), self.configer.get('data',
'num_classes'), 4))
gt_cls_roi_locs[torch.arange(0, sample_rois.size(0)).long(),
gt_roi_labels.long()] = gt_roi_locs
gt_cls_roi_locs = gt_cls_roi_locs.contiguous().view(
-1, 4 * self.configer.get('data', 'num_classes'))
eye_matrix = torch.eye(self.configer.get('data', 'num_classes'))
gt_roi_scores = eye_matrix[gt_roi_labels.view(-1)].view(
gt_roi_labels.size(0),
self.configer.get('data', 'num_classes'))
test_rois_num = torch.zeros((len(gt_bboxes), )).long()
for batch_id in range(len(gt_bboxes)):
batch_index = (
sample_rois[:, 0] == batch_id).nonzero().contiguous().view(
-1, )
test_rois_num[batch_id] = batch_index.numel()
batch_detections = FastRCNNTest.decode(gt_cls_roi_locs,
gt_roi_scores, sample_rois,
test_rois_num,
self.configer, input_size)
for j in range(inputs.size(0)):
count = count + 1
if count > 20:
exit(1)
ori_img_bgr = self.blob_helper.tensor2bgr(inputs[j])
self.det_visualizer.vis_default_bboxes(
ori_img_bgr, self.fr_priorbox_layer(feat_list, input_size),
gt_rpn_labels[j])
json_dict = self.__get_info_tree(batch_detections[j],
ori_img_bgr)
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('vis', 'conf_threshold'))
cv2.imwrite(
os.path.join(base_dir, '{}_{}_vis.png'.format(i, j)),
image_canvas)
cv2.imshow('main', image_canvas)
cv2.waitKey()
class OpenPoseTest(object):
def __init__(self, configer):
self.configer = configer
self.blob_helper = BlobHelper(configer)
self.pose_visualizer = PoseVisualizer(configer)
self.pose_parser = PoseParser(configer)
self.pose_model_manager = PoseModelManager(configer)
self.pose_data_loader = DataLoader(configer)
self.heatmap_generator = HeatmapGenerator(configer)
self.paf_generator = PafGenerator(configer)
self.device = torch.device('cpu' if self.configer.get('gpu') is None else 'cuda')
self.pose_net = None
self._init_model()
def _init_model(self):
self.pose_net = self.pose_model_manager.multi_pose_detector()
self.pose_net = RunnerHelper.load_net(self, self.pose_net)
self.pose_net.eval()
def _get_blob(self, ori_image, scale=None):
assert scale is not None
image = self.blob_helper.make_input(image=ori_image, scale=scale)
b, c, h, w = image.size()
border_hw = [h, w]
if self.configer.exists('test', 'fit_stride'):
stride = self.configer.get('test', 'fit_stride')
pad_w = 0 if (w % stride == 0) else stride - (w % stride) # right
pad_h = 0 if (h % stride == 0) else stride - (h % stride) # down
expand_image = torch.zeros((b, c, h + pad_h, w + pad_w)).to(image.device)
expand_image[:, :, 0:h, 0:w] = image
image = expand_image
return image, border_hw
def __test_img(self, image_path, json_path, raw_path, vis_path):
Log.info('Image Path: {}'.format(image_path))
ori_image = ImageHelper.read_image(image_path,
tool=self.configer.get('data', 'image_tool'),
mode=self.configer.get('data', 'input_mode'))
ori_width, ori_height = ImageHelper.get_size(ori_image)
ori_img_bgr = ImageHelper.get_cv2_bgr(ori_image, mode=self.configer.get('data', 'input_mode'))
heatmap_avg = np.zeros((ori_height, ori_width, self.configer.get('network', 'heatmap_out')))
paf_avg = np.zeros((ori_height, ori_width, self.configer.get('network', 'paf_out')))
multiplier = [scale * self.configer.get('test', 'input_size')[1] / ori_height
for scale in self.configer.get('test', 'scale_search')]
stride = self.configer.get('network', 'stride')
for i, scale in enumerate(multiplier):
image, border_hw = self._get_blob(ori_image, scale=scale)
with torch.no_grad():
paf_out_list, heatmap_out_list = self.pose_net(image)
paf_out = paf_out_list[-1]
heatmap_out = heatmap_out_list[-1]
# extract outputs, resize, and remove padding
heatmap = heatmap_out.squeeze(0).cpu().numpy().transpose(1, 2, 0)
heatmap = cv2.resize(heatmap, None, fx=stride, fy=stride, interpolation=cv2.INTER_CUBIC)
heatmap = cv2.resize(heatmap[:border_hw[0], :border_hw[1]],
(ori_width, ori_height), interpolation=cv2.INTER_CUBIC)
paf = paf_out.squeeze(0).cpu().numpy().transpose(1, 2, 0)
paf = cv2.resize(paf, None, fx=stride, fy=stride, interpolation=cv2.INTER_CUBIC)
paf = cv2.resize(paf[:border_hw[0], :border_hw[1]],
(ori_width, ori_height), interpolation=cv2.INTER_CUBIC)
heatmap_avg = heatmap_avg + heatmap / len(multiplier)
paf_avg = paf_avg + paf / len(multiplier)
all_peaks = self.__extract_heatmap_info(heatmap_avg)
special_k, connection_all = self.__extract_paf_info(ori_img_bgr, paf_avg, all_peaks)
subset, candidate = self.__get_subsets(connection_all, special_k, all_peaks)
json_dict = self.__get_info_tree(ori_img_bgr, subset, candidate)
image_canvas = self.pose_parser.draw_points(ori_img_bgr.copy(), json_dict)
image_canvas = self.pose_parser.link_points(image_canvas, json_dict)
ImageHelper.save(image_canvas, vis_path)
ImageHelper.save(ori_img_bgr, raw_path)
Log.info('Json Save Path: {}'.format(json_path))
JsonHelper.save_file(json_dict, json_path)
def __get_info_tree(self, image_raw, subset, candidate):
json_dict = dict()
height, width, _ = image_raw.shape
json_dict['image_height'] = height
json_dict['image_width'] = width
object_list = list()
for n in range(len(subset)):
if subset[n][-1] < self.configer.get('res', 'num_threshold'):
continue
if subset[n][-2] / subset[n][-1] < self.configer.get('res', 'avg_threshold'):
continue
object_dict = dict()
object_dict['kpts'] = np.zeros((self.configer.get('data', 'num_kpts'), 3)).tolist()
for j in range(self.configer.get('data', 'num_kpts')):
index = subset[n][j]
if index == -1:
object_dict['kpts'][j][0] = -1
object_dict['kpts'][j][1] = -1
object_dict['kpts'][j][2] = -1
else:
object_dict['kpts'][j][0] = candidate[index.astype(int)][0]
object_dict['kpts'][j][1] = candidate[index.astype(int)][1]
object_dict['kpts'][j][2] = 1
object_dict['score'] = subset[n][-2]
object_list.append(object_dict)
json_dict['objects'] = object_list
return json_dict
def __extract_heatmap_info(self, heatmap_avg):
all_peaks = []
peak_counter = 0
for part in range(self.configer.get('data', 'num_kpts')):
map_ori = heatmap_avg[:, :, part]
map_gau = gaussian_filter(map_ori, sigma=3)
map_left = np.zeros(map_gau.shape)
map_left[1:, :] = map_gau[:-1, :]
map_right = np.zeros(map_gau.shape)
map_right[:-1, :] = map_gau[1:, :]
map_up = np.zeros(map_gau.shape)
map_up[:, 1:] = map_gau[:, :-1]
map_down = np.zeros(map_gau.shape)
map_down[:, :-1] = map_gau[:, 1:]
peaks_binary = np.logical_and.reduce(
(map_gau >= map_left, map_gau >= map_right, map_gau >= map_up,
map_gau >= map_down, map_gau > self.configer.get('res', 'part_threshold')))
peaks = zip(np.nonzero(peaks_binary)[1], np.nonzero(peaks_binary)[0]) # note reverse
peaks = list(peaks)
'''
del_flag = [0 for i in range(len(peaks))]
for i in range(len(peaks)):
if del_flag[i] == 0:
for j in range(i+1, len(peaks)):
if max(abs(peaks[i][0] - peaks[j][0]), abs(peaks[i][1] - peaks[j][1])) <= 6:
del_flag[j] = 1
new_peaks = list()
for i in range(len(peaks)):
if del_flag[i] == 0:
new_peaks.append(peaks[i])
peaks = new_peaks
'''
peaks_with_score = [x + (map_ori[x[1], x[0]],) for x in peaks]
ids = range(peak_counter, peak_counter + len(peaks))
peaks_with_score_and_id = [peaks_with_score[i] + (ids[i],) for i in range(len(ids))]
all_peaks.append(peaks_with_score_and_id)
peak_counter += len(peaks)
return all_peaks
def __extract_paf_info(self, img_raw, paf_avg, all_peaks):
connection_all = []
special_k = []
mid_num = self.configer.get('res', 'mid_point_num')
for k in range(len(self.configer.get('details', 'limb_seq'))):
score_mid = paf_avg[:, :, [k*2, k*2+1]]
candA = all_peaks[self.configer.get('details', 'limb_seq')[k][0] - 1]
candB = all_peaks[self.configer.get('details', 'limb_seq')[k][1] - 1]
nA = len(candA)
nB = len(candB)
if nA != 0 and nB != 0:
connection_candidate = []
for i in range(nA):
for j in range(nB):
vec = np.subtract(candB[j][:2], candA[i][:2])
norm = math.sqrt(vec[0] * vec[0] + vec[1] * vec[1]) + 1e-9
vec = np.divide(vec, norm)
startend = zip(np.linspace(candA[i][0], candB[j][0], num=mid_num),
np.linspace(candA[i][1], candB[j][1], num=mid_num))
startend = list(startend)
vec_x = np.array([score_mid[int(round(startend[I][1])), int(round(startend[I][0])), 0]
for I in range(len(startend))])
vec_y = np.array([score_mid[int(round(startend[I][1])), int(round(startend[I][0])), 1]
for I in range(len(startend))])
score_midpts = np.multiply(vec_x, vec[0]) + np.multiply(vec_y, vec[1])
score_with_dist_prior = sum(score_midpts) / len(score_midpts)
score_with_dist_prior += min(0.5 * img_raw.shape[0] / norm - 1, 0)
num_positive = len(np.nonzero(score_midpts > self.configer.get('res', 'limb_threshold'))[0])
criterion1 = num_positive > int(self.configer.get('res', 'limb_pos_ratio') * len(score_midpts))
criterion2 = score_with_dist_prior > 0
if criterion1 and criterion2:
connection_candidate.append(
[i, j, score_with_dist_prior, score_with_dist_prior + candA[i][2] + candB[j][2]])
connection_candidate = sorted(connection_candidate, key=lambda x: x[2], reverse=True)
connection = np.zeros((0, 5))
for c in range(len(connection_candidate)):
i, j, s = connection_candidate[c][0:3]
if i not in connection[:, 3] and j not in connection[:, 4]:
connection = np.vstack([connection, [candA[i][3], candB[j][3], s, i, j]])
if len(connection) >= min(nA, nB):
break
connection_all.append(connection)
else:
special_k.append(k)
connection_all.append([])
return special_k, connection_all
def __get_subsets(self, connection_all, special_k, all_peaks):
# last number in each row is the total parts number of that person
# the second last number in each row is the score of the overall configuration
subset = -1 * np.ones((0, self.configer.get('data', 'num_kpts') + 2))
candidate = np.array([item for sublist in all_peaks for item in sublist])
for k in self.configer.get('details', 'mini_tree'):
if k not in special_k:
partAs = connection_all[k][:, 0]
partBs = connection_all[k][:, 1]
indexA, indexB = np.array(self.configer.get('details', 'limb_seq')[k]) - 1
for i in range(len(connection_all[k])): # = 1:size(temp,1)
found = 0
subset_idx = [-1, -1]
for j in range(len(subset)): # 1:size(subset,1):
if subset[j][indexA] == partAs[i] or subset[j][indexB] == partBs[i]:
subset_idx[found] = j
found += 1
if found == 1:
j = subset_idx[0]
if (subset[j][indexB] != partBs[i]):
subset[j][indexB] = partBs[i]
subset[j][-1] += 1
subset[j][-2] += candidate[partBs[i].astype(int), 2] + connection_all[k][i][2]
elif found == 2: # if found 2 and disjoint, merge them
j1, j2 = subset_idx
membership = ((subset[j1] >= 0).astype(int) + (subset[j2] >= 0).astype(int))[:-2]
if len(np.nonzero(membership == 2)[0]) == 0: # merge
subset[j1][:-2] += (subset[j2][:-2] + 1)
subset[j1][-2:] += subset[j2][-2:]
subset[j1][-2] += connection_all[k][i][2]
subset = np.delete(subset, j2, 0)
else: # as like found == 1
subset[j1][indexB] = partBs[i]
subset[j1][-1] += 1
subset[j1][-2] += candidate[partBs[i].astype(int), 2] + connection_all[k][i][2]
# if find no partA in the subset, create a new subset
elif not found:
row = -1 * np.ones(self.configer.get('data', 'num_kpts') + 2)
row[indexA] = partAs[i]
row[indexB] = partBs[i]
row[-1] = 2
row[-2] = sum(candidate[connection_all[k][i, :2].astype(int), 2]) + connection_all[k][i][2]
subset = np.vstack([subset, row])
return subset, candidate
def debug(self, vis_dir):
for i, data_dict in enumerate(self.pose_data_loader.get_trainloader()):
inputs = data_dict['img']
maskmap = data_dict['maskmap']
heatmap = data_dict['heatmap']
vecmap = data_dict['vecmap']
for j in range(inputs.size(0)):
count = count + 1
if count > 10:
exit(1)
Log.info(heatmap.size())
image_bgr = self.blob_helper.tensor2bgr(inputs[j])
mask_canvas = maskmap[j].repeat(3, 1, 1).numpy().transpose(1, 2, 0)
mask_canvas = (mask_canvas * 255).astype(np.uint8)
mask_canvas = cv2.resize(mask_canvas, (0, 0), fx=self.configer.get('network', 'stride'),
fy=self.configer.get('network', 'stride'), interpolation=cv2.INTER_CUBIC)
image_bgr = cv2.addWeighted(image_bgr, 0.6, mask_canvas, 0.4, 0)
heatmap_avg = heatmap[j].numpy().transpose(1, 2, 0)
heatmap_avg = cv2.resize(heatmap_avg, (0, 0), fx=self.configer.get('network', 'stride'),
fy=self.configer.get('network', 'stride'), interpolation=cv2.INTER_CUBIC)
paf_avg = vecmap[j].numpy().transpose(1, 2, 0)
paf_avg = cv2.resize(paf_avg, (0, 0), fx=self.configer.get('network', 'stride'),
fy=self.configer.get('network', 'stride'), interpolation=cv2.INTER_CUBIC)
self.pose_visualizer.vis_peaks(heatmap_avg, image_bgr)
self.pose_visualizer.vis_paf(paf_avg, image_bgr)
all_peaks = self.__extract_heatmap_info(heatmap_avg)
special_k, connection_all = self.__extract_paf_info(image_bgr, paf_avg, all_peaks)
subset, candidate = self.__get_subsets(connection_all, special_k, all_peaks)
json_dict = self.__get_info_tree(image_bgr, subset, candidate)
image_canvas = self.pose_parser.draw_points(image_bgr, json_dict)
image_canvas = self.pose_parser.link_points(image_canvas, json_dict)
cv2.imwrite(os.path.join(vis_dir, '{}_{}_vis.png'.format(i, j)), image_canvas)
cv2.imshow('main', image_canvas)
cv2.waitKey()
class ConvPoseMachineTest(object):
def __init__(self, configer):
self.configer = configer
self.blob_helper = BlobHelper(configer)
self.pose_vis = PoseVisualizer(configer)
self.pose_model_manager = ModelManager(configer)
self.pose_data_loader = DataLoader(configer)
self.device = torch.device(
'cpu' if self.configer.get('gpu') is None else 'cuda')
self.pose_net = None
self._init_model()
def _init_model(self):
self.pose_net = self.pose_model_manager.multi_pose_detector()
self.pose_net = RunnerHelper.load_net(self, self.pose_net)
self.pose_net.eval()
def __test_img(self, image_path, save_path):
Log.info('Image Path: {}'.format(image_path))
ori_image = ImageHelper.read_image(
image_path,
tool=self.configer.get('data', 'image_tool'),
mode=self.configer.get('data', 'input_mode'))
ori_width, ori_height = ImageHelper.get_size(ori_image)
ori_img_bgr = ImageHelper.get_cv2_bgr(ori_image,
mode=self.configer.get(
'data', 'input_mode'))
heatmap_avg = np.zeros(
(ori_height, ori_width, self.configer.get('network',
'heatmap_out')))
for i, scale in enumerate(self.configer.get('test', 'scale_search')):
image = self.blob_helper.make_input(ori_image,
input_size=self.configer.get(
'test', 'input_size'),
scale=scale)
with torch.no_grad():
heatmap_out_list = self.pose_net(image)
heatmap_out = heatmap_out_list[-1]
# extract outputs, resize, and remove padding
heatmap = heatmap_out.squeeze(0).cpu().numpy().transpose(
1, 2, 0)
heatmap = cv2.resize(heatmap, (ori_width, ori_height),
interpolation=cv2.INTER_CUBIC)
heatmap_avg = heatmap_avg + heatmap / len(
self.configer.get('test', 'scale_search'))
all_peaks = self.__extract_heatmap_info(heatmap_avg)
image_canvas = self.__draw_key_point(all_peaks, ori_img_bgr)
ImageHelper.save(image_canvas, save_path)
def __extract_heatmap_info(self, heatmap_avg):
all_peaks = []
for part in range(self.configer.get('network', 'heatmap_out') - 1):
map_ori = heatmap_avg[:, :, part]
map_gau = gaussian_filter(map_ori, sigma=3)
map_left = np.zeros(map_gau.shape)
map_left[1:, :] = map_gau[:-1, :]
map_right = np.zeros(map_gau.shape)
map_right[:-1, :] = map_gau[1:, :]
map_up = np.zeros(map_gau.shape)
map_up[:, 1:] = map_gau[:, :-1]
map_down = np.zeros(map_gau.shape)
map_down[:, :-1] = map_gau[:, 1:]
peaks_binary = np.logical_and.reduce(
(map_gau >= map_left, map_gau >= map_right, map_gau >= map_up,
map_gau >= map_down,
map_gau > self.configer.get('vis', 'part_threshold')))
peaks = zip(
np.nonzero(peaks_binary)[1],
np.nonzero(peaks_binary)[0]) # note reverse
peaks = list(peaks)
peaks_with_score = [x + (map_ori[x[1], x[0]], ) for x in peaks]
all_peaks.append(peaks_with_score)
return all_peaks
def __draw_key_point(self, all_peaks, img_raw):
img_canvas = img_raw.copy() # B,G,R order
for i in range(self.configer.get('network', 'heatmap_out') - 1):
for j in range(len(all_peaks[i])):
cv2.circle(img_canvas,
all_peaks[i][j][0:2],
self.configer.get('vis', 'stick_width'),
self.configer.get('details', 'color_list')[i],
thickness=-1)
return img_canvas
def debug(self, vis_dir):
for i, data_dict in enumerate(self.pose_data_loader.get_trainloader()):
inputs = data_dict['img']
heatmap = data_dict['heatmap']
for j in range(inputs.size(0)):
image_bgr = self.blob_helper.tensor2bgr(inputs[j])
heatmap_avg = heatmap[j].numpy().transpose(1, 2, 0)
heatmap_avg = cv2.resize(
heatmap_avg, (0, 0),
fx=self.configer.get('network', 'stride'),
fy=self.configer.get('network', 'stride'),
interpolation=cv2.INTER_CUBIC)
all_peaks = self.__extract_heatmap_info(heatmap_avg)
image_save = self.__draw_key_point(all_peaks, image_bgr)
cv2.imwrite(
os.path.join(vis_dir, '{}_{}_result.jpg'.format(i, j)),
image_save)
class FCClassifierTest(object):
def __init__(self, configer):
self.configer = configer
self.blob_helper = BlobHelper(configer)
self.cls_model_manager = ClsModelManager(configer)
self.cls_data_loader = ClsDataLoader(configer)
self.module_utilizer = ModuleUtilizer(configer)
self.cls_parser = ClsParser(configer)
self.device = torch.device(
'cpu' if self.configer.get('gpu') is None else 'cuda')
self.cls_net = None
if self.configer.get('dataset') == 'imagenet':
with open(
os.path.join(
self.configer.get('project_dir'),
'datasets/cls/imagenet/imagenet_class_index.json')
) as json_stream:
name_dict = json.load(json_stream)
name_seq = [
name_dict[str(i)][1]
for i in range(self.configer.get('data', 'num_classes'))
]
self.configer.add_key_value(['details', 'name_seq'], name_seq)
self._init_model()
def _init_model(self):
self.cls_net = self.cls_model_manager.image_classifier()
self.cls_net = self.module_utilizer.load_net(self.cls_net)
self.cls_net.eval()
def __test_img(self, image_path, json_path, raw_path, vis_path):
Log.info('Image Path: {}'.format(image_path))
img = ImageHelper.read_image(
image_path,
tool=self.configer.get('data', 'image_tool'),
mode=self.configer.get('data', 'input_mode'))
trans = None
if self.configer.get('dataset') == 'imagenet':
if self.configer.get('data', 'image_tool') == 'cv2':
img = Image.fromarray(img)
trans = transforms.Compose([
transforms.Scale(256),
transforms.CenterCrop(224),
])
assert trans is not None
img = trans(img)
ori_img_bgr = ImageHelper.get_cv2_bgr(img,
mode=self.configer.get(
'data', 'input_mode'))
inputs = self.blob_helper.make_input(img,
input_size=self.configer.get(
'test', 'input_size'),
scale=1.0)
with torch.no_grad():
outputs = self.cls_net(inputs)
json_dict = self.__get_info_tree(outputs, image_path)
image_canvas = self.cls_parser.draw_label(ori_img_bgr.copy(),
json_dict['label'])
cv2.imwrite(vis_path, image_canvas)
cv2.imwrite(raw_path, ori_img_bgr)
Log.info('Json Path: {}'.format(json_path))
JsonHelper.save_file(json_dict, json_path)
return json_dict
def __get_info_tree(self, outputs, image_path=None):
json_dict = dict()
if image_path is not None:
json_dict['image_path'] = image_path
topk = (1, 3, 5)
maxk = max(topk)
_, pred = outputs.topk(maxk, 1, True, True)
pred = pred.t()
for k in topk:
if k == 1:
json_dict['label'] = pred[0][0]
else:
json_dict['label_top{}'.format(k)] = pred[0][:k]
return json_dict
def test(self):
base_dir = os.path.join(self.configer.get('project_dir'),
'val/results/cls',
self.configer.get('dataset'))
test_img = self.configer.get('test_img')
test_dir = self.configer.get('test_dir')
if test_img is None and test_dir is None:
Log.error('test_img & test_dir not exists.')
exit(1)
if test_img is not None and test_dir is not None:
Log.error('Either test_img or test_dir.')
exit(1)
if test_img is not None:
base_dir = os.path.join(base_dir, 'test_img')
filename = test_img.rstrip().split('/')[-1]
json_path = os.path.join(
base_dir, 'json',
'{}.json'.format('.'.join(filename.split('.')[:-1])))
raw_path = os.path.join(base_dir, 'raw', filename)
vis_path = os.path.join(
base_dir, 'vis',
'{}_vis.png'.format('.'.join(filename.split('.')[:-1])))
FileHelper.make_dirs(json_path, is_file=True)
FileHelper.make_dirs(raw_path, is_file=True)
FileHelper.make_dirs(vis_path, is_file=True)
self.__test_img(test_img, json_path, raw_path, vis_path)
else:
base_dir = os.path.join(base_dir, 'test_dir',
test_dir.rstrip('/').split('/')[-1])
FileHelper.make_dirs(base_dir)
for filename in FileHelper.list_dir(test_dir):
image_path = os.path.join(test_dir, filename)
json_path = os.path.join(
base_dir, 'json',
'{}.json'.format('.'.join(filename.split('.')[:-1])))
raw_path = os.path.join(base_dir, 'raw', filename)
vis_path = os.path.join(
base_dir, 'vis',
'{}_vis.png'.format('.'.join(filename.split('.')[:-1])))
FileHelper.make_dirs(json_path, is_file=True)
FileHelper.make_dirs(raw_path, is_file=True)
FileHelper.make_dirs(vis_path, is_file=True)
self.__test_img(image_path, json_path, raw_path, vis_path)
def debug(self):
base_dir = os.path.join(self.configer.get('project_dir'),
'vis/results/cls',
self.configer.get('dataset'), 'debug')
if not os.path.exists(base_dir):
os.makedirs(base_dir)
count = 0
for i, data_dict in enumerate(self.cls_data_loader.get_trainloader()):
inputs = data_dict['img']
labels = data_dict['label']
eye_matrix = torch.eye(self.configer.get('data', 'num_classes'))
labels_target = eye_matrix[labels.view(-1)].view(
inputs.size(0), self.configer.get('data', 'num_classes'))
for j in range(inputs.size(0)):
count = count + 1
if count > 20:
exit(1)
ori_img_bgr = self.blob_helper.tensor2bgr(inputs[j])
json_dict = self.__get_info_tree(labels_target)
image_canvas = self.cls_parser.draw_label(
ori_img_bgr.copy(), json_dict['label'])
cv2.imwrite(
os.path.join(base_dir, '{}_{}_vis.png'.format(i, j)),
image_canvas)
cv2.imshow('main', image_canvas)
cv2.waitKey()
class FastRCNNTest(object):
def __init__(self, configer):
self.configer = configer
self.blob_helper = BlobHelper(configer)
self.det_visualizer = DetVisualizer(configer)
self.det_parser = DetParser(configer)
self.det_model_manager = DetModelManager(configer)
self.det_data_loader = DataLoader(configer)
self.roi_sampler = FRROISampler(configer)
self.rpn_target_generator = RPNTargetAssigner(configer)
self.fr_priorbox_layer = FRPriorBoxLayer(configer)
self.fr_roi_generator = FRROIGenerator(configer)
self.device = torch.device(
'cpu' if self.configer.get('gpu') is None else 'cuda')
self.det_net = None
self._init_model()
def _init_model(self):
self.det_net = self.det_model_manager.object_detector()
self.det_net = RunnerHelper.load_net(self, self.det_net)
self.det_net.eval()
def __test_img(self, image_path, json_path, raw_path, vis_path):
Log.info('Image Path: {}'.format(image_path))
image = ImageHelper.read_image(
image_path,
tool=self.configer.get('data', 'image_tool'),
mode=self.configer.get('data', 'input_mode'))
ori_img_bgr = ImageHelper.get_cv2_bgr(image,
mode=self.configer.get(
'data', 'input_mode'))
width, height = ImageHelper.get_size(image)
scale1 = self.configer.get('test', 'resize_bound')[0] / min(
width, height)
scale2 = self.configer.get('test', 'resize_bound')[1] / max(
width, height)
scale = min(scale1, scale2)
inputs = self.blob_helper.make_input(image, scale=scale)
b, c, h, w = inputs.size()
border_wh = [w, h]
if self.configer.exists('test', 'fit_stride'):
stride = self.configer.get('test', 'fit_stride')
pad_w = 0 if (w % stride == 0) else stride - (w % stride) # right
pad_h = 0 if (h % stride == 0) else stride - (h % stride) # down
expand_image = torch.zeros(
(b, c, h + pad_h, w + pad_w)).to(inputs.device)
expand_image[:, :, 0:h, 0:w] = inputs
inputs = expand_image
data_dict = dict(
img=inputs,
meta=DataContainer([[
dict(ori_img_size=ImageHelper.get_size(ori_img_bgr),
aug_img_size=border_wh,
img_scale=scale,
input_size=[inputs.size(3),
inputs.size(2)])
]],
cpu_only=True))
with torch.no_grad():
# Forward pass.
test_group = self.det_net(data_dict)
test_indices_and_rois, test_roi_locs, test_roi_scores, test_rois_num = test_group
batch_detections = self.decode(test_roi_locs, test_roi_scores,
test_indices_and_rois, test_rois_num,
self.configer,
DCHelper.tolist(data_dict['meta']))
json_dict = self.__get_info_tree(batch_detections[0],
ori_img_bgr,
scale=scale)
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
cv2.imwrite(vis_path, image_canvas)
cv2.imwrite(raw_path, ori_img_bgr)
Log.info('Json Path: {}'.format(json_path))
JsonHelper.save_file(json_dict, json_path)
return json_dict
@staticmethod
def decode(roi_locs, roi_scores, indices_and_rois, test_rois_num, configer,
metas):
indices_and_rois = indices_and_rois
num_classes = configer.get('data', 'num_classes')
mean = torch.Tensor(configer.get(
'roi', 'loc_normalize_mean')).repeat(num_classes)[None]
std = torch.Tensor(configer.get(
'roi', 'loc_normalize_std')).repeat(num_classes)[None]
mean = mean.to(roi_locs.device)
std = std.to(roi_locs.device)
roi_locs = (roi_locs * std + mean)
roi_locs = roi_locs.contiguous().view(-1, num_classes, 4)
# roi_locs = roi_locs[:,:, [1, 0, 3, 2]]
rois = indices_and_rois[:, 1:]
rois = rois.contiguous().view(-1, 1, 4).expand_as(roi_locs)
wh = torch.exp(roi_locs[:, :, 2:]) * (rois[:, :, 2:] - rois[:, :, :2])
cxcy = roi_locs[:, :, :2] * (rois[:, :, 2:] - rois[:, :, :2]) + (
rois[:, :, :2] + rois[:, :, 2:]) / 2
dst_bbox = torch.cat([cxcy - wh / 2, cxcy + wh / 2], 2) # [b, 8732,4]
if configer.get('phase') != 'debug':
cls_prob = F.softmax(roi_scores, dim=1)
else:
cls_prob = roi_scores
cls_label = torch.LongTensor([i for i in range(num_classes)])\
.contiguous().view(1, num_classes).repeat(indices_and_rois.size(0), 1).to(roi_locs.device)
output = [None for _ in range(test_rois_num.size(0))]
start_index = 0
for i in range(test_rois_num.size(0)):
# batch_index = (indices_and_rois[:, 0] == i).nonzero().contiguous().view(-1,)
# tmp_dst_bbox = dst_bbox[batch_index]
# tmp_cls_prob = cls_prob[batch_index]
# tmp_cls_label = cls_label[batch_index]
tmp_dst_bbox = dst_bbox[start_index:start_index + test_rois_num[i]]
# clip bounding box
tmp_dst_bbox[:, :, 0::2] = tmp_dst_bbox[:, :, 0::2].clamp(
min=0, max=metas[i]['border_size'][0] - 1)
tmp_dst_bbox[:, :, 1::2] = tmp_dst_bbox[:, :, 1::2].clamp(
min=0, max=metas[i]['border_size'][1] - 1)
tmp_cls_prob = cls_prob[start_index:start_index + test_rois_num[i]]
tmp_cls_label = cls_label[start_index:start_index +
test_rois_num[i]]
start_index += test_rois_num[i]
mask = (tmp_cls_prob > configer.get(
'res', 'val_conf_thre')) & (tmp_cls_label > 0)
tmp_dst_bbox = tmp_dst_bbox[mask].contiguous().view(-1, 4)
if tmp_dst_bbox.numel() == 0:
continue
tmp_cls_prob = tmp_cls_prob[mask].contiguous().view(
-1, ).unsqueeze(1)
tmp_cls_label = tmp_cls_label[mask].contiguous().view(
-1, ).unsqueeze(1)
valid_preds = torch.cat(
(tmp_dst_bbox, tmp_cls_prob.float(), tmp_cls_label.float()), 1)
output[i] = DetHelper.cls_nms(valid_preds,
labels=valid_preds[:, 5],
max_threshold=configer.get(
'nms', 'max_threshold'))
return output
def __get_info_tree(self, detections, image_raw, scale=1.0):
height, width, _ = image_raw.shape
json_dict = dict()
object_list = list()
if detections is not None:
for x1, y1, x2, y2, conf, cls_pred in detections:
object_dict = dict()
xmin = min(x1.cpu().item() / scale, width - 1)
ymin = min(y1.cpu().item() / scale, height - 1)
xmax = min(x2.cpu().item() / scale, width - 1)
ymax = min(y2.cpu().item() / scale, height - 1)
object_dict['bbox'] = [xmin, ymin, xmax, ymax]
object_dict['label'] = int(cls_pred.cpu().item()) - 1
object_dict['score'] = float('%.2f' % conf.cpu().item())
object_list.append(object_dict)
json_dict['objects'] = object_list
return json_dict
def debug(self, vis_dir):
count = 0
for i, data_dict in enumerate(self.det_data_loader.get_trainloader()):
feat_list = list()
input_size = data_dict['meta'][0]['input_size']
for stride in self.configer.get('rpn', 'stride_list'):
feat_list.append(
torch.zeros(
(data_dict['img'].size(0), 1, input_size[1] // stride,
input_size[0] // stride)))
gt_rpn_locs, gt_rpn_labels = self.rpn_target_generator(
feat_list, data_dict['bboxes'], data_dict['meta'])
eye_matrix = torch.eye(2)
gt_rpn_labels[gt_rpn_labels == -1] = 0
gt_rpn_scores = eye_matrix[gt_rpn_labels.view(-1)].view(
data_dict['img'].size(0), -1, 2)
test_indices_and_rois, _ = self.fr_roi_generator(
feat_list, gt_rpn_locs, gt_rpn_scores,
self.configer.get('rpn', 'n_test_pre_nms'),
self.configer.get('rpn', 'n_test_post_nms'), data_dict['meta'])
sample_rois, gt_roi_locs, gt_roi_labels = self.roi_sampler(
test_indices_and_rois, data_dict['bboxes'],
data_dict['labels'], data_dict['meta'])
self.det_visualizer.vis_rois(data_dict['img'],
sample_rois[gt_roi_labels > 0])
gt_cls_roi_locs = torch.zeros(
(gt_roi_locs.size(0), self.configer.get('data',
'num_classes'), 4))
gt_cls_roi_locs[torch.arange(0, sample_rois.size(0)).long(),
gt_roi_labels.long()] = gt_roi_locs
gt_cls_roi_locs = gt_cls_roi_locs.contiguous().view(
-1, 4 * self.configer.get('data', 'num_classes'))
eye_matrix = torch.eye(self.configer.get('data', 'num_classes'))
gt_roi_scores = eye_matrix[gt_roi_labels.view(-1)].view(
gt_roi_labels.size(0),
self.configer.get('data', 'num_classes'))
test_rois_num = torch.zeros((len(data_dict['bboxes']), )).long()
for batch_id in range(len(data_dict['bboxes'])):
batch_index = (
sample_rois[:, 0] == batch_id).nonzero().contiguous().view(
-1, )
test_rois_num[batch_id] = batch_index.numel()
batch_detections = FastRCNNTest.decode(gt_cls_roi_locs,
gt_roi_scores, sample_rois,
test_rois_num,
self.configer,
data_dict['meta'])
for j in range(data_dict['img'].size(0)):
count = count + 1
if count > 20:
exit(1)
ori_img_bgr = self.blob_helper.tensor2bgr(data_dict['img'][j])
self.det_visualizer.vis_default_bboxes(
ori_img_bgr, self.fr_priorbox_layer(feat_list, input_size),
gt_rpn_labels[j])
json_dict = self.__get_info_tree(batch_detections[j],
ori_img_bgr)
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
cv2.imwrite(
os.path.join(vis_dir, '{}_{}_vis.png'.format(i, j)),
image_canvas)
cv2.imshow('main', image_canvas)
cv2.waitKey()
class FCNSegmentorTest(object):
def __init__(self, configer):
self.configer = configer
self.blob_helper = BlobHelper(configer)
self.seg_visualizer = SegVisualizer(configer)
self.seg_parser = SegParser(configer)
self.seg_model_manager = SegModelManager(configer)
self.seg_data_loader = SegDataLoader(configer)
self.module_utilizer = ModuleUtilizer(configer)
self.data_transformer = DataTransformer(configer)
self.device = torch.device('cpu' if self.configer.get('gpu') is None else 'cuda')
self.seg_net = None
self._init_model()
def _init_model(self):
self.seg_net = self.seg_model_manager.semantic_segmentor()
self.seg_net = self.module_utilizer.load_net(self.seg_net)
self.seg_net.eval()
def __test_img(self, image_path, label_path, vis_path, raw_path):
Log.info('Image Path: {}'.format(image_path))
ori_image = ImageHelper.read_image(image_path,
tool=self.configer.get('data', 'image_tool'),
mode=self.configer.get('data', 'input_mode'))
ori_width, ori_height = ImageHelper.get_size(ori_image)
total_logits = np.zeros((ori_height, ori_width, self.configer.get('data', 'num_classes')), np.float32)
for scale in self.configer.get('test', 'scale_search'):
image = self.blob_helper.make_input(image=ori_image,
input_size=self.configer.get('test', 'input_size'),
scale=scale)
if self.configer.get('test', 'crop_test'):
crop_size = self.configer.get('test', 'crop_size')
if image.size()[3] > crop_size[0] and image.size()[2] > crop_size[1]:
results = self._crop_predict(image, crop_size)
else:
results = self._predict(image)
else:
results = self._predict(image)
results = cv2.resize(results, (ori_width, ori_height), interpolation=cv2.INTER_LINEAR)
total_logits += results
if self.configer.get('test', 'mirror'):
if self.configer.get('data', 'image_tool') == 'cv2':
image = cv2.flip(ori_image, 1)
else:
image = ori_image.transpose(Image.FLIP_LEFT_RIGHT)
image = self.blob_helper.make_input(image, input_size=self.configer.get('test', 'input_size'), scale=1.0)
if self.configer.get('test', 'crop_test'):
crop_size = self.configer.get('test', 'crop_size')
if image.size()[3] > crop_size[0] and image.size()[2] > crop_size[1]:
results = self._crop_predict(image, crop_size)
else:
results = self._predict(image)
else:
results = self._predict(image)
results = cv2.resize(results[:, ::-1], (ori_width, ori_height), interpolation=cv2.INTER_LINEAR)
total_logits += results
label_map = np.argmax(total_logits, axis=-1)
label_img = np.array(label_map, dtype=np.uint8)
image_bgr = cv2.cvtColor(np.array(ori_image), cv2.COLOR_RGB2BGR)
image_canvas = self.seg_parser.colorize(label_img, image_canvas=image_bgr)
ImageHelper.save(image_canvas, save_path=vis_path)
ImageHelper.save(ori_image, save_path=raw_path)
if not self.configer.is_empty('data', 'label_list'):
label_img = self.__relabel(label_img)
label_img = Image.fromarray(label_img, 'P')
Log.info('Label Path: {}'.format(label_path))
ImageHelper.save(label_img, label_path)
def _crop_predict(self, image, crop_size):
height, width = image.size()[2:]
np_image = image.squeeze(0).permute(1, 2, 0).cpu().numpy()
height_starts = self._decide_intersection(height, crop_size[1])
width_starts = self._decide_intersection(width, crop_size[0])
split_crops = []
for height in height_starts:
for width in width_starts:
image_crop = np_image[height:height + crop_size[1], width:width + crop_size[0]]
split_crops.append(image_crop[np.newaxis, :])
split_crops = np.concatenate(split_crops, axis=0) # (n, crop_image_size, crop_image_size, 3)
inputs = torch.from_numpy(split_crops).permute(0, 3, 1, 2).to(self.device)
with torch.no_grad():
results = self.seg_net.forward(inputs)
results = results[0].permute(0, 2, 3, 1).cpu().numpy()
reassemble = np.zeros((np_image.shape[0], np_image.shape[1], results.shape[-1]), np.float32)
index = 0
for height in height_starts:
for width in width_starts:
reassemble[height:height+crop_size[1], width:width+crop_size[0]] += results[index]
index += 1
return reassemble
def _decide_intersection(self, total_length, crop_length):
stride = int(crop_length * self.configer.get('test', 'crop_stride_ratio')) # set the stride as the paper do
times = (total_length - crop_length) // stride + 1
cropped_starting = []
for i in range(times):
cropped_starting.append(stride*i)
if total_length - cropped_starting[-1] > crop_length:
cropped_starting.append(total_length - crop_length) # must cover the total image
return cropped_starting
def _predict(self, inputs):
with torch.no_grad():
results = self.seg_net.forward(inputs)
results = results[0].squeeze().permute(1, 2, 0).cpu().numpy()
return results
def __relabel(self, label_map):
height, width = label_map.shape
label_dst = np.zeros((height, width), dtype=np.uint8)
for i in range(self.configer.get('data', 'num_classes')):
label_dst[label_map == i] = self.configer.get('data', 'label_list')[i]
label_dst = np.array(label_dst, dtype=np.uint8)
return label_dst
def test(self):
base_dir = os.path.join(self.configer.get('project_dir'),
'val/results/seg', self.configer.get('dataset'))
test_img = self.configer.get('test_img')
test_dir = self.configer.get('test_dir')
if test_img is None and test_dir is None:
Log.error('test_img & test_dir not exists.')
exit(1)
if test_img is not None and test_dir is not None:
Log.error('Either test_img or test_dir.')
exit(1)
if test_img is not None:
base_dir = os.path.join(base_dir, 'test_img')
filename = test_img.rstrip().split('/')[-1]
label_path = os.path.join(base_dir, 'label', '{}.png'.format('.'.join(filename.split('.')[:-1])))
raw_path = os.path.join(base_dir, 'raw', filename)
vis_path = os.path.join(base_dir, 'vis', '{}_vis.png'.format('.'.join(filename.split('.')[:-1])))
FileHelper.make_dirs(label_path, is_file=True)
FileHelper.make_dirs(raw_path, is_file=True)
FileHelper.make_dirs(vis_path, is_file=True)
self.__test_img(test_img, label_path, vis_path, raw_path)
else:
base_dir = os.path.join(base_dir, 'test_dir', test_dir.rstrip('/').split('/')[-1])
FileHelper.make_dirs(base_dir)
for filename in FileHelper.list_dir(test_dir):
image_path = os.path.join(test_dir, filename)
label_path = os.path.join(base_dir, 'label', '{}.png'.format('.'.join(filename.split('.')[:-1])))
raw_path = os.path.join(base_dir, 'raw', filename)
vis_path = os.path.join(base_dir, 'vis', '{}_vis.png'.format('.'.join(filename.split('.')[:-1])))
FileHelper.make_dirs(label_path, is_file=True)
FileHelper.make_dirs(raw_path, is_file=True)
FileHelper.make_dirs(vis_path, is_file=True)
self.__test_img(image_path, label_path, vis_path, raw_path)
def debug(self):
base_dir = os.path.join(self.configer.get('project_dir'),
'vis/results/seg', self.configer.get('dataset'), 'debug')
if not os.path.exists(base_dir):
os.makedirs(base_dir)
count = 0
for i, data_dict in enumerate(self.seg_data_loader.get_trainloader()):
inputs = data_dict['img']
targets = data_dict['labelmap']
for j in range(inputs.size(0)):
count = count + 1
if count > 20:
exit(1)
image_bgr = self.blob_helper.tensor2bgr(inputs[j])
label_map = targets[j].numpy()
image_canvas = self.seg_parser.colorize(label_map, image_canvas=image_bgr)
cv2.imwrite(os.path.join(base_dir, '{}_{}_vis.png'.format(i, j)), image_canvas)
cv2.imshow('main', image_canvas)
cv2.waitKey()
class FCClassifierTest(object):
def __init__(self, configer):
self.configer = configer
self.blob_helper = BlobHelper(configer)
self.cls_model_manager = ClsModelManager(configer)
self.cls_data_loader = DataLoader(configer)
self.cls_parser = ClsParser(configer)
self.device = torch.device(
'cpu' if self.configer.get('gpu') is None else 'cuda')
self.cls_net = None
if self.configer.get('dataset') == 'imagenet':
with open(
os.path.join(
self.configer.get('project_dir'),
'datasets/cls/imagenet/imagenet_class_index.json')
) as json_stream:
name_dict = json.load(json_stream)
name_seq = [
name_dict[str(i)][1]
for i in range(self.configer.get('data', 'num_classes'))
]
self.configer.add(['details', 'name_seq'], name_seq)
self._init_model()
def _init_model(self):
self.cls_net = self.cls_model_manager.image_classifier()
self.cls_net = RunnerHelper.load_net(self, self.cls_net)
self.cls_net.eval()
def __test_img(self, image_path, json_path, raw_path, vis_path):
Log.info('Image Path: {}'.format(image_path))
img = ImageHelper.read_image(
image_path,
tool=self.configer.get('data', 'image_tool'),
mode=self.configer.get('data', 'input_mode'))
trans = None
if self.configer.get('dataset') == 'imagenet':
if self.configer.get('data', 'image_tool') == 'cv2':
img = Image.fromarray(img)
trans = transforms.Compose([
transforms.Scale(256),
transforms.CenterCrop(224),
])
assert trans is not None
img = trans(img)
ori_img_bgr = ImageHelper.get_cv2_bgr(img,
mode=self.configer.get(
'data', 'input_mode'))
inputs = self.blob_helper.make_input(img,
input_size=self.configer.get(
'test', 'input_size'),
scale=1.0)
with torch.no_grad():
outputs = self.cls_net(inputs)
json_dict = self.__get_info_tree(outputs, image_path)
image_canvas = self.cls_parser.draw_label(ori_img_bgr.copy(),
json_dict['label'])
cv2.imwrite(vis_path, image_canvas)
cv2.imwrite(raw_path, ori_img_bgr)
Log.info('Json Path: {}'.format(json_path))
JsonHelper.save_file(json_dict, json_path)
return json_dict
def __get_info_tree(self, outputs, image_path=None):
json_dict = dict()
if image_path is not None:
json_dict['image_path'] = image_path
topk = (1, 3, 5)
maxk = max(topk)
_, pred = outputs.topk(maxk, 0, True, True)
for k in topk:
if k == 1:
json_dict['label'] = pred[0]
else:
json_dict['label_top{}'.format(k)] = pred[:k]
return json_dict
def debug(self, vis_dir):
count = 0
for i, data_dict in enumerate(self.cls_data_loader.get_trainloader()):
inputs = data_dict['img']
labels = data_dict['label']
eye_matrix = torch.eye(self.configer.get('data', 'num_classes'))
labels_target = eye_matrix[labels.view(-1)].view(
inputs.size(0), self.configer.get('data', 'num_classes'))
for j in range(inputs.size(0)):
count = count + 1
if count > 20:
exit(1)
ori_img_bgr = self.blob_helper.tensor2bgr(inputs[j])
json_dict = self.__get_info_tree(labels_target[j])
image_canvas = self.cls_parser.draw_label(
ori_img_bgr.copy(), json_dict['label'])
cv2.imwrite(
os.path.join(vis_dir, '{}_{}_vis.png'.format(i, j)),
image_canvas)
cv2.imshow('main', image_canvas)
cv2.waitKey()
