def main():
input_size = (416,416)
image_file = './005767.jpg'
image = cv2.imread(image_file)
image_shape = image.shape[:2]
tf.reset_default_graph()
# copy、resize416*416、
image_cp = preprocess_image(image,input_size)
#image_cp=np.ones([1,416,416,3]).astype(np.float32)
image_cp=np.load("005767.npy")#("/home/huawei/chems/bioavailability_model/atlas_data/005767.npy")
image_cp=np.transpose(image_cp,[0,2,3,1])
np.save("atoms.npy",image_cp)
#
with tf.name_scope('input'):
tf_image = tf.placeholder(tf.float32,[1,input_size[0],input_size[1],3],name='input_data')
#meta_variable=tf.placeholder(tf.float32,[1,1,len(class_names)*1024,1],name='meta_weigiht')
model_output = Darknet(tf_image)
#meta=np.ones([1,1,len(class_names)*1024,1], dtype=np.float32)
model_path = "./yolov2_model/yolov2_coco.ckpt"
saver = tf.train.Saver()
with tf.Session() as sess:
#sess.run(model_output,feed_dict={tf_image:image_cp,meta_variable:meta})
sess.run(tf.global_variables_initializer())
a=sess.run(model_output.rtn(),feed_dict={tf_image:image_cp})
a=np.transpose(a,[0,3,1,2])
#a=np.transpose(a,[0,3,2,1])
a=np.reshape(a,[-1])[:90]
#print(a)
for i in range(90):
# print("=============================")
print(a[i],i)
saver.save(sess,model_path)
def test():
model = Darknet()
print('Size of the test set:{}'.format(len(testset)))
# load ckpt
ckpt = torch.load(os.path.join(EXPT_DIR, CKPT_FILE))
model.load_state_dict(ckpt['model'])
fw = Flow(model, trainset, testset, hyp)
# write prediction
fw.validate(batch_size=16)
def infer():
model = Darknet()
ckpt = torch.load(os.path.join(EXPT_DIR, CKPT_FILE))
model.load_state_dict(ckpt['model'])
fw = Flow(model, trainset, testset, hyp)
# get the indices of unlabeled data
with open(os.path.join(EXPT_DIR, 'unlabeled.pkl'), 'rb') as f:
dt = pickle.load(f)
unlabeled = [i for i in dt]
fw.infer(unlabeled)
return
def train():
# Evaluation pipeline
files = glob.glob(
os.path.join('/home/iotsc_group1/ChangxingDENG/det/datasets/',
'PretrainImageNet', 'ILSVRC2012_img_val', '*.JPEG'))
files = sorted(files,
key=lambda f: f.split('/')[-1].split('_')[-1].split('.')[0])
labels = loadlabel(
os.path.join(
'/home/iotsc_group1/ChangxingDENG/det/datasets/',
'PretrainImageNet',
'ILSVRC2012_devkit_t12/data/ILSVRC2012_validation_ground_truth.txt'
))
eval_pipeline = EvalImageDecoderPipeline(files=files, labels=labels)
eval_pipeline.build()
eval_pii = pytorchIterator(eval_pipeline,
last_batch_policy=LastBatchPolicy.PARTIAL,
reader_name='Reader',
auto_reset=True)
model = Darknet()
state_dict = torch.load(
'logs/PretrainImageNet_20210316173822_1/13_70056.pth')
model.load_state_dict(state_dict=state_dict)
model = model.cuda()
criterion = nn.CrossEntropyLoss()
model.eval()
epoch_loss = 0
prediciton = []
target = []
with torch.no_grad():
for iter, data in enumerate(eval_pii):
x = data[0]['data']
label = data[0]['label'].squeeze(-1).long().cuda()
output = model(x)
loss = criterion(output, label).item()
epoch_loss += loss * x.shape[0]
prediciton.append(output)
target.append(label)
loss = epoch_loss / 50000
prediciton = torch.cat(prediciton, dim=0)
target = torch.cat(target, dim=0)
acc = top1accuracy(prediciton, target)
acctop5 = top5accuracy(prediciton, target)
print(f'Top1 ACC: {acc} Top5 ACC {acctop5} loss: {loss}')
def main():
# Initiate model
eval_model = Darknet("config/net/resnet_dropout.cfg").to('cuda')
eval_model.load_state_dict(torch.load("./logs/model/model_params_99.ckpt"))
precision, recall, AP, f1, ap_class = evaluate(eval_model, ['2012', 'val'],
[0.5, 0.5, 0.5],
4,
True,
diagnosis_code=1)
evaluation_metrics = [
("val_precision", precision.mean()),
("val_recall", recall.mean()),
("val_mAP", AP.mean()),
("val_f1", f1.mean()),
]
for tag, value in evaluation_metrics:
print("{}: {}".format(tag, value.item()))
def train():
epochs = 1
model = Darknet()
if RESUME_FROM:
ckpt = torch.load(os.path.join(EXPT_DIR, RESUME_FROM))
model.load_state_dict(ckpt['model'])
trainset.augment = True
fw = Flow(model, trainset, testset, hyp)
with open(os.path.join(EXPT_DIR, 'labeled.pkl'), 'rb') as f:
selected = pickle.load(f)
# if want to try pollution study
# load labels from EXPT_DIR/labeled.pkl
for epoch in range(epochs):
fw.train(epoch, samples=list(selected.keys()), prebias=False)
return
def train(params):
params = Params(params)
set_random_seeds(params.seed)
time_now = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
params.save_root = params.save_root + f'/{params.project_name}_{time_now}_{params.version}'
os.makedirs(params.save_root, exist_ok=True)
logging.basicConfig(
filename=
f'{params.save_root}/{params.project_name}_{time_now}_{params.version}.log',
filemode='a',
format='%{asctime}s - %(levalname)s: %(message)s')
if params.num_gpus == 0:
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
logging.info(f'Available GPUs: {torch.cuda.device_count()}')
data_transform = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize(mean=params.mean, std=params.std)
])
train_set = TrainDataset(root=os.path.join(params.data_root,
params.project_name,
params.train_set),
transform=data_transform)
# val_set = EvalDataset(root=os.path.join(params.data_root, params.project_name, params.val_set),
# label_path=os.path.join(params.data_root, params.project_name,
# 'ILSVRC2012_devkit_t12/data/ILSVRC2012_validation_ground_truth.txt'),
# transform=data_transform)
train_params = {
'batch_size': params.batch_size,
'shuffle': False,
'num_workers': 4,
'drop_last': True
}
# val_params = {'batch_size': params.batch_size, 'shuffle': False, 'num_workers': params.num_gpus * 4,
# 'drop_last': False}
train_loader = DataLoader(train_set, **train_params)
# val_loader = DataLoader(val_set, **val_params)
eli = ExternalInputIterator(params.batch_size)
params.mean = torch.Tensor(params.mean).unsqueeze(0).unsqueeze(0)
params.std = torch.Tensor(params.std).unsqueeze(0).unsqueeze(0)
pipe = ExternalSourcePipeline(params=params,
num_threads=4,
device_id=0,
external_date=eli,
seed=params.seed)
# pipe.build()
# images, _ = pipe.run()
# print(np.array(images[0].as_cpu()).shape)
import matplotlib.pyplot as plt
# plt.imsave('image[0].jpg', np.array(images[0].as_cpu()).transpose((1, 2, 0)))
# plt.imsave('image[0].jpg', images[0].as_cpu())
# exit()
pii = pytorchIterator(pipe,
last_batch_padded=True,
last_batch_policy=LastBatchPolicy.DROP)
model = Darknet()
criterion = nn.CrossEntropyLoss()
last_step = 0
last_epoch = 0
if params.load_weights != 'None':
try:
state_dict = torch.load(params.load_weights)
model.load_state_dict(state_dict)
last_step = int(params.load_weights.split('_')[-1].split('.')[0])
last_epoch = int(params.load_weights.split('_')[-2])
except:
logging.error('Fail to resuming from weight!')
exit()
if params.num_gpus > 0:
model = model.cuda()
if params.num_gpus > 1:
model = nn.DataParallel(model)
if params.optim == 'Adam':
optimizer = torch.optim.Adam(model.parameters(),
lr=params.learning_rate)
else:
optimizer = torch.optim.SGD(model.parameters(),
lr=params.learning_rate,
momentum=0.9,
nesterov=True)
epoch = 0
begin_epoch = max(0, last_epoch)
step = max(0, last_step)
logging.info('Begin to train...')
model.train()
try:
import time
for epoch in range(begin_epoch, params.epoch):
for iter, (data_pii,
data_torch) in enumerate(zip(pii, train_loader)):
t = time.time()
# type(x)显示torch.Tensor，但是x已经在显存上
x_pii = data_pii[0]['data']
label_pii = data_pii[0]['label'].cuda()
x_torch = data_torch[0].cuda()
label_torch = data_torch[1].cuda()
x_pii = x_pii.cpu().squeeze(0).numpy().transpose((1, 2, 0))
x_torch = x_torch.cpu().squeeze(0).numpy().transpose((1, 2, 0))
import matplotlib.pyplot as plt
plt.imsave('x_pii.jpg', x_pii)
plt.imsave('x_torch.jpg', x_torch)
exit()
# print('load data time:', time.time() - t)
# t = time.time()
# output = model(x)
# loss = criterion(output, label)
# optimizer.zero_grad()
# loss.backward()
# optimizer.step()
# print('running time:', time.time() - t)
# if iter == 6:
# exit()
except KeyboardInterrupt:
save_checkpoint(model,
f'{params.save_root}/Interrupt_{epoch}_{step}.pth')
label_noobj_mask * FOCAL(input=p_conf, target=label_obj_mask)) * label_mix
# loss classes
loss_cls = label_obj_mask * BCE(input=p_cls, target=label_cls) * label_mix
loss_giou = (torch.sum(loss_giou)) / batch_size
loss_conf = (torch.sum(loss_conf)) / batch_size
loss_cls = (torch.sum(loss_cls)) / batch_size
loss = loss_giou + loss_conf + loss_cls
return loss, loss_giou, loss_conf, loss_cls
if __name__ == "__main__":
from model import Darknet
net = Darknet("cfg/yolov3-voc.cfg")
p, p_d = net(torch.rand(3, 3, 416, 416))
label_sbbox = torch.rand(3, 52, 52, 3,26)
label_mbbox = torch.rand(3, 26, 26, 3, 26)
label_lbbox = torch.rand(3, 13, 13, 3,26)
sbboxes = torch.rand(3, 150, 4)
mbboxes = torch.rand(3, 150, 4)
lbboxes = torch.rand(3, 150, 4)
loss, loss_xywh, loss_conf, loss_cls = YoloV3Loss(pms.MODEL["ANCHORS"], pms.MODEL["STRIDES"])(p, p_d, label_sbbox,
label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes)
print(loss)
def __init__(self, path, args, with_tracking, widget, queue_size=3000):
# initialize the file video stream along with the boolean
# used to indicate if the thread should be stopped or not
self.stream = cv2.VideoCapture(path)
self.widget = widget
self.tracking = with_tracking
if not self.stream:
if type(path) == int:
print_info(widget, True, "error",
f"Error opening web cam on {path}")
else:
print_info(widget, True, "error",
f"Error opening video file {path}")
self.stopped = False
self.canceled = False
self.paused = False
self.ready = False
# initialize the queue used to store frames read from
# the video file
self.Q = Queue(maxsize=queue_size)
self.imread = Queue(maxsize=queue_size)
self.Q_processed = Queue(maxsize=queue_size)
self.inp_dim = int(args.reso)
self.batch_size = int(args.bs)
self.names_file = args.names
self.confidence = float(args.confidence)
self.nms_thresh = float(args.nms_thresh)
self.is_classifier = args.is_classifier
self.classes = load_classes(self.names_file)
self.num_classes = len(self.classes)
self.model = None
self.model_classifier = None
if self.is_classifier:
print_info(widget, False, "info",
"Loading network for detection.....", -1)
self.model = Darknet(args.classifier_cfg)
self.model.load_weights(args.classifier_weights)
print_info(widget, False, "info",
"Network for detection successfully loaded", 0)
print_info(widget, False, "info",
"Loading network for classification.....", -1)
self.model_classifier = Darknet(args.cfg)
self.model_classifier.load_weights(args.weights)
print_info(widget, False, "info",
"Network for classification successfully loaded", 0)
self.model_classifier.net_info["height"] = args.reso
self.inp_dim = int(self.model_classifier.net_info["height"])
# If there's a GPU availible, put the model on GPU
self.cuda = torch.cuda.is_available()
if self.cuda:
self.model_classifier.cuda()
# Set the model in evaluation mode
self.model_classifier.eval()
self.classifier_confidence = self.confidence
self.classifier_nms_thesh = self.nms_thresh
self.classifier_classes = self.classes
self.classifier_num_classes = self.num_classes
self.classifier_names_file = self.names_file
self.classifier_inp_dim = self.inp_dim
self.inp_dim = args.classifier_inp_dim
self.confidence = args.classifier_confidence
self.nms_thresh = args.classifier_nms_thresh
self.names_file = args.classifier_names
self.classes = load_classes(self.names_file)
self.num_classes = len(self.classes)
else:
print_info(widget, False, "info", "Loading network.....", -1)
self.model = Darknet(args.cfg)
self.model.load_weights(args.weights)
print_info(widget, False, "info", "Network successfully loaded", 0)
self.model.net_info["height"] = self.inp_dim
assert self.inp_dim % 32 == 0
assert self.inp_dim > 32
# If there's a GPU availible, put the model on GPU
self.cuda = torch.cuda.is_available()
if self.cuda:
self.model.cuda()
# Set the model in evaluation mode
self.model.eval()
# if tracking selected, initialize sort class
self.mot_tracking = None
if self.tracking == "sort":
self.mot_tracking = Sort(max_age=30, min_hits=3)
elif self.tracking == "deep_sort":
print_info(widget, False, "info", "Loading Deep Sort model ...",
-1)
self.mot_tracking = DeepSort()
print_info(widget, False, "info", "Deep Sort model loaded", -1)
def test(payload):
ckpt_file = payload["ckpt_file"]
batch_size = 16
coco = COCO("./data", Transforms(), train=False)
loader = DataLoader(coco,
shuffle=False,
batch_size=batch_size,
collate_fn=collate_fn)
config_file = "yolov3.cfg"
model = Darknet(config_file).to(device)
ckpt = torch.load(os.path.join("./log", ckpt_file))
model.load_state_dict(ckpt["model"])
model.eval()
# batch predictions from the entire test set
predictions = []
# keep track of ground-truth boxes and label
labels = []
with torch.no_grad():
for img, boxes, class_labels in loader:
img = img.to(device)
# get inference output
output = model(img)
for b, c in zip(boxes, class_labels):
labels.append((b, c))
# batch predictions from 3 yolo layers
batched_prediction = []
for p in output: # (bacth_size, 3, gx, gy, 85)
p = p.view(p.shape[0], -1, 85)
batched_prediction.append(p)
batched_prediction = torch.cat(batched_prediction, dim=1)
predictions.append(batched_prediction)
predictions = torch.cat(predictions, dim=0)
# apply nms to predicted bounding boxes
predicted_boxes, predicted_objectness, predicted_class_dist = bbox_transform(
predictions)
# the predicted boxes are in log space relative to the anchor priors
# bring them back to normalized xyxy format
cxcy_priors = anchors.normalize("cxcy")
# expand the priors to match the dimension of predicted_boxes
batched_cxcy_priors = cxcy_priors.unsqueeze(0).repeat(
predicted_boxes.shape[0], 1, 1)
predicted_boxes = batched_gcxgcy_to_cxcy(predicted_boxes,
batched_cxcy_priors)
del batched_cxcy_priors
# convert predicted_boxes to xyxy format and perform nms
xyxy = batched_cxcy_to_xy(predicted_boxes)
del predicted_boxes # (no longer need cxcy format)
# get predicted object
# apply softmax to the predicted class distribution
# note that bbox_tranform does not apply softmax
# because the loss we are using requires us to use raw output
predicted_objects = torch.argmax(F.softmax(predicted_class_dist, dim=-1),
dim=-1)
# predictions on the test set (value of "predictions" of the return)
prd = {}
for i in range(len(coco)):
# get boxes, scores, and objects on each image
_xyxy, _scores = xyxy[i], predicted_objectness[i]
_objects = predicted_objects[i]
keep = tv.ops.nms(_xyxy, _scores, 0.5)
boxes, scores, objects = _xyxy[keep], _scores[keep], _objects[keep]
prd[i] = {
"boxes": boxes.cpu().numpy().tolist(),
"objects": objects.cpu().numpy().tolist(),
"scores": scores.cpu().numpy().tolist(),
}
# ground-truth of the test set
# skip "difficulties" field, because every object in COCO
# should be considered reasonable
lbs = {}
for i in range(len(coco)):
boxes, class_labels = labels[i]
lbs[i] = {
"boxes": boxes.cpu().numpy().tolist(),
"objects": class_labels
}
return {"predictions": prd, "labels": lbs}
def infer(payload):
unlabeled = payload["unlabeled"]
ckpt_file = payload["ckpt_file"]
batch_size = 16
coco = COCO("./data", Transforms(), samples=unlabeled, train=True)
loader = DataLoader(coco,
shuffle=False,
batch_size=batch_size,
collate_fn=collate_fn)
config_file = "yolov3.cfg"
model = Darknet(config_file).to(device)
ckpt = torch.load(os.path.join("./log", ckpt_file))
model.load_state_dict(ckpt["model"])
model.eval()
# batch predictions from the entire test set
predictions = []
with torch.no_grad():
for img, _, _ in loader:
img = img.to(device)
# get inference output
output = model(img)
# batch predictions from 3 yolo layers
batched_prediction = []
for p in output: # (batch_size, 3, gx, gy, 85)
batch_size = p.shape[0]
p = p.view(batch_size, -1, 85)
batched_prediction.append(p)
batched_prediction = torch.cat(batched_prediction, dim=1)
predictions.append(batched_prediction)
predictions = torch.cat(predictions, dim=0)
# apply nms to predicted bounding boxes
predicted_boxes, predicted_objectness, predicted_class_dist = bbox_transform(
predictions)
# the predicted boxes are in log space relative to the anchor priors
# bring them back to normalized xyxy format
cxcy_priors = anchors.normalize("cxcy")
# expand the priors to match the dimension of predicted_boxes
batched_cxcy_priors = cxcy_priors.unsqueeze(0).repeat(
predicted_boxes.shape[0], 1, 1)
predicted_boxes = batched_gcxgcy_to_cxcy(predicted_boxes,
batched_cxcy_priors)
del batched_cxcy_priors
# convert predicted_boxes to xyxy format and perform nms
xyxy = batched_cxcy_to_xy(predicted_boxes)
del predicted_boxes # (no longer need cxcy format)
# class distribution is part of the return
# do notapply softmax to the predicted class distribution
# as we will do it internally for efficiency
outputs = {}
for i in range(len(coco)):
# get boxes, scores, and objects on each image
_xyxy, _scores = xyxy[i], predicted_objectness[i]
_pre_softmax = predicted_class_dist[i]
keep = tv.ops.nms(_xyxy, _scores, 0.5)
boxes, scores, pre_softmax = _xyxy[keep], _scores[keep], _pre_softmax[
keep]
outputs[i] = {
"boxes": boxes.cpu().numpy().tolist(),
"pre_softmax": pre_softmax.cpu().numpy().tolist(),
"scores": scores.cpu().numpy().tolist(),
}
return {"outputs": outputs}
def train(params):
params = Params(params)
set_random_seeds(params.seed)
time_now = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
params.save_root = params.save_root + f'/{params.project_name}_{time_now}_{params.version}'
os.makedirs(params.save_root, exist_ok=True)
logging.basicConfig(
filename=
f'{params.save_root}/{params.project_name}_{time_now}_{params.version}.log',
filemode='a',
format='%{asctime}s - %(levalname)s: %(message)s')
if params.num_gpus == 0:
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
logging.info(f'Available GPUs: {torch.cuda.device_count()}')
# Train pipeline
files = glob.glob(
os.path.join(params.data_root, params.project_name, params.train_set,
'*/*.JPEG'))
labels = []
for fp in files:
label = int(fp.split('/')[-2]) - 1
labels.append(label)
assert len(files) == len(labels)
train_pipeline = TrainImageDecoderPipeline(params=params,
device_id=0,
files=files,
labels=labels)
train_pipeline.build()
train_pii = pytorchIterator(train_pipeline,
last_batch_policy=LastBatchPolicy.DROP,
reader_name='Reader',
auto_reset=True)
# Evaluation pipeline
files = glob.glob(
os.path.join(params.data_root, params.project_name, params.val_set,
'*.JPEG'))
files = sorted(files,
key=lambda f: f.split('/')[-1].split('_')[-1].split('.')[0])
labels = loadlabel(
os.path.join(
params.data_root, params.project_name,
'ILSVRC2012_devkit_t12/data/ILSVRC2012_validation_ground_truth.txt'
))
eval_pipeline = EvalImageDecoderPipeline(params=params,
device_id=0,
files=files,
labels=labels)
eval_pipeline.build()
eval_pii = pytorchIterator(eval_pipeline,
last_batch_policy=LastBatchPolicy.PARTIAL,
reader_name='Reader',
auto_reset=True)
model = Darknet()
last_step = 0
last_epoch = 0
if params.load_weights != 'None':
try:
state_dict = torch.load(params.load_weights)
model.load_state_dict(state_dict)
last_step = int(params.load_weights.split('_')[-1].split('.')[0])
last_epoch = int(params.load_weights.split('_')[-2])
except:
logging.error('Fail to resuming from weight!')
exit()
if params.num_gpus > 0:
model = model.cuda()
if params.num_gpus > 1:
model = nn.DataParallel(model)
if params.optim == 'Adam':
optimizer = torch.optim.Adam(model.parameters(),
lr=params.learning_rate)
else:
optimizer = torch.optim.SGD(model.parameters(),
lr=params.learning_rate,
momentum=0.9,
nesterov=True)
criterion = nn.CrossEntropyLoss()
# ls_scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer=optimizer, factor=0.5, verbose=True, patience=8)
epoch = 0
begin_epoch = max(0, last_epoch)
step = max(0, last_step)
best_loss = 100
logging.info('Begin to train...')
model.train()
try:
for epoch in range(begin_epoch, params.epoch):
for iter, data in enumerate(train_pii):
x = data[0]['data']
label = data[0]['label'].squeeze(-1).long().cuda()
output = model(x)
loss = criterion(output, label)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if iter % params.save_interval == 0:
logging.info(
f'{datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")} '
f'Train Epoch: {epoch} iter: {iter} loss: {loss.item()}'
)
step += 1
if epoch % params.eval_interval == 0:
model.eval()
epoch_loss = 0
prediciton = []
target = []
with torch.no_grad():
for iter, data in enumerate(eval_pii):
x = data[0]['data']
label = data[0]['label'].squeeze(-1).long().cuda()
output = model(x)
loss = criterion(output, label).item()
epoch_loss += loss * x.shape[0]
prediciton.append(output)
target.append(label)
loss = epoch_loss / 50000
prediciton = torch.cat(prediciton, dim=0)
target = torch.cat(target, dim=0)
acc = top1accuracy(prediciton, target)
acctop5 = top5accuracy(prediciton, target)
logging.info(
f'{datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")} '
f'Eval Epoch: {epoch} loss: {loss} accuracy: {acc} Top5 acc: {acctop5}'
)
if loss < best_loss:
best_loss = loss
save_checkpoint(
model, f'{params.save_root}/{epoch}_{step}.pth')
model.train()
except KeyboardInterrupt:
save_checkpoint(model,
f'{params.save_root}/Interrupt_{epoch}_{step}.pth')
"D:\py_pro\YOLOv3-PyTorch\weights\kalete\ep893-map80.55-loss0.00.weights",
type=str)
parser.add_argument("--evaluation_interval",
type=int,
default=2,
help="每隔几次使用验证集")
args = parser.parse_args()
print(args)
class_names = load_classes(
r"D:\py_pro\YOLOv3-PyTorch\data\kalete\dnf_classes.txt") # 加载所有种类名称
train_path = r'D:\py_pro\YOLOv3-PyTorch\data\kalete\train.txt'
val_path = r'D:\py_pro\YOLOv3-PyTorch\data\kalete\val.txt'
print("载入网络...")
model = Darknet(args.cfg)
pretrained = True
if pretrained:
model.load_state_dict(torch.load(args.weights))
else:
# 随机初始化权重,会对模型进行高斯随机初始化
model.apply(weights_init_normal)
print("网络权重加载成功.")
# 设置网络输入图片尺寸大小与学习率
reso = int(model.net_info["height"])
lr = float(model.net_info["learning_rate"])
assert reso % 32 == 0 # 判断如果不是32的整数倍就抛出异常
assert reso > 32 # 判断如果网络输入图片尺寸小于32也抛出异常
print(opt)
#logger = Logger("logs")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
os.makedirs("output", exist_ok=True)
os.makedirs("checkpoints", exist_ok=True)
# Get data configuration
data_config = parse_data_config(opt.data_config)
train_path = data_config["train"]
valid_path = data_config["valid"]
class_names = load_classes(data_config["names"])
# Initiate model
model = Darknet(opt.model_def).to(device)
model.apply(weights_init_normal)
# If specified we start from checkpoint
if opt.pretrained_weights:
if opt.pretrained_weights.endswith(".pth"):
model.load_state_dict(torch.load(opt.pretrained_weights))
else:
model.load_darknet_weights(opt.pretrained_weights)
# Get dataloader
dataset = ListDataset(train_path,
augment=True,
multiscale=opt.multiscale_training)
dataloader = torch.utils.data.DataLoader(
dataset,
import os
import sys
weights = './pretrained.pt'
imgsz = 448
conf_thres = 0.35
iou_thres = 0.5
cfg = './cfg/yolov4-pacsp.cfg'
names = ['fire', 'smoke']
colors = [(255, 30, 0), (50, 0, 255)]
device = torch.device('cpu')
if not os.path.isfile(weights):
# Download weight 200Mb
# torch.hub.download_url_to_file('https://www.dropbox.com/s/a1puv47v6tmrk6j/weights.pt?dl=1', weights)
pass
# Load model
model = Darknet(cfg, imgsz)
# model.load_state_dict(weights)
model.to(device).eval()
source = sys.argv[1]
out = detect(model, source, './out.png', imgsz, conf_thres, iou_thres,
names, colors, device)
cv2.imshow('output', out)
cv2.waitKey(0)
cv2.destroyAllWindows()
def main():
# Hyperparameters parser
parser = argparse.ArgumentParser()
parser.add_argument("--year", type=str, default='2012', help="used to select training set")
parser.add_argument("--set", type=str, default='train', help="used to select training set")
parser.add_argument("--epochs", type=int, default=201, help="number of epochs")
parser.add_argument("--batch_size", type=int, default=8, help="size of each image batch")
parser.add_argument("--model_def", type=str, default="config/net/resnet_dropout.cfg", help="path to model definition file")
# parser.add_argument("--model_def", type=str, default="config/net/dqnyolo_large.cfg", help="path to model definition file")
# parser.add_argument("--model_def", type=str, default="config/net/dqnyolo_mini.cfg", help="path to model definition file")
# parser.add_argument("--model_def", type=str, default="config/net/dqnyolo_tiny.cfg", help="path to model definition file")
parser.add_argument("--img_size", type=int, default=416, help="size of each image dimension")
parser.add_argument("--opt_lr", type=float, default=1e-5, help="learning rate for optimizer")
parser.add_argument("--use_gpu", default=True, help="use GPU to accelerate training")
parser.add_argument("--shuffle_train", default=True, help="shuffle the training dataset")
parser.add_argument("--checkpoint_interval", type=int, default=20, help="interval between saving model weights")
parser.add_argument("--evaluation_interval", type=int, default=10, help="interval evaluations on validation set")
# parser.add_argument("--pretrained_weights", type=str, default="data/backbone/darknet53.conv.74", help="if specified starts from checkpoint model")
# parser.add_argument("--pretrained_weights", type=str, default="logs/model/model_params_200.ckpt", help="if specified starts from checkpoint model")
parser.add_argument("--pretrained_weights", default=False, help="if specified starts from checkpoint model")
opt = parser.parse_args()
print(opt)
if opt.use_gpu is True:
if torch.cuda.is_available():
device = torch.device('cuda')
else:
raise RuntimeError("Current Torch doesn't have GPU support.")
else:
device = torch.device('cpu')
logger = SummaryWriter(exist_or_create_folder("./logs/tb/"))
# Initiate model
eval_model = Darknet(opt.model_def).to(device)
if opt.pretrained_weights:
print("Initialize model with pretrained_model")
if opt.pretrained_weights.endswith(".ckpt"):
eval_model.load_state_dict(torch.load(opt.pretrained_weights))
else:
eval_model.load_darknet_weights(opt.pretrained_weights)
else:
print("Initialize model randomly")
eval_model.apply(weights_init_normal)
# eval_model.load_state_dict(torch.load("./logs/saved_exp/master-v2/model_params_80.ckpt"))
print(eval_model)
summary(eval_model, (3, 416, 416))
learn_batch_counter = 0 # for logger update (total numbers)
batch_size = opt.batch_size
# Get dataloader
print("Begin loading train dataset ......")
t_load_data = time.time()
dataset = torchvision.datasets.VOCDetection(root='data/VOC/',
year=opt.year,
image_set=opt.set,
transforms=None,
download=True)
dataset_dict = trans_voc(dataset)
dataset = ListDataset(dataset_dict)
loader = torch.utils.data.DataLoader(
dataset,
batch_size=opt.batch_size,
shuffle=opt.shuffle_train,
pin_memory=True,
collate_fn=dataset.collate_fn,
)
print("Complete loading train dataset in {} s".format(time.time() - t_load_data))
optimizer = torch.optim.Adam(eval_model.parameters(), lr=opt.opt_lr)
# Warmup and learning rate decay
scheduler_cosine = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, opt.epochs)
# 5 epoch warmup, lr from 1e-5 to 1e-4, after that schedule as after_scheduler
scheduler_warmup = GradualWarmupScheduler(optimizer, multiplier=10, total_epoch=10,
after_scheduler=scheduler_cosine)
start_time = time.time()
for i_epoch in range(opt.epochs):
eval_model.train()
for i_batch, (_, imgs, raw_targets, transform_params, tar_boxes) in enumerate(loader):
print("\n++++++++++ i_epoch-i_batch {}-{} ++++++++++".format(i_epoch, i_batch))
batch_step_counter = 0
if len(imgs) != batch_size:
print("Current batch size is smaller than opt.batch_size!")
continue
imgs = imgs.to(device)
raw_targets = raw_targets.to(device)
tar_boxes = tar_boxes.to(device)
input_img = imgs
if i_epoch == 0 and i_batch == 0:
logger.add_graph(eval_model, input_img)
# print(raw_targets)
# print(raw_targets.size())
# print(raw_targets[:, :, :, 6:].size())
# print(raw_targets[:, :, :, 0].unsqueeze(3).size())
cls_targets = torch.cat((raw_targets[:, :, :, 0].unsqueeze(3), raw_targets[:, :, :, 6:]), 3)
# print(cls_targets.size())
loss, pred = eval_model(input_img, cls_targets)
optimizer.zero_grad()
loss.backward()
optimizer.step()
batch_step_counter += 1
learn_batch_counter += 1
print("Ep-bt: {}-{} | Loss: {}".format(i_epoch, i_batch, loss.item()))
logger.add_scalar('loss/loss', loss.item(), learn_batch_counter)
if (i_epoch + 1) % opt.checkpoint_interval == 0:
print("Saving model in epoch {}".format(i_epoch))
torch.save(eval_model.state_dict(),
exist_or_create_folder("./logs/model/model_params_{}.ckpt".format(i_epoch)))
# Evaluate the model on the validation set
if (i_epoch + 1) % opt.evaluation_interval == 0:
precision, recall, AP, f1, ap_class = evaluate(
eval_model,
[opt.year, 'val'],
[0.5, 0.5, 0.5],
batch_size,
True,
diagnosis_code=1
)
evaluation_metrics = [
("val_precision", precision.mean()),
("val_recall", recall.mean()),
("val_mAP", AP.mean()),
("val_f1", f1.mean()),
]
for tag, value in evaluation_metrics:
logger.add_scalar("val/{}".format(tag), value.item(), i_epoch)
# Print class APs and mAP
ap_table = [["Index", "Class name", "AP"]]
for i, c in enumerate(ap_class):
ap_table += [[c, val2labels(c), "%.5f" % AP[i]]]
print(AsciiTable(ap_table).table)
print(f"---- validation mAP {AP.mean()}")
# Evaluate the model on the training set
if (i_epoch + 1) % opt.evaluation_interval == 0:
precision, recall, AP, f1, ap_class = evaluate(
eval_model,
[opt.year, 'train'],
[0.5, 0.5, 0.5],
batch_size,
True,
diagnosis_code=1
)
evaluation_metrics = [
("train_precision", precision.mean()),
("train_recall", recall.mean()),
("train_mAP", AP.mean()),
("train_f1", f1.mean()),
]
for tag, value in evaluation_metrics:
logger.add_scalar("train/{}".format(tag), value.item(), i_epoch)
# Print class APs and mAP
ap_table = [["Index", "Class name", "AP"]]
for i, c in enumerate(ap_class):
ap_table += [[c, val2labels(c), "%.5f" % AP[i]]]
print(AsciiTable(ap_table).table)
print(f"---- training mAP {AP.mean()}")
# Warmup and lr decay
scheduler_warmup.step()
# Free GPU memory
torch.cuda.empty_cache()
total_train_time = time.time() - start_time
print("Training complete in {} hours".format(total_train_time / 3600))
continue
#org_weights_mess.append([var_name, var_shape])
#print(var_name,var_shape)
#print("=> " + str(var_name).ljust(50), var_shape)
print()
tf.reset_default_graph()
cur_weights_mess = []
tf.Graph().as_default()
with tf.name_scope('input'):
input_data = tf.placeholder(dtype=tf.float32,
shape=(1, 416, 416, 3),
name='input_data')
#meta_weight=tf.placeholder(dtype=tf.float32,shape=(1,1,20*1024,1),name='meta_weight')
#training = tf.placeholder(dtype=tf.bool, name='trainable')
model = Darknet(input_data, False)
for var in tf.global_variables():
var_name = var.op.name
var_name_mess = str(var_name).split('/')
var_shape = var.shape
#print(var_name_mess[0])
#if flag.train_from_coco:
#if 'dyconv' in var_name_mess and 'weights' in var_name_mess:
# cur_weights_mess.append([var_name,])
if (var_name_mess[-1] not in [
'weights', 'gamma', 'beta', 'moving_mean', 'moving_variance'
]) or 'pred' in var_name_mess or 'decode' in var_name_mess:
print("===========", var_shape)
continue
#cur_weights_mess.append([var_name, var_shape])
#print("=> " + str(var_name).ljust(50), var_shape)
import os
import cv2
import torch
import numpy as np
from torch.autograd import Variable
from model import Darknet
def get_test_img():
img = cv2.imread('dog-cycle-car.png')
img = cv2.resize(img, (416, 416))
img = img[:, :, ::-1].transpose((2, 0, 1))
img = img[np.newaxis, :, :, :] / 255.
img = torch.from_numpy(img).float()
img = Variable(img)
return img
model = Darknet('config/yolov3.cfg')
img = get_test_img()
out = model(img)
print(out)
print(f'Shape:=> First YOLO:{out[0].shape} Sencond YOLO:{out[0].shape}')
def detect(kitti_weights='../checkpoints/best_weights_kitti.pth', config_path='../config/yolov3-kitti.cfg',
class_path='../data/names.txt'):
"""
Script to run inference on sample images. It will store all the inference results in /output directory (
relative to repo root)
Args
kitti_weights: Path of weights
config_path: Yolo configuration file path
class_path: Path of class names txt file
"""
cuda = torch.cuda.is_available()
os.makedirs('../output', exist_ok=True)
# Set up model
model = Darknet(config_path, img_size=416)
model.load_weights(kitti_weights)
if cuda:
model.cuda()
print("Cuda available for inference")
model.eval() # Set in evaluation mode
dataloader = DataLoader(ImageFolder("../data/samples/", img_size=416),
batch_size=2, shuffle=False, num_workers=0)
classes = load_classes(class_path) # Extracts class labels from file
Tensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor
imgs = [] # Stores image paths
img_detections = [] # Stores detections for each image index
print('data size : %d' % len(dataloader))
print('\nPerforming object detection:')
prev_time = time.time()
for batch_i, (img_paths, input_imgs) in enumerate(dataloader):
# Configure input
input_imgs = Variable(input_imgs.type(Tensor))
# Get detections
with torch.no_grad():
detections = model(input_imgs)
detections = non_max_suppression(detections, 80, 0.8, 0.4)
# print(detections)
# Log progress
current_time = time.time()
inference_time = datetime.timedelta(seconds=current_time - prev_time)
prev_time = current_time
print('\t+ Batch %d, Inference Time: %s' % (batch_i, inference_time))
# Save image and detections
imgs.extend(img_paths)
img_detections.extend(detections)
# Bounding-box colors
# cmap = plt.get_cmap('tab20b')
cmap = plt.get_cmap('tab10')
colors = [cmap(i) for i in np.linspace(0, 1, 20)]
print('\nSaving images:')
# Iterate through images and save plot of detections
for img_i, (path, detections) in enumerate(zip(imgs, img_detections)):
print("(%d) Image: '%s'" % (img_i, path))
# Create plot
img = np.array(Image.open(path))
plt.figure()
fig, ax = plt.subplots(1)
ax.imshow(img)
kitti_img_size = 416
# The amount of padding that was added
pad_x = max(img.shape[0] - img.shape[1], 0) * (kitti_img_size / max(img.shape))
pad_y = max(img.shape[1] - img.shape[0], 0) * (kitti_img_size / max(img.shape))
# Image height and width after padding is removed
unpad_h = kitti_img_size - pad_y
unpad_w = kitti_img_size - pad_x
# Draw bounding boxes and labels of detections
if detections is not None:
print(type(detections))
print(detections.size())
unique_labels = detections[:, -1].cpu().unique()
n_cls_preds = len(unique_labels)
bbox_colors = random.sample(colors, n_cls_preds)
for x1, y1, x2, y2, conf, cls_conf, cls_pred in detections:
print('\t+ Label: %s, Conf: %.5f' % (classes[int(cls_pred)], cls_conf.item()))
# Rescale coordinates to original dimensions
box_h = int(((y2 - y1) / unpad_h) * (img.shape[0]))
box_w = int(((x2 - x1) / unpad_w) * (img.shape[1]))
y1 = int(((y1 - pad_y // 2) / unpad_h) * (img.shape[0]))
x1 = int(((x1 - pad_x // 2) / unpad_w) * (img.shape[1]))
color = bbox_colors[int(np.where(unique_labels == int(cls_pred))[0])]
# Create a Rectangle patch
bbox = patches.Rectangle((x1, y1), box_w, box_h, linewidth=2,
edgecolor=color,
facecolor='none')
# Add the bbox to the plot
ax.add_patch(bbox)
# Add label
plt.text(x1, y1 - 30, s=classes[int(cls_pred)] + ' ' + str('%.4f' % cls_conf.item()), color='white',
verticalalignment='top',
bbox={'color': color, 'pad': 0})
# Save generated image with detections
plt.axis('off')
plt.gca().xaxis.set_major_locator(NullLocator())
plt.gca().yaxis.set_major_locator(NullLocator())
plt.savefig('../output/%d.png' % (img_i), bbox_inches='tight', pad_inches=0.0)
plt.close()
def main(train_path="../data/train/images/",
val_path="../data/train/images/",
labels_path="../data/train/yolo_labels/",
weights_path="../checkpoints/",
preload_weights_file="darknet53.conv.74",
output_path="../output",
yolo_config_file="../config/yolov3-kitti.cfg",
fraction=1,
learning_rate=1e-3,
weight_decay=1e-4,
batch_size=2,
epochs=30,
freeze_struct=[True, 5]):
"""
This is the point of entry to the neural network program.
All the training history will be saved as a csv in the output path
Args
train_path (string): Directory containing the training images
val_path (string):: Directory containing the val images
labels_path (string):: Directory containing the yolo format labels for data
weights_path (string):: Directory containing the weights (new weights for this program will also be added here)
preload_weights_file (string): Name of preload weights file
output_path (string): Directory to store the training history outputs as csv
yolo_config_file (string): file path of yolo configuration file
fraction (float): fraction of data to use for training
learning_rate (float): initial learning rate
weight_decay (float): weight decay value
batch_size (int): batch_size for both training and validation
epochs (int): maximum number of epochs to train the model
freeze_struct (list): [bool, int] indicating whether to freeze the Darknet backbone and until which epoch should it be frozen
Returns
None
"""
# Set up checkpoints path
checkpoints_path = weights_path
# Set up env variables and create required directories
os.makedirs(output_path, exist_ok=True)
os.makedirs(checkpoints_path, exist_ok=True)
# Set up cuda
use_cuda = torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")
print("Available device = ", device)
# Create model and load pretrained darknet weights
model = Darknet(yolo_config_file)
print("Loading imagenet weights to darknet")
model.load_weights(os.path.join(weights_path, preload_weights_file))
model.to(device)
#print(model)
# Create datasets
train_dataset = KITTI2D(train_path,
labels_path,
fraction=fraction,
train=True)
valid_dataset = KITTI2D(val_path,
labels_path,
fraction=fraction,
train=False)
# Create dataloaders
train_dataloader = DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True)
valid_dataloader = DataLoader(valid_dataset,
batch_size=batch_size,
shuffle=False)
# Create optimizers
optimizer = torch.optim.Adam(filter(lambda p: p.requires_grad,
model.parameters()),
lr=learning_rate,
weight_decay=weight_decay)
lr_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, 10)
# Create log csv files
train_log_file = open(os.path.join(output_path, "train_results.csv"),
"w",
newline="")
valid_log_file = open(os.path.join(output_path, "valid_results.csv"),
"w",
newline="")
train_csv = csv.writer(train_log_file)
valid_csv = csv.writer(valid_log_file)
print("Starting to train yolov3 model...")
# Train model here
train_model(model,
device,
optimizer,
lr_scheduler,
train_dataloader,
valid_dataloader,
train_csv,
valid_csv,
weights_path,
max_epochs=epochs,
tensor_type=torch.cuda.FloatTensor,
update_gradient_samples=1,
freeze_darknet=freeze_struct[0],
freeze_epoch=freeze_struct[1])
# Close the log files
train_log_file.close()
valid_log_file.close()
print("Training completed")
help="the image to predict (default: %(default)s)")
parser.add_argument("--weight", required=True, metavar="/path/to/yolov4.weights", help="the path of weight file")
parser.add_argument("--save-img", metavar="predicted-img", help="the path to save predicted image")
args = parser.parse_args()
return args
if __name__ == "__main__":
args = parse_args()
img: Image.Image = Image.open(args.img_file)
img = img.resize((608, 608))
# C*H*W
img_data = to_image(img)
net = Darknet(img_data.size(0))
net.load_weights(args.weight)
net.eval()
with torch.no_grad():
boxes, confs = net(img_data.unsqueeze(0))
idxes_pred, boxes_pred, probs_pred = utils.post_processing(boxes, confs, 0.4, 0.6)
utils.plot_box(boxes_pred, args.img_file, args.save_img)
map(pre_img, loaded_imgs, [height for i in range(len(loaded_imgs))]))
left_over = 0
if (len(loaded_imgs) % batch_size):
left_over = 1
num_batches = (len(loaded_imgs) // batch_size) + left_over
batches = [
det_imgs[i * batch_size:min((i + 1) * batch_size, len(loaded_imgs))]
for i in range(num_batches)
]
batches = [torch.cat(batch, 0) for batch in batches]
net = Darknet()
net = net.cuda()
net.load_weights()
net.eval()
write = 0
def put_rectangle(x, results):
c1 = tuple(x[1:3].int())
c2 = tuple(x[3:5].int())
img = results[int(x[0])]
cls = int(x[-1])
label = "{0}".format(classes[cls])
cv2.rectangle(img, c1, c2, [255, 0, 0], 1)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 1, 1)[0]
def detect_images(widget=None):
if not widget:
args = arg_parse()
else:
args = widget.args
read_dir = time.time()
print_info(widget, False, "info", "Reading addresses.....")
images = args.images
im_list = []
img = None
try:
for img in images:
if os.path.isabs(img):
im_list.append(img)
else:
im_list.append(osp.join(osp.realpath('.'), img))
except FileNotFoundError:
print_info(widget, True, "error", "No file or directory with the name {}".format(img))
if not os.path.exists(args.det):
os.makedirs(args.det)
print_info(widget, False, "info", "Finished reading addresses")
finish_read_dir = time.time()
batch_size = int(args.bs)
confidence = float(args.confidence)
nms_thesh = float(args.nms_thresh)
namesfile = args.names
cuda_present = torch.cuda.is_available()
classes = load_classes(namesfile)
num_classes = len(classes)
# Set up the neural network
load_net = time.time()
print_info(widget, False, "info", "Loading network.....")
model = Darknet(args.cfg)
model.load_weights(args.weights)
print_info(widget, False, "info", "Network successfully loaded")
finish_load_net = time.time()
model.net_info["height"] = args.reso
model.net_info["width"] = args.reso
inp_dim = int(model.net_info["height"])
assert inp_dim % 32 == 0
assert inp_dim > 32
# If there's a GPU availible, put the model on GPU
if cuda_present:
model.cuda()
# Set the model in evaluation mode (for Batchnorm layers)
model.eval()
# Detection phase
load_batch = time.time()
print_info(widget, False, "info", "Loading batches.....")
loaded_ims = [cv2.imread(x) for x in im_list]
im_batches = list(map(prep_image, loaded_ims, [inp_dim for _ in range(len(im_list))]))
im_dim_list = [(x.shape[1], x.shape[0]) for x in loaded_ims]
im_dim_list = torch.FloatTensor(im_dim_list).repeat(1, 2)
leftover = 0
if len(im_dim_list) % batch_size:
leftover = 1
if batch_size != 1:
num_batches = len(im_list) // batch_size + leftover
im_batches = [torch.cat((im_batches[i * batch_size: min((i + 1) * batch_size,
len(im_batches))])) for i in range(num_batches)]
if cuda_present:
im_dim_list = im_dim_list.cuda()
output = torch.empty((0, 0))
print_info(widget, False, "info", "Finished loading batches....")
start_det_loop = time.time()
for i, batch in enumerate(im_batches):
# load the image
start = time.time()
print_info(widget, False, "info", f"Detecting batch no {i}....")
if cuda_present:
batch = batch.cuda()
with torch.no_grad():
prediction = model(batch, cuda_present)
prediction = write_results(prediction, confidence, num_classes, nms_conf=nms_thesh)
end = time.time()
if type(prediction) == int:
for im_num, image in enumerate(im_list[i * batch_size: min((i + 1) * batch_size, len(im_list))]):
im_id = i * batch_size + im_num
msg = "{0:20s} predicted in {1:6.3f} seconds".format(image.split("/")[-1], (end - start) / batch_size)
msg += "\n{0:20s} {1:s}".format("Objects Detected:", "")
msg += "\n----------------------------------------------------------"
print_info(widget, False, 'batch_info', msg, im_id)
continue
prediction[:, 0] += i * batch_size # transform the atribute from index in batch to index in imlist
if np.size(output, 0) == 0: # If we have't initialised output
output = prediction
else:
output = torch.cat((output, prediction))
for im_num, image in enumerate(im_list[i * batch_size: min((i + 1) * batch_size, len(im_list))]):
im_id = i * batch_size + im_num
objs = [classes[int(x[-1])] for x in output if int(x[0]) == im_id]
msg = "{0:20s} predicted in {1:6.3f} seconds".format(image.split("/")[-1], (end - start) / batch_size)
msg += "\n{0:20s} {1:s}".format("Objects Detected:", " ".join(objs))
msg += "\n----------------------------------------------------------"
print_info(widget, False, 'batch_info', msg, im_id)
if cuda_present:
torch.cuda.synchronize()
print_info(widget, False, "info", f"Finished detecting batch no {i}")
if np.size(output, 0) == 0:
print_info(widget, False, 'no_detections', "No detections were made")
print_info(widget, False, 'finished')
return
# Start rescaling
print_info(widget, False, "info", "Output processing....")
output_rescale = time.time()
im_dim_list = torch.index_select(im_dim_list, 0, output[:, 0].long())
scaling_factor = torch.min(inp_dim / im_dim_list, 1)[0].view(-1, 1)
output[:, [1, 3]] -= (inp_dim - scaling_factor * im_dim_list[:, 0].view(-1, 1)) / 2
output[:, [2, 4]] -= (inp_dim - scaling_factor * im_dim_list[:, 1].view(-1, 1)) / 2
output[:, 1:5] /= scaling_factor
# set padding space black
for i in range(output.shape[0]):
output[i, [1, 3]] = torch.clamp(output[i, [1, 3]], 0.0, im_dim_list[i, 0])
output[i, [2, 4]] = torch.clamp(output[i, [2, 4]], 0.0, im_dim_list[i, 1])
class_load = time.time()
print_info(widget, False, "info", "Finished output processing.")
# Start draw
print_info(widget, False, "info", "Drawing boxes....")
draw = time.time()
images_handler = ImagesHandler(classes, output, loaded_ims, args.det, im_list, batch_size)
images_handler.write()
print_info(widget, False, "images_ready", images_handler.imageList)
end = time.time()
print_info(widget, False, "info", "Finished drawing boxes")
msg = "\n\nSUMMARY"
msg += "\n----------------------------------------------------------"
msg += "\n{:25s}: {}".format("Task", "Time Taken (in seconds)")
msg += "\n"
msg += "\n{:25s}: {:2.3f}".format("Reading addresses", finish_read_dir - read_dir)
msg += "\n{:25s}: {:2.3f}".format("Loading network", finish_load_net - load_net)
msg += "\n{:25s}: {:2.3f}".format("Loading batch", start_det_loop - load_batch)
msg += "\n{:25s}: {:2.3f}".format("Detection (" + str(len(im_list)) + " images)", output_rescale - start_det_loop)
msg += "\n{:25s}: {:2.3f}".format("Output Processing", class_load - output_rescale)
msg += "\n{:25s}: {:2.3f}".format("Drawing Boxes", end - draw)
msg += "\n{:25s}: {:2.3f}".format("Average time_per_img", (end - load_batch) / len(im_list))
msg += "\n----------------------------------------------------------"
print_info(widget, False, 'info', msg)
torch.cuda.empty_cache()
print_info(widget, False, 'finished')
def train(payload):
labeled = payload["labeled"]
resume_from = payload["resume_from"]
ckpt_file = payload["ckpt_file"]
# hyperparameters
batch_size = 16
epochs = 2 # just for demo
lr = 1e-2
weight_decay = 1e-2
coco = COCO("./data", Transforms(), samples=labeled, train=True)
loader = DataLoader(coco,
shuffle=True,
batch_size=batch_size,
collate_fn=collate_fn)
config_file = "yolov3.cfg"
model = Darknet(config_file).to(device)
optimizer = optim.Adam(model.parameters(),
lr=lr,
weight_decay=weight_decay)
# resume model and optimizer from previous loop
if resume_from is not None:
ckpt = torch.load(os.path.join("./log", resume_from))
model.load_state_dict(ckpt["model"])
optimizer.load_state_dict(ckpt["optimizer"])
# loss function
priors = anchors.normalize("xyxy")
loss_fn = HardNegativeMultiBoxesLoss(priors, device=device)
model.train()
for img, boxes, labels in loader:
img = img.to(device)
# 3 predictions from 3 yolo layers
output = model(img)
# batch predictions on each image
batched_prediction = []
for p in output: # (batch_size, 3, gx, gy, 85)
batch_size = p.shape[0]
p = p.view(batch_size, -1, 85)
batched_prediction.append(p)
batched_prediction = torch.cat(batched_prediction, dim=1)
# (batch_size, n_priors, 85)
# the last dim of batched_prediction represent the predicted box
# batched_prediction[...,:4] is the coordinate of the predicted bbox
# batched_prediction[...,4] is the objectness score
# batched_prediction[...,5:] is the pre-softmax class distribution
# we need to apply some transforms to the those predictions
# before we can use HardNegativeMultiBoxesLoss
# In particular, the predicted bbox need to be relative to
# normalized anchor priors
# we will define another function bbox_transform
# to do those transform, since it will be used by other processes
# as well.
# see documentation on HardNegativeMultiBoxesLoss
# on its input parameters
predicted_boxes, predicted_objectness, predicted_class_dist = bbox_transform(
batched_prediction)
loss = loss_fn(predicted_boxes, predicted_objectness,
predicted_class_dist, boxes, labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
# save ckpt for this loop
ckpt = {"model": model.state_dict(), "optimizer": optimizer.state_dict()}
torch.save(ckpt, os.path.join("./log", ckpt_file))
return