def __init__(
self,
gpu_id=0,
model1_path=None,
model2_path=None,
data_dir=None,
# result_dir=None,
mnist=False,
):
self.__num_class = cfg.Customer_DATA["NUM"]
self.__conf_threshold = cfg.VAL["CONF_THRESH"]
self.__nms_threshold = cfg.VAL["NMS_THRESH"]
self.__device = gpu.select_device(gpu_id)
self.__multi_scale_val = cfg.VAL["MULTI_SCALE_VAL"]
self.__flip_val = cfg.VAL["FLIP_VAL"]
self.__data_dir = data_dir
print(self.__data_dir)
self.__classes = cfg.Customer_DATA["CLASSES"]
self.__mnist = mnist
self.__model1 = Build_Model().to(self.__device)
if mnist:
self.__model2 = torch.load(model2_path).double().cuda()
else:
self.__model2 = torch.load(model2_path).cuda()
self.__load_model_weights(model1_path)
self.__evalter = Evaluator(self.__model1, showatt=False)
def __init__(self, weight_path=None, gpu_id=0, visiual=None, eval=False):
self.img_size = cfg.TEST["TEST_IMG_SIZE"]
self.__num_class = cfg.DATA["NUM"]
self.__conf_threshold = cfg.TEST["CONF_THRESH"]
self.__nms_threshold = cfg.TEST["NMS_THRESH"]
self.__device = gpu.select_device(gpu_id, force_cpu=False)
self.__multi_scale_test = cfg.TEST["MULTI_SCALE_TEST"]
self.__flip_test = cfg.TEST["FLIP_TEST"]
self.__classes = cfg.DATA["CLASSES"]
self.__visiual = visiual
self.__eval = eval
self.__model = NPMMRDet().to(self.__device) # Single GPU
net_model = NPMMRDet()
if torch.cuda.device_count() >1: ## Multi GPUs
print("Let's use", torch.cuda.device_count(), "GPUs!")
net_model = torch.nn.DataParallel(net_model) ## Multi GPUs
self.__model = net_model.to(self.__device)
elif torch.cuda.device_count() ==1:
self.__model = net_model.to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, visiual=False)
def __init__(self, config_path, log_level='info'):
"""
:param str config_path: path to config file
"""
self.__logger = logging.getLogger()
self.__logger.setLevel(LOG_LEVELS[log_level])
ch = logging.StreamHandler()
formatter = logging.Formatter(
'%(asctime)s [%(levelname)s]: %(message)s ' \
'(%(module)s:%(funcName)s:%(lineno)d)')
ch.setFormatter(formatter)
self.__logger.addHandler(ch)
with open(config_path, 'r') as ymlfile:
self.__cfg = yaml.load(ymlfile, Loader=yaml.FullLoader)
self.__client = Client(
self.__cfg['moodle'].get('data_path', DEFAULT_MOODLE_DATA_PATH),
self.__logger, self.__cfg['moodle'].get('timeout',
DEFAULT_TIMEOUT),
self.__cfg['moodle'].get('max_retries', DEFAULT_MAX_RETRIES))
eval_data_path = DEFAULT_EVAL_DATA_PATH
if 'eval' in self.__cfg and 'data_path' in self.__cfg['eval']:
eval_data_path = self.__cfg['eval']['data_path']
self.__evaluator = Evaluator(eval_data_path, self.__logger)
def __init__(
self,
gpu_id=0,
weight_path=None,
visiual=None,
eval=False,
):
# self.__num_class = cfg.VOC_DATA["NUM"]
self.__num_class = cfg.Customer_DATA["NUM"]
self.__conf_threshold = cfg.VAL["CONF_THRESH"]
self.__nms_threshold = cfg.VAL["NMS_THRESH"]
self.__device = gpu.select_device(gpu_id)
self.__multi_scale_val = cfg.VAL["MULTI_SCALE_VAL"]
self.__flip_val = cfg.VAL["FLIP_VAL"]
self.__visiual = visiual
self.__eval = eval
# self.__classes = cfg.VOC_DATA["CLASSES"]
self.__classes = cfg.Customer_DATA["CLASSES"]
self.__model = Build_Model().to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, showatt=False)
def __init__(self,
model,
weight_path=None,
gpu_id=0,
img_size=544,
visiual=None,
eval=False):
self.model = model
self.img_size = img_size
self.__num_class = cfg.DATA["NUM"]
self.__conf_threshold = cfg.TEST["CONF_THRESH"]
self.__nms_threshold = cfg.TEST["NMS_THRESH"]
self.__device = gpu.select_device(gpu_id)
self.__multi_scale_test = cfg.TEST["MULTI_SCALE_TEST"]
self.__flip_test = cfg.TEST["FLIP_TEST"]
self.__visiual = visiual
self.__eval = eval
self.__classes = cfg.DATA["CLASSES"]
if self.model == 's':
self.__model = Yolov3_S().to(self.__device)
else:
self.__model = Yolov3().to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, visiual=False)
def __init__(self,
gpu_id='0',
weight_path=None,
img_size=544,
visiual=None,
eval=False,
epoch=None):
self.img_size = img_size
self.__num_class = cfg.DATA["NUM"]
self.__conf_threshold = cfg.VAL["CONF_THRESH"]
self.__nms_threshold = cfg.VAL["NMS_THRESH"]
# self.__device = select_device('0', batch_size=cfg.VAL["BATCH_SIZE"])
self.__device = gpu.select_device(gpu_id)
self.__multi_scale_val = cfg.VAL["MULTI_SCALE_VAL"]
self.__flip_val = cfg.VAL["FLIP_VAL"]
self.__visiual = visiual
self.__eval = eval
self.__classes = cfg.DATA["CLASSES"]
self.__model = Build_Model().to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, epoch, showatt=False)
self.epoch = epoch
def evaluate(config, args):
if args.onnx:
model = onnx_model_for_eval(args.onnx, args.device == 'cuda')
else:
model = torch_model_for_eval(args.cfg, args.weight, device=args.device)
eval_dataset = EvalDataset(config)
evaluator = Evaluator(model, eval_dataset, config)
AP = evaluator.evaluate()
tools.print_metric(AP)
def test(self):
eval_dataset = EvalDataset(self.cfg)
dataloader = torch.utils.data.DataLoader(
eval_dataset, batch_size=None, shuffle=False,
num_workers=self._num_workers, pin_memory=True,
collate_fn=lambda x: x,
)
evaluator = Evaluator(self.new_model, dataloader, self.cfg)
self.new_model.eval()
AP = evaluator.evaluate()
# 打印
tools.print_metric(AP)
def __init__(self, weight_path, resume, exp_name, accumulate=None):
# precision=16 for fp16
super().__init__()
self.model = Build_Model(weight_path=weight_path, resume=resume)
self.criterion = YoloV4Loss(
anchors=cfg.MODEL["ANCHORS"],
strides=cfg.MODEL["STRIDES"],
iou_threshold_loss=cfg.TRAIN["IOU_THRESHOLD_LOSS"])
self.evaluator = Evaluator(self.model,
showatt=False,
exp_name=exp_name)
self.evaluator.clear_predict_file()
def test(self):
if self.__visiual:
imgs = os.listdir(self.__visiual)
for v in imgs:
path = os.path.join(self.__visiual, v)
print("test images : {}".format(path))
img = cv2.imread(path)
assert img is not None
bboxes_prd = self.__evalter.get_bbox(img)
if bboxes_prd.shape[0] != 0:
boxes = bboxes_prd[..., :4]
class_inds = bboxes_prd[..., 5].astype(np.int32)
scores = bboxes_prd[..., 4]
visualize_boxes(image=img, boxes=boxes, labels=class_inds, probs=scores, class_labels=self.__classes)
path = os.path.join(cfg.PROJECT_PATH, "data/{}".format(v))
cv2.imwrite(path, img)
print("saved images : {}".format(path))
if self.__eval:
mAP = 0
print('*' * 20 + "Validate" + '*' * 20)
with torch.no_grad():
APs = Evaluator(self.__model).APs_voc(self.__multi_scale_test, self.__flip_test)
for i in APs:
print("{} --> mAP : {}".format(i, APs[i]))
mAP += APs[i]
mAP = mAP / self.__num_class
print('mAP:%g' % (mAP))
class DlEval:
def __init__(self, config_path, log_level='info'):
"""
:param str config_path: path to config file
"""
self.__logger = logging.getLogger()
self.__logger.setLevel(LOG_LEVELS[log_level])
ch = logging.StreamHandler()
formatter = logging.Formatter(
'%(asctime)s [%(levelname)s]: %(message)s ' \
'(%(module)s:%(funcName)s:%(lineno)d)')
ch.setFormatter(formatter)
self.__logger.addHandler(ch)
with open(config_path, 'r') as ymlfile:
self.__cfg = yaml.load(ymlfile, Loader=yaml.FullLoader)
self.__client = Client(
self.__cfg['moodle'].get('data_path', DEFAULT_MOODLE_DATA_PATH),
self.__logger, self.__cfg['moodle'].get('timeout',
DEFAULT_TIMEOUT),
self.__cfg['moodle'].get('max_retries', DEFAULT_MAX_RETRIES))
eval_data_path = DEFAULT_EVAL_DATA_PATH
if 'eval' in self.__cfg and 'data_path' in self.__cfg['eval']:
eval_data_path = self.__cfg['eval']['data_path']
self.__evaluator = Evaluator(eval_data_path, self.__logger)
def run(self):
while True:
try:
ok = self.__client.login(self.__cfg['moodle']['username'],
self.__cfg['moodle']['password'])
if not ok:
self.__logger.critical('login failed')
else:
allowed_assignments = \
self.__evaluator.get_allowed_assignments()
course_data = self.__client.download_new_course_data(
self.__cfg['moodle']['course_id'], allowed_assignments)
self.__evaluator.evaluate(course_data)
self.__client.send_feedback(course_data)
except:
tback = ''.join(traceback.format_exception(*sys.exc_info()))
self.__logger.critical('an exception occured!\n' + tback)
sleep(self.__cfg.get('interval', DEFAULT_INTERVAL))
def __init__(self,
gpu_id=0,
weight_path=None,
visiual=None,
eval=False,
mode=None):
self.__num_class = cfg.VOC_DATA["NUM"]
self.__conf_threshold = cfg.VAL["CONF_THRESH"]
self.__nms_threshold = cfg.VAL["NMS_THRESH"]
self.__device = gpu.select_device(gpu_id)
self.__showatt = cfg.TRAIN["showatt"]
self.__visiual = visiual
self.__mode = mode
self.__classes = cfg.VOC_DATA["CLASSES"]
self.__model = Build_Model(showatt=self.__showatt).to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, showatt=self.__showatt)
def __init__(self,
label_path,
weight_path=None,
output_dir=None,
):
self.__label_path = os.path.join("/data",label_path)
self.get_first_10_imgs()
self.__num_class = cfg.DATASET.NUM
self.__conf_threshold = cfg.VAL.CONF_THRESH
self.__nms_threshold = cfg.VAL.NMS_THRESH
self.__device = gpu.select_device()
self.__classes = cfg.DATASET.CLASSES
# self.__video_path = video_path
self.__output_dir = output_dir
self.__model = Build_Model().to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, showatt=False)
def __init__(self,
gpu_id=0,
weight_path=None,
visiual=None,
heatmap=False):
self.__num_class = cfg.COCO_DATA.NUM
self.__conf_threshold = cfg.VAL.CONF_THRESH
self.__nms_threshold = cfg.VAL.NMS_THRESH
self.__device = gpu.select_device(gpu_id)
self.__multi_scale_val = cfg.VAL.MULTI_SCALE_VAL
self.__flip_val = cfg.VAL.FLIP_VAL
self.__visiual = visiual
self.__eval = eval
self.__classes = cfg.COCO_DATA.CLASSES
self.__model = Build_Model().to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, showatt=heatmap)
def __init__(self,
cfg_path=None,
weight_path=None,
gpu_id=0,
img_size=544,
visiual=None,
eval=False):
self.img_size = img_size
self.__num_class = pms.DATA["NUM"]
self.__conf_threshold = pms.TEST["CONF_THRESH"]
self.__nms_threshold = pms.TEST["NMS_THRESH"]
self.__device = gpu.select_device(gpu_id)
self.__visiual = visiual
self.__eval = eval
self.__classes = pms.DATA["CLASSES"]
self.__model = Darknet(cfg_path=cfg_path,
img_size=img_size).to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, visiual=False)
def __init__(
self,
label_path,
weight_path=None,
output_dir=None,
):
self.__label_path = os.path.join("/data", label_path)
self.get_first_10_imgs()
self.__num_class = cfg.DATASET.NUM
# these should be set still
self.__conf_threshold = 0.25
self.__nms_threshold = 0.5
#######################################
self.__device = gpu.select_device()
self.__classes = cfg.DATASET.CLASSES
self.__output_dir = output_dir
self.__model = Build_Model().to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, showatt=False)
def val(self):
global logger
if self.__eval:
logger.info("***********Start Evaluation****************")
start = time.time()
mAP = 0
with torch.no_grad():
APs, inference_time = Evaluator(self.__model, showatt=False).APs_voc(self.__multi_scale_val, self.__flip_val)
for i in APs:
logger.info("{} --> mAP : {}".format(i, APs[i]))
mAP += APs[i]
mAP = mAP / self.__num_class
logger.info('mAP:{}'.format(mAP))
logger.info("inference time: {:.2f} ms".format(inference_time))
end = time.time()
logger.info(" ===val cost time:{:.4f}s".format(end - start))
def val(self):
global writer, logger
if self.__eval:
logger.info("***********Start Evaluation****************")
start = time.time()
mAP = 0
with torch.no_grad():
_, _, APs = Evaluator(self.__model, self.epoch,
showatt=False).APs_voc(
self.__multi_scale_val,
self.__flip_val)
for i in APs:
logger.info("{} --> mAP : {}".format(i, APs[i]))
mAP += APs[i]
mAP = mAP / self.__num_class
logger.info('mAP:{}'.format(mAP))
writer.add_scalar('mAP', mAP, self.epoch)
end = time.time()
logger.info(" ===val cost time:{:.4f}s".format(end - start))
class Tester(object):
def __init__(self,
weight_path=None,
gpu_id=0,
img_size=544,
visiual=None,
eval=False):
self.img_size = img_size
self.__num_class = cfg.DATA["NUM"]
self.__conf_threshold = cfg.TEST["CONF_THRESH"]
self.__nms_threshold = cfg.TEST["NMS_THRESH"]
self.__device = gpu.select_device(gpu_id)
self.__multi_scale_test = cfg.TEST["MULTI_SCALE_TEST"]
self.__flip_test = cfg.TEST["FLIP_TEST"]
self.__visiual = visiual
self.__eval = eval
self.__classes = cfg.DATA["CLASSES"]
self.__model = Yolov3().to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, visiual=False)
def __load_model_weights(self, weight_path):
print("loading weight file from : {}".format(weight_path))
weight = os.path.join(weight_path)
chkpt = torch.load(weight, map_location=self.__device)
self.__model.load_state_dict(chkpt)
print("loading weight file is done")
del chkpt
def test(self):
if self.__visiual:
imgs = os.listdir(self.__visiual)
for v in imgs:
path = os.path.join(self.__visiual, v)
print("test images : {}".format(path))
img = cv2.imread(path)
assert img is not None
bboxes_prd = self.__evalter.get_bbox(img)
if bboxes_prd.shape[0] != 0:
boxes = bboxes_prd[..., :4]
class_inds = bboxes_prd[..., 5].astype(np.int32)
scores = bboxes_prd[..., 4]
visualize_boxes(image=img,
boxes=boxes,
labels=class_inds,
probs=scores,
class_labels=self.__classes)
path = os.path.join(cfg.PROJECT_PATH, "data/{}".format(v))
cv2.imwrite(path, img)
print("saved images : {}".format(path))
if self.__eval:
mAP = 0
print('*' * 20 + "Validate" + '*' * 20)
with torch.no_grad():
APs = Evaluator(self.__model).APs_voc(self.__multi_scale_test,
self.__flip_test)
for i in APs:
print("{} --> mAP : {}".format(i, APs[i]))
mAP += APs[i]
mAP = mAP / self.__num_class
print('mAP:%g' % (mAP))
class Evaluation(object):
def __init__(self,
gpu_id=0,
weight_path=None,
visiual=None,
heatmap=False):
self.__num_class = cfg.COCO_DATA["NUM"]
self.__conf_threshold = cfg.VAL["CONF_THRESH"]
self.__nms_threshold = cfg.VAL["NMS_THRESH"]
self.__device = gpu.select_device(gpu_id)
self.__multi_scale_val = cfg.VAL["MULTI_SCALE_VAL"]
self.__flip_val = cfg.VAL["FLIP_VAL"]
self.__visiual = visiual
self.__eval = eval
self.__classes = cfg.COCO_DATA["CLASSES"]
self.__model = Build_Model().to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, showatt=heatmap)
def __load_model_weights(self, weight_path):
print("loading weight file from : {}".format(weight_path))
weight = os.path.join(weight_path)
chkpt = torch.load(weight, map_location=self.__device)
self.__model.load_state_dict(chkpt)
print("loading weight file is done")
del chkpt
def reset(self):
path1 = os.path.join(cfg.DETECTION_PATH, "detection_result/")
path2 = os.path.join(cfg.DETECTION_PATH, "ShowAtt/")
for i in os.listdir(path1):
path_file = os.path.join(path1, i)
if os.path.isfile(path_file):
os.remove(path_file)
else:
for f in os.listdir(path_file):
path_file2 = os.path.join(path_file, f)
if os.path.isfile(path_file2):
os.remove(path_file2)
for i in os.listdir(path2):
path_file = os.path.join(path2, i)
if os.path.isfile(path_file):
os.remove(path_file)
else:
for f in os.listdir(path_file):
path_file2 = os.path.join(path_file, f)
if os.path.isfile(path_file2):
os.remove(path_file2)
def study(self):
# Parameter study
y = []
for i in [0.08, 0.07, 0.06]:
t = time.time()
evaluator = COCOAPIEvaluator(model_type='YOLOv3',
data_dir=cfg.DATA_PATH,
img_size=cfg.VAL["TEST_IMG_SIZE"],
confthre=i,
nmsthre=cfg.VAL["NMS_THRESH"])
_, r = evaluator.evaluate(self.__model)
y.append(
str(i) + str(' ') + str(r) + str(' ') +
str(time.time() - t, ))
np.savetxt('study.txt', y, fmt='%s') # y = np.loadtxt('study.txt')
def val(self):
global logger
logger.info("***********Start Evaluation****************")
start = time.time()
evaluator = COCOAPIEvaluator(model_type='YOLOv4',
data_dir=cfg.DATA_PATH,
img_size=cfg.VAL["TEST_IMG_SIZE"],
confthre=cfg.VAL["CONF_THRESH"],
nmsthre=cfg.VAL["NMS_THRESH"])
ap50_95, ap50 = evaluator.evaluate(self.__model)
logger.info('ap50_95:{}|ap50:{}'.format(ap50_95, ap50))
end = time.time()
logger.info(" ===val cost time:{:.4f}s".format(end - start))
def Inference(self):
global logger
# clear cache
self.reset()
logger.info("***********Start Inference****************")
imgs = os.listdir(self.__visiual)
logger.info("images path: {}".format(self.__visiual))
path = os.path.join(cfg.DETECTION_PATH, "detection_result")
logger.info("saved images at: {}".format(path))
inference_times = []
for v in imgs:
start_time = time.time()
path = os.path.join(self.__visiual, v)
img = cv2.imread(path)
assert img is not None
bboxes_prd = self.__evalter.get_bbox(img, v)
if bboxes_prd.shape[0] != 0:
boxes = bboxes_prd[..., :4]
class_inds = bboxes_prd[..., 5].astype(np.int32)
scores = bboxes_prd[..., 4]
visualize_boxes(image=img,
boxes=boxes,
labels=class_inds,
probs=scores,
class_labels=self.__classes)
path = os.path.join(cfg.DETECTION_PATH,
"detection_result/{}".format(v))
cv2.imwrite(path, img)
end_time = time.time()
inference_times.append(end_time - start_time)
inference_time = sum(inference_times) / len(inference_times)
fps = 1.0 / inference_time
logging.info("Inference_Time: {:.5f} s/image, FPS: {}".format(
inference_time, fps))
class lightenYOLOv4(pl.LightningModule):
def __init__(self, weight_path, resume, exp_name, accumulate=None):
# precision=16 for fp16
super().__init__()
self.model = Build_Model(weight_path=weight_path, resume=resume)
self.criterion = YoloV4Loss(
anchors=cfg.MODEL["ANCHORS"],
strides=cfg.MODEL["STRIDES"],
iou_threshold_loss=cfg.TRAIN["IOU_THRESHOLD_LOSS"])
self.evaluator = Evaluator(self.model,
showatt=False,
exp_name=exp_name)
self.evaluator.clear_predict_file()
# how you want your model to do inference/predictions
def forward(self, img):
p, p_d = self.model(img)
return p, p_d
"""
def training_epoch_end(self,outputs):
# the function is called after every epoch is completed
# calculating average loss
avg_loss = 0
avg_loss = torch.stack([x['loss'] for x in outputs]).mean()
# creating log dictionary
result = pl.TrainResult()
result.log('val/loss_epoch', avg_loss)
return result
"""
# the train loop INDEPENDENT of forward.
def training_step(self, batch, batch_idx):
img, label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes, _ = batch
p, p_d = self(img)
loss, loss_ciou, loss_conf, loss_cls = self.criterion(
p, p_d, label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes,
lbboxes)
result = pl.TrainResult(minimize=loss)
#result = pl.TrainResult(loss)
#result.log('train_loss_ciou', loss_ciou)
#result.log('train_loss_conf', loss_conf)
#result.log('train_loss_cls', loss_cls)
result.log('train_loss', loss, on_step=True, on_epoch=True)
return result
'''
#https://www.learnopencv.com/tensorboard-with-pytorch-lightning/
logs={"train_loss": loss,
"train_loss_ciou":loss_ciou,
"train_loss_conf":loss_conf,
"train_loss_cls":loss_cls,}
batch_dictionary={
#REQUIRED: It ie required for us to return "loss"
"loss": loss,
#optional for batch logging purposes
"log": logs,
}
return batch_dictionary
'''
def validation_epoch_end(self, outputs):
APs = self.evaluator.calc_APs()
self.evaluator.clear_predict_file()
mAP = 0
for i in APs:
mAP += APs[i]
mAP = mAP / self.model.getNC()
result = pl.EvalResult()
result.log('val/mAP_epoch', torch.Tensor([mAP]).cuda())
#trainer.logger_connector.logged_metrics
return result
def validation_step(self, batch, batch_idx):
img_batch, label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes, img_name = batch
for idx, img in tqdm(zip(img_name, img_batch)):
# CHW -> HWC
img = img.cpu().numpy().transpose(1, 2, 0)
bboxes_prd = self.evaluator.get_bbox(img,
multi_test=False,
flip_test=False)
self.evaluator.store_bbox(idx, bboxes_prd)
'''
loss, loss_ciou, loss_conf, loss_cls = self.criterion(p, p_d, label_sbbox, label_mbbox,
label_lbbox, sbboxes, mbboxes, lbboxes)
self.log('val_loss_ciou', loss_ciou)
self.log('val_loss_conf', loss_conf)
self.log('val_loss_cls', loss_cls)
self.log('val_loss', loss)
'''
return 1
def test_step(self, batch, batch_idx):
img, label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes = batch
p, p_d = self(img)
loss, loss_ciou, loss_conf, loss_cls = self.criterion(
p, p_d, label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes,
lbboxes)
#, loss_ciou, loss_conf, loss_cls
return loss
def configure_optimizers(self):
optimizer = optim.SGD(self.model.parameters(),
lr=cfg.TRAIN["LR_INIT"],
momentum=cfg.TRAIN["MOMENTUM"],
weight_decay=cfg.TRAIN["WEIGHT_DECAY"])
return optimizer
def test(self):
global logger
logger.info("***********Start Evaluation****************")
if self.__visiual:
imgs = os.listdir(self.__visiual)
for v in imgs:
path = os.path.join(self.__visiual, v)
#print("test images : {}".format(path))
img = cv2.imread(path)
assert img is not None
bboxes_prd = self.__evalter.get_bbox(img)
if bboxes_prd.shape[0] != 0:
boxes = bboxes_prd[..., :4]
class_inds = bboxes_prd[..., 5].astype(np.int32)
scores = bboxes_prd[..., 4]
visualize_boxes(image=img, boxes=boxes, labels=class_inds, probs=scores, class_labels=self.__classes)
path = os.path.join(cfg.PROJECT_PATH, "prediction/imgs_all/{}".format(v))
cv2.imwrite(path, img)
#print("saved images : {}".format(path))
mAP = 0
if self.__eval and cfg.TEST["EVAL_TYPE"] == 'VOC':
with torch.no_grad():
start = time.time()
APs, inference_time = Evaluator(self.__model).APs_voc(self.__multi_scale_test, self.__flip_test)
for i in APs:
print("{} --> AP : {}".format(i, APs[i]))
mAP += APs[i]
mAP = mAP / self.__num_class
logger.info('mAP:{}'.format(mAP))
logger.info("inference time: {:.2f} ms".format(inference_time))
writer.add_scalar('test/VOCmAP', mAP)
end = time.time()
logger.info("Test cost time:{:.4f}s".format(end - start))
#print('mAP:%g' % (mAP))
#print("inference time : {:.2f} ms".format(inference_time))
elif self.__eval and cfg.TEST["EVAL_TYPE"] == 'COCO':
with torch.no_grad():
start = time.time()
evaluator = COCOEvaluator(data_dir=cfg.DATA_PATH,
img_size=cfg.TEST["TEST_IMG_SIZE"],
confthre=cfg.TEST["CONF_THRESH"],
nmsthre=cfg.TEST["NMS_THRESH"])
ap50_95, ap50, inference_time = evaluator.evaluate(self.__model)
logger.info('ap50_95:{} | ap50:{}'.format(ap50_95, ap50))
logger.info("inference time: {:.2f} ms".format(inference_time))
writer.add_scalar('test/COCOAP50', ap50)
writer.add_scalar('test/COCOAP50_95', ap50_95)
end = time.time()
logger.info("Test cost time:{:.4f}s".format(end - start))
elif self.__eval and cfg.TEST["EVAL_TYPE"] == 'BOTH':
with torch.no_grad():
start = time.time()
APs, inference_time = Evaluator(self.__model).APs_voc(self.__multi_scale_test, self.__flip_test)
for i in APs:
print("{} --> mAP : {}".format(i, APs[i]))
mAP += APs[i]
mAP = mAP / self.__num_class
logger.info('mAP:{}'.format(mAP))
logger.info("inference time: {:.2f} ms".format(inference_time))
writer.add_scalar('test/VOCmAP', mAP)
end = time.time()
logger.info("Test cost time:{:.4f}s".format(end - start))
start = time.time()
evaluator = COCOEvaluator(data_dir=cfg.DATA_PATH,
img_size=cfg.TEST["TEST_IMG_SIZE"],
confthre=cfg.TEST["CONF_THRESH"],
nmsthre=cfg.TEST["NMS_THRESH"])
ap50_95, ap50, inference_time = evaluator.evaluate(self.__model)
logger.info('ap50_95:{} | ap50:{}'.format(ap50_95, ap50))
logger.info("inference time: {:.2f} ms".format(inference_time))
writer.add_scalar('test/COCOAP50', ap50)
writer.add_scalar('test/COCOAP50_95', ap50_95)
end = time.time()
logger.info("Test cost time:{:.4f}s".format(end - start))
def video_detection(self):
vid = cv2.VideoCapture(self.video_path)
if not vid.isOpened():
raise IOError("Couldn't open webcam or video")
video_FourCC = int(vid.get(cv2.CAP_PROP_FOURCC))
video_fps = vid.get(cv2.CAP_PROP_FPS)
video_size = (
int(vid.get(cv2.CAP_PROP_FRAME_WIDTH)),
int(vid.get(cv2.CAP_PROP_FRAME_HEIGHT)),
)
isOutput = True if self.output_dir != "" else False
if isOutput:
print(
"!!! TYPE:",
type(self.output_dir),
type(video_FourCC),
type(video_fps),
type(video_size),
)
out = cv2.VideoWriter(self.output_dir, video_FourCC, video_fps,
video_size)
accum_time = 0
curr_fps = 0
fps = "FPS: ??"
prev_time = timer()
while True:
return_value, frame = vid.read()
evaluator_imgs = Evaluator(self.__model,
self.__classes,
self.__num_classes,
visual=False)
bboxes_prd = evaluator_imgs.get_bbox(frame)
if bboxes_prd.shape[0] != 0:
boxes = bboxes_prd[..., :4]
class_inds = bboxes_prd[..., 5].astype(np.int32)
scores = bboxes_prd[..., 4]
visualize_boxes(image=frame,
boxes=boxes,
labels=class_inds,
probs=scores,
class_labels=self.__classes)
curr_time = timer()
exec_time = curr_time - prev_time
prev_time = curr_time
accum_time = accum_time + exec_time
curr_fps = curr_fps + 1
if accum_time > 1:
accum_time = accum_time - 1
fps = "FPS: " + str(curr_fps)
curr_fps = 0
cv2.putText(frame,
text=fps,
org=(3, 15),
fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.50,
color=(255, 0, 0),
thickness=2)
cv2.namedWindow("result", cv2.WINDOW_NORMAL)
cv2.imshow("result", frame)
if isOutput:
out.write(frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
class Detection(object):
def __init__(self,
label_path,
weight_path=None,
output_dir=None,
):
self.__label_path = os.path.join("/data",label_path)
self.get_first_10_imgs()
self.__num_class = cfg.DATASET.NUM
self.__conf_threshold = cfg.VAL.CONF_THRESH
self.__nms_threshold = cfg.VAL.NMS_THRESH
self.__device = gpu.select_device()
self.__classes = cfg.DATASET.CLASSES
# self.__video_path = video_path
self.__output_dir = output_dir
self.__model = Build_Model().to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, showatt=False)
def __load_model_weights(self, weight_path):
print("loading weight file from : {}".format(weight_path))
weight = os.path.join(weight_path)
chkpt = torch.load(weight, map_location=self.__device)
self.__model.load_state_dict(chkpt)
print("loading weight file is done")
del chkpt
def detect_demo(self):
import cv2
accum_time = 0
for image_path in self.__file_list:
frame = cv2.imread(image_path)
# prev_time = timer()
bboxes_prd = self.__evalter.get_bbox(frame)
if bboxes_prd.shape[0] != 0:
boxes = bboxes_prd[..., :4]
class_inds = bboxes_prd[..., 5].astype(np.int32)
scores = bboxes_prd[..., 4]
visualize_boxes(image=frame, boxes=boxes, labels=class_inds, probs=scores, class_labels=self.__classes)
# curr_time = timer()
# accum_time += curr_time - prev_time
cv2.imwrite(os.path.join(self.__output_dir,os.path.basename(image_path)),frame)
print("FPS: {:.04f}".format(len(self.__file_list)/self.__evalter.inference_time))
def get_first_10_imgs(self):
fh = open(self.__label_path)
image_paths = []
for line in fh.readlines():
line = line.rstrip().split()
if len(image_paths) < 100:
if len(line) > 1:
image_paths.append(os.path.join("/data",line[0]))
else:
break
print(image_paths)
self.__file_list = image_paths
class Detection(object):
def __init__(
self,
label_path,
weight_path=None,
output_dir=None,
):
self.__label_path = os.path.join("/data", label_path)
self.get_first_10_imgs()
self.__num_class = cfg.DATASET.NUM
# these should be set still
self.__conf_threshold = 0.25
self.__nms_threshold = 0.5
#######################################
self.__device = gpu.select_device()
self.__classes = cfg.DATASET.CLASSES
self.__output_dir = output_dir
self.__model = Build_Model().to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, showatt=False)
def __load_model_weights(self, weight_path):
print("loading weight file from : {}".format(weight_path))
weight = os.path.join(weight_path)
chkpt = torch.load(weight, map_location=self.__device)
self.__model.load_state_dict(chkpt)
print("loading weight file is done")
del chkpt
def detect_demo(self):
import cv2
accum_time = 0
for image_path in tqdm(self.__file_dict.keys()):
# print(self.__file_dict[image_path])
frame = cv2.imread(image_path)
# prev_time = timer()
bboxes_prd = self.__evalter.get_bbox(frame)
if bboxes_prd.shape[0] != 0:
boxes = bboxes_prd[..., :4]
class_inds = bboxes_prd[..., 5].astype(np.int32)
scores = bboxes_prd[..., 4]
visualize_boxes(image=frame,
boxes=boxes,
labels=class_inds,
probs=scores,
class_labels=self.__classes)
visualize_boxes_and_labels_on_image_array(
image=frame,
boxes=self.__file_dict[image_path][:, :4],
classes=self.__file_dict[image_path][:, 4],
scores=None,
line_thickness=10,
category_index=self.__classes)
cv2.imwrite(
os.path.join(self.__output_dir, os.path.basename(image_path)),
frame)
print("FPS: {:.04f}".format(1000 * len(self.__file_dict.keys()) /
self.__evalter.inference_time))
def get_first_10_imgs(self):
fh = open(self.__label_path)
image_paths = {}
####################################
# for random select
####################################
# random.seed(1)
# lines = random.choices(fh.readlines(),k=10)
# for line in lines:
# line = line.rstrip().split()
# if len(line)>1:
# image_paths[os.path.join("/data",line[0])] = np.array([list(map(int,i.split(","))) for i in line[1:]])
# else:
# break
####################################
# for on demand plot
####################################
lines = fh.readlines()
imgs = [
"images/0021023.png", "images/0020485.png", "images/0021042.png",
"images/0021630.png", "images/0021729.png", "images/0021781.png"
]
for line in lines:
line = line.rstrip().split()
if line[0] in imgs:
image_paths[os.path.join("/data", line[0])] = np.array(
[list(map(int, i.split(","))) for i in line[1:]])
#####################################
self.__file_dict = image_paths
class Tester(object):
def __init__(self, weight_path=None, gpu_id=0, visiual=None, eval=False):
self.img_size = cfg.TEST["TEST_IMG_SIZE"]
self.__num_class = cfg.DATA["NUM"]
self.__conf_threshold = cfg.TEST["CONF_THRESH"]
self.__nms_threshold = cfg.TEST["NMS_THRESH"]
self.__device = gpu.select_device(gpu_id, force_cpu=False)
self.__multi_scale_test = cfg.TEST["MULTI_SCALE_TEST"]
self.__flip_test = cfg.TEST["FLIP_TEST"]
self.__classes = cfg.DATA["CLASSES"]
self.__visiual = visiual
self.__eval = eval
self.__model = NPMMRDet().to(self.__device) # Single GPU
net_model = NPMMRDet()
if torch.cuda.device_count() >1: ## Multi GPUs
print("Let's use", torch.cuda.device_count(), "GPUs!")
net_model = torch.nn.DataParallel(net_model) ## Multi GPUs
self.__model = net_model.to(self.__device)
elif torch.cuda.device_count() ==1:
self.__model = net_model.to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, visiual=False)
def __load_model_weights(self, weight_path):
print("loading weight file from : {}".format(weight_path))
weight = os.path.join(weight_path)
chkpt = torch.load(weight, map_location=self.__device)
self.__model.load_state_dict(chkpt) #['model']
#print("loading weight file is done")
del chkpt
def test(self):
global logger
logger.info("***********Start Evaluation****************")
if self.__visiual:
imgs = os.listdir(self.__visiual)
for v in imgs:
path = os.path.join(self.__visiual, v)
#print("test images : {}".format(path))
img = cv2.imread(path)
assert img is not None
bboxes_prd = self.__evalter.get_bbox(img)
if bboxes_prd.shape[0] != 0:
boxes = bboxes_prd[..., :4]
class_inds = bboxes_prd[..., 5].astype(np.int32)
scores = bboxes_prd[..., 4]
visualize_boxes(image=img, boxes=boxes, labels=class_inds, probs=scores, class_labels=self.__classes)
path = os.path.join(cfg.PROJECT_PATH, "prediction/imgs_all/{}".format(v))
cv2.imwrite(path, img)
#print("saved images : {}".format(path))
mAP = 0
if self.__eval and cfg.TEST["EVAL_TYPE"] == 'VOC':
with torch.no_grad():
start = time.time()
APs, inference_time = Evaluator(self.__model).APs_voc(self.__multi_scale_test, self.__flip_test)
for i in APs:
print("{} --> AP : {}".format(i, APs[i]))
mAP += APs[i]
mAP = mAP / self.__num_class
logger.info('mAP:{}'.format(mAP))
logger.info("inference time: {:.2f} ms".format(inference_time))
writer.add_scalar('test/VOCmAP', mAP)
end = time.time()
logger.info("Test cost time:{:.4f}s".format(end - start))
#print('mAP:%g' % (mAP))
#print("inference time : {:.2f} ms".format(inference_time))
elif self.__eval and cfg.TEST["EVAL_TYPE"] == 'COCO':
with torch.no_grad():
start = time.time()
evaluator = COCOEvaluator(data_dir=cfg.DATA_PATH,
img_size=cfg.TEST["TEST_IMG_SIZE"],
confthre=cfg.TEST["CONF_THRESH"],
nmsthre=cfg.TEST["NMS_THRESH"])
ap50_95, ap50, inference_time = evaluator.evaluate(self.__model)
logger.info('ap50_95:{} | ap50:{}'.format(ap50_95, ap50))
logger.info("inference time: {:.2f} ms".format(inference_time))
writer.add_scalar('test/COCOAP50', ap50)
writer.add_scalar('test/COCOAP50_95', ap50_95)
end = time.time()
logger.info("Test cost time:{:.4f}s".format(end - start))
elif self.__eval and cfg.TEST["EVAL_TYPE"] == 'BOTH':
with torch.no_grad():
start = time.time()
APs, inference_time = Evaluator(self.__model).APs_voc(self.__multi_scale_test, self.__flip_test)
for i in APs:
print("{} --> mAP : {}".format(i, APs[i]))
mAP += APs[i]
mAP = mAP / self.__num_class
logger.info('mAP:{}'.format(mAP))
logger.info("inference time: {:.2f} ms".format(inference_time))
writer.add_scalar('test/VOCmAP', mAP)
end = time.time()
logger.info("Test cost time:{:.4f}s".format(end - start))
start = time.time()
evaluator = COCOEvaluator(data_dir=cfg.DATA_PATH,
img_size=cfg.TEST["TEST_IMG_SIZE"],
confthre=cfg.TEST["CONF_THRESH"],
nmsthre=cfg.TEST["NMS_THRESH"])
ap50_95, ap50, inference_time = evaluator.evaluate(self.__model)
logger.info('ap50_95:{} | ap50:{}'.format(ap50_95, ap50))
logger.info("inference time: {:.2f} ms".format(inference_time))
writer.add_scalar('test/COCOAP50', ap50)
writer.add_scalar('test/COCOAP50_95', ap50_95)
end = time.time()
logger.info("Test cost time:{:.4f}s".format(end - start))
class Evaluation(object):
def __init__(self,
gpu_id=0,
weight_path=None,
visiual=None,
eval=False,
showatt=False,
mode=None):
self.__num_class = cfg.VOC_DATA["NUM"]
self.__conf_threshold = cfg.VAL["CONF_THRESH"]
self.__nms_threshold = cfg.VAL["NMS_THRESH"]
self.__device = gpu.select_device(gpu_id)
self.__multi_scale_val = cfg.VAL["MULTI_SCALE_VAL"]
self.__flip_val = cfg.VAL["FLIP_VAL"]
self.__showatt = showatt
self.__visiual = visiual
self.__eval = eval
self.__mode = mode
self.__classes = cfg.VOC_DATA["CLASSES"]
self.__model = Build_Model(showatt=self.__showatt).to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, showatt=self.__showatt)
def __load_model_weights(self, weight_path):
print("loading weight file from : {}".format(weight_path))
weight = os.path.join(weight_path)
chkpt = torch.load(weight, map_location=self.__device)
self.__model.load_state_dict(chkpt["model"])
print("loading weight file is done")
del chkpt
def val(self):
global logger
if self.__eval:
logger.info("***********Start Evaluation****************")
start = time.time()
mAP = 0
with torch.no_grad():
APs, inference_time = Evaluator(self.__model,
showatt=False).APs_voc(
self.__multi_scale_val,
self.__flip_val)
for i in APs:
logger.info("{} --> mAP : {}".format(i, APs[i]))
mAP += APs[i]
mAP = mAP / self.__num_class
logger.info("mAP:{}".format(mAP))
logger.info("inference time: {:.2f} ms".format(inference_time))
end = time.time()
logger.info(" ===val cost time:{:.4f}s".format(end - start))
def detection(self):
global logger
if self.__visiual:
imgs = os.listdir(self.__visiual)
logger.info("***********Start Detection****************")
for v in imgs:
path = os.path.join(self.__visiual, v)
logger.info("val images : {}".format(path))
img = cv2.imread(path)
assert img is not None
bboxes_prd = self.__evalter.get_bbox(img, v, mode=self.__mode)
if bboxes_prd.shape[0] != 0:
boxes = bboxes_prd[..., :4]
class_inds = bboxes_prd[..., 5].astype(np.int32)
scores = bboxes_prd[..., 4]
visualize_boxes(
image=img,
boxes=boxes,
labels=class_inds,
probs=scores,
class_labels=self.__classes,
)
path = os.path.join(cfg.PROJECT_PATH,
"detection_result/{}".format(v))
cv2.imwrite(path, img)
logger.info("saved images : {}".format(path))
class Detection(object):
def __init__(self,
gpu_id=0,
weight_path=None,
video_path=None,
output_dir=None,
):
self.__num_class = cfg.VOC_DATA["NUM"]
self.__conf_threshold = cfg.VAL["CONF_THRESH"]
self.__nms_threshold = cfg.VAL["NMS_THRESH"]
self.__device = gpu.select_device(gpu_id)
self.__multi_scale_val = cfg.VAL["MULTI_SCALE_VAL"]
self.__flip_val = cfg.VAL["FLIP_VAL"]
self.__classes = cfg.VOC_DATA["CLASSES"]
self.__video_path = video_path
self.__output_dir = output_dir
self.__model = Build_Model().to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, showatt=False)
def __load_model_weights(self, weight_path):
print("loading weight file from : {}".format(weight_path))
weight = os.path.join(weight_path)
chkpt = torch.load(weight, map_location=self.__device)
self.__model.load_state_dict(chkpt)
print("loading weight file is done")
del chkpt
def Video_detection(self):
import cv2
vid = cv2.VideoCapture(self.__video_path)
if not vid.isOpened():
raise IOError("Couldn't open webcam or video")
video_FourCC = int(vid.get(cv2.CAP_PROP_FOURCC))
video_fps = vid.get(cv2.CAP_PROP_FPS)
video_size = (int(vid.get(cv2.CAP_PROP_FRAME_WIDTH)),
int(vid.get(cv2.CAP_PROP_FRAME_HEIGHT)))
isOutput = True if self.__output_dir != "" else False
if isOutput:
print("!!! TYPE:", type(self.__output_dir), type(video_FourCC), type(video_fps), type(video_size))
out = cv2.VideoWriter(self.__output_dir, video_FourCC, video_fps, video_size)
accum_time = 0
curr_fps = 0
fps = "FPS: ??"
prev_time = timer()
while True:
return_value, frame = vid.read()
bboxes_prd = self.__evalter.get_bbox(frame)
if bboxes_prd.shape[0] != 0:
boxes = bboxes_prd[..., :4]
class_inds = bboxes_prd[..., 5].astype(np.int32)
scores = bboxes_prd[..., 4]
visualize_boxes(image=frame, boxes=boxes, labels=class_inds, probs=scores, class_labels=self.__classes)
curr_time = timer()
exec_time = curr_time - prev_time
prev_time = curr_time
accum_time = accum_time + exec_time
curr_fps = curr_fps + 1
if accum_time > 1:
accum_time = accum_time - 1
fps = "FPS: " + str(curr_fps)
curr_fps = 0
cv2.putText(frame, text=fps, org=(3, 15), fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.50, color=(255, 0, 0), thickness=2)
cv2.namedWindow("result", cv2.WINDOW_NORMAL)
cv2.imshow("result", frame)
if isOutput:
out.write(frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
def train(self):
global writer
logger.info(
"Training start,img size is: {:d},batchsize is: {:d},work number is {:d}"
.format(
cfg.TRAIN["TRAIN_IMG_SIZE"],
cfg.TRAIN["BATCH_SIZE"],
cfg.TRAIN["NUMBER_WORKERS"],
))
logger.info(self.yolov4)
logger.info("Train datasets number is : {}".format(
len(self.train_dataset)))
logger.info(" ======= start training ====== ")
for epoch in range(self.start_epoch, self.epochs):
start = time.time()
self.yolov4.train()
mloss = torch.zeros(4)
# logger.info("===Epoch:[{}/{}]===".format(epoch, self.epochs))
for i, (
imgs,
label_sbbox,
label_mbbox,
label_lbbox,
sbboxes,
mbboxes,
lbboxes,
) in enumerate(self.train_dataloader):
self.scheduler.step(
len(self.train_dataloader) /
(cfg.TRAIN["BATCH_SIZE"]) * epoch + i)
imgs = imgs.to(self.device)
label_sbbox = label_sbbox.to(self.device)
label_mbbox = label_mbbox.to(self.device)
label_lbbox = label_lbbox.to(self.device)
sbboxes = sbboxes.to(self.device)
mbboxes = mbboxes.to(self.device)
lbboxes = lbboxes.to(self.device)
p, p_d = self.yolov4(imgs)
loss, loss_ciou, loss_conf, loss_cls = self.criterion(
p,
p_d,
label_sbbox,
label_mbbox,
label_lbbox,
sbboxes,
mbboxes,
lbboxes,
)
loss.backward()
# Accumulate gradient for x batches before optimizing
if i % self.accumulate == 0:
self.optimizer.step()
self.optimizer.zero_grad()
# Update running mean of tracked metrics
loss_items = torch.tensor(
[loss_ciou, loss_conf, loss_cls, loss])
mloss = (mloss * i + loss_items) / (i + 1)
# Print batch results
if i % 10 == 0:
logger.info(
" === Epoch:[{:3}/{}],step:[{:3}/{}],img_size:[{:3}],total_loss:{:.4f}|loss_ciou:{:.4f}|loss_conf:{:.4f}|loss_cls:{:.4f}|lr:{:.4e}"
.format(
epoch + 1,
self.epochs,
i,
len(self.train_dataloader) - 1,
self.train_dataset.img_size,
mloss[3],
mloss[0],
mloss[1],
mloss[2],
self.optimizer.param_groups[0]["lr"],
))
writer.add_scalar(
"loss_ciou",
mloss[0],
len(self.train_dataloader) * epoch + i,
)
writer.add_scalar(
"loss_conf",
mloss[1],
len(self.train_dataloader) * epoch + i,
)
writer.add_scalar(
"loss_cls",
mloss[2],
len(self.train_dataloader) * epoch + i,
)
writer.add_scalar(
"train_loss",
mloss[3],
len(self.train_dataloader) * epoch + i,
)
# multi-sclae training (320-608 pixels) every 10 batches
if self.multi_scale_train and (i + 1) % 10 == 0:
self.train_dataset.img_size = (
random.choice(range(10, 20)) * 32)
if cfg.TRAIN["DATA_TYPE"] == "Customer":
mAP = 0.0
if epoch >= 0:
logger.info("===== Validate =====".format(
epoch, self.epochs))
logger.info("val img size is {}".format(
cfg.VAL["TEST_IMG_SIZE"]))
with torch.no_grad():
APs, inference_time = Evaluator(
self.yolov4, showatt=False).APs_voc()
for i in APs:
logger.info("{} --> mAP : {}".format(i, APs[i]))
mAP += APs[i]
mAP = mAP / self.train_dataset.num_classes
logger.info("mAP : {}".format(mAP))
logger.info(
"inference time: {:.2f} ms".format(inference_time))
writer.add_scalar("mAP", mAP, epoch)
self.__save_model_weights(epoch, mAP)
logger.info("save weights done")
logger.info(" ===test mAP:{:.6f}".format(mAP))
end = time.time()
logger.info(" ===cost time:{:.4f}s".format(end - start))
logger.info(
"=====Training Finished. best_test_mAP:{:.3f}%====".format(
self.best_mAP))
class Evaluation(object):
def __init__(self,
gpu_id='0',
weight_path=None,
img_size=544,
visiual=None,
eval=False,
epoch=None):
self.img_size = img_size
self.__num_class = cfg.DATA["NUM"]
self.__conf_threshold = cfg.VAL["CONF_THRESH"]
self.__nms_threshold = cfg.VAL["NMS_THRESH"]
# self.__device = select_device('0', batch_size=cfg.VAL["BATCH_SIZE"])
self.__device = gpu.select_device(gpu_id)
self.__multi_scale_val = cfg.VAL["MULTI_SCALE_VAL"]
self.__flip_val = cfg.VAL["FLIP_VAL"]
self.__visiual = visiual
self.__eval = eval
self.__classes = cfg.DATA["CLASSES"]
self.__model = Build_Model().to(self.__device)
self.__load_model_weights(weight_path)
self.__evalter = Evaluator(self.__model, epoch, showatt=False)
self.epoch = epoch
def __load_model_weights(self, weight_path):
print("loading weight file from : {}".format(weight_path))
weight = os.path.join(weight_path)
chkpt = torch.load(weight, map_location=self.__device)
self.__model.load_state_dict(chkpt)
print("loading weight file is done")
del chkpt
def val(self):
global writer, logger
if self.__eval:
logger.info("***********Start Evaluation****************")
start = time.time()
mAP = 0
with torch.no_grad():
_, _, APs = Evaluator(self.__model, self.epoch,
showatt=False).APs_voc(
self.__multi_scale_val,
self.__flip_val)
for i in APs:
logger.info("{} --> mAP : {}".format(i, APs[i]))
mAP += APs[i]
mAP = mAP / self.__num_class
logger.info('mAP:{}'.format(mAP))
writer.add_scalar('mAP', mAP, self.epoch)
end = time.time()
logger.info(" ===val cost time:{:.4f}s".format(end - start))
def detection(self):
global writer, logger
if self.__visiual:
imgs = os.listdir(self.__visiual)
logger.info("***********Start Detection****************")
start = time.clock()
for v in imgs:
path = os.path.join(self.__visiual, v)
logger.info("val images : {}".format(path))
img = cv2.imread(path)
assert img is not None
bboxes_prd = self.__evalter.get_bbox(img, v)
if bboxes_prd.shape[0] != 0:
boxes = bboxes_prd[..., :4]
class_inds = bboxes_prd[..., 5].astype(np.int32)
scores = bboxes_prd[..., 4]
visualize_boxes(image=img,
boxes=boxes,
labels=class_inds,
probs=scores,
class_labels=self.__classes)
path = os.path.join(cfg.PROJECT_PATH,
"detection_result/{}".format(v))
cv2.imwrite(path, img)
logger.info("saved images : {}".format(path))
end = time.clock()
times = end - start
FPS = len(imgs) / times
logger.info('FPS:{}'.format(FPS))
logger.info(" ===detection cost time:{:.4f}s".format(times))
