from configs.CC import Config
from tqdm import tqdm
from utils.core import *
parser = argparse.ArgumentParser(description='M2Det Testing')
parser.add_argument('-c', '--config', default='configs/m2det320_vgg.py', type=str)
parser.add_argument('-d', '--dataset', default='COCO', help='VOC or COCO version')
parser.add_argument('-m', '--trained_model', default=None, type=str, help='Trained state_dict file path to open')
parser.add_argument('--test', action='store_true', help='to submit a test file')
args = parser.parse_args()
print_info('----------------------------------------------------------------------\n'
'| M2Det Evaluation Program |\n'
'----------------------------------------------------------------------', ['yellow','bold'])
global cfg
cfg = Config.fromfile(args.config)
if not os.path.exists(cfg.test_cfg.save_folder):
os.mkdir(cfg.test_cfg.save_folder)
anchor_config = anchors(cfg)
print_info('The Anchor info: \n{}'.format(anchor_config))
priorbox = PriorBox(anchor_config)
with torch.no_grad():
priors = priorbox.forward()
if cfg.test_cfg.cuda:
priors = priors.cuda()
def test_net(save_folder, net, detector, cuda, testset, transform, max_per_image=300, thresh=0.005):
if not os.path.exists(save_folder):
os.mkdir(save_folder)
num_images = len(testset)
difficult = False
else:
difficult = int(obj.find('difficult').text) == 1
if not self.keep_difficult and difficult:
continue
name = obj.find('name').text.lower().strip()
bbox = obj.find('bndbox')
pts = ['xmin', 'ymin', 'xmax', 'ymax']
bndbox = []
for i, pt in enumerate(pts):
cur_pt = int(bbox.find(pt).text) - 1
bndbox.append(cur_pt)
label_idx = self.class_names.index(name)
bndbox.append(label_idx)
res = np.vstack((res,bndbox)) # [xmin, ymin, xmax, ymax, label_ind]
return res # [[xmin, ymin, xmax, ymax, label_ind], ... ]
if __name__ == '__main__':
from configs.CC import Config
from utils.core import config_compile
from data import preproc
cfg = Config.fromfile("./configs/m2det320_resnet101.py")
config_compile(cfg)
_preproc = preproc(cfg.model.input_size, cfg.model.rgb_means, cfg.model.p)
dataset = GeneralImageDataset(root_dir="./dataset",
class_names=cfg.model.m2det_config.class_names,
transforms=_preproc)
print(dataset[0])
v,
kernel_size=3,
stride=stride[k],
padding=padding[k])
]
else:
layers += [
conv_relu(in_channels,
v,
kernel_size=3,
stride=stride[k],
padding=padding[k])
]
in_channels = v
return layers
if __name__ == "__main__":
"""Testing
"""
cfg = Config.fromfile('configs/Pelee_VOC.py')
model = ShuffleNet("test", 304, cfg.model)
#init_net(model, cfg, None)
dummy_input = torch.rand([10, 3, 304, 304])
#with SummaryWriter(comment='ShuffleNet') as w:
# w.add_graph(model, (dummy_input,), verbose=True)
y = model(dummy_input)
g = make_dot(y)
g.view()
from configs.CC import Config
global cfg
cfg = Config.fromfile("m2det320_vgg.py")
print(cfg.model.input_size)
print(cfg.model.m2det_config)
def Model_Params(self, model_dir="output", use_gpu=True):
'''
User Function - Set Model Params
Args:
model_dir (str): Select the right model name as per training
model_path (str): Relative path to params file
use_gpu (bool): If True use GPU else run on CPU
Returns:
None
'''
f = open(model_dir +"/config_final.py", 'r');
lines = f.read();
f.close();
if(not use_gpu):
lines = lines.replace("cuda=True",
"cuda=False");
f = open(model_dir +"/config_test.py", 'w');
f.write(lines);
f.close();
print("Loading model for inference");
self.system_dict["cfg"] = Config.fromfile(model_dir +"/config_test.py")
anchor_config = anchors(self.system_dict["cfg"].model)
self.system_dict["priorbox"] = PriorBox(anchor_config)
self.system_dict["net"] = build_net('test', self.system_dict["cfg"].model.input_size, self.system_dict["cfg"].model)
init_net(self.system_dict["net"], self.system_dict["cfg"], model_dir + "/VOC/Final_Pelee_VOC_size304.pth")
print_info('===> Finished constructing and loading model', ['yellow', 'bold'])
self.system_dict["net"].eval()
with torch.no_grad():
self.system_dict["priors"] = self.system_dict["priorbox"].forward()
if self.system_dict["cfg"].test_cfg.cuda:
self.system_dict["net"] = self.system_dict["net"].cuda()
self.system_dict["priors"] = self.system_dict["priors"].cuda()
cudnn.benchmark = True
else:
self.system_dict["net"] = self.system_dict["net"].cpu()
self.system_dict["_preprocess"] = BaseTransform(self.system_dict["cfg"].model.input_size,
self.system_dict["cfg"].model.rgb_means, (2, 0, 1))
self.system_dict["num_classes"] = self.system_dict["cfg"].model.num_classes
self.system_dict["detector"] = Detect(self.system_dict["num_classes"],
self.system_dict["cfg"].loss.bkg_label, anchor_config)
print("Done....");
print("Loading other params");
base = int(np.ceil(pow(self.system_dict["num_classes"], 1. / 3)))
self.system_dict["colors"] = [self._to_color(x, base)
for x in range(self.system_dict["num_classes"])]
cats = ['__background__'];
f = open(self.system_dict["class_list"]);
lines = f.readlines();
f.close();
for i in range(len(lines)):
if(lines != ""):
cats.append(lines[i][:len(lines[i])-1])
self.system_dict["labels"] = cats;
print("Done....");
from darknet_dnn.msg import *
from cv_bridge import CvBridge, CvBridgeError
#parameters
show_result = rospy.get_param("/m2det_ros/show_result")
subscribe_image = rospy.get_param("/m2det_ros/subscribe_image")
print_info(
' -------------------------------------------------------------\n'
'| M2Det ROS |\n'
' -------------------------------------------------------------',
['blue', 'bold'])
global cfg
#cfg = Config.fromfile(args.config)
cfg = Config.fromfile(
roslib.packages.get_pkg_dir("m2det_ros") + "/configs/m2det512_vgg.py")
anchor_config = anchors(cfg)
print_info('The Anchor info: \n{}'.format(anchor_config))
priorbox = PriorBox(anchor_config)
net = build_net('test',
size=cfg.model.input_size,
config=cfg.model.m2det_config)
#init_net(net, cfg, args.trained_model)
init_net(
net, cfg,
roslib.packages.get_pkg_dir("m2det_ros") + "/weights/m2det512_vgg.pth")
print_info('===> Finished constructing and loading model', ['yellow', 'bold'])
net.eval()
with torch.no_grad():
priors = priorbox.forward()
import cv2
from configs.CC import Config
import time
#import boto3
#endpoint='m2det-endpoint'
#runtime_client = boto3.client('sagemaker-runtime')
#response = runtime_client.invoke_endpoint(EndpointName=endpoint,
# Body=img_encoded.tostring(), ContentType='text/csv')
##files= {'image': open(sys.argv[1], 'rb')}
##r = requests.post(url, files=files)
#print(response['Body'].read().decode('ascii'))
global cfg
cfg = Config.fromfile('configs/m2det512_vgg.py')
def _to_color(indx, base):
""" return (b, r, g) tuple"""
base2 = base * base
b = 2 - indx / base2
r = 2 - (indx % base2) / base
g = 2 - (indx % base2) % base
return b * 127, r * 127, g * 127
print(cfg.model.m2det_config.num_classes)
base = int(np.ceil(pow(cfg.model.m2det_config.num_classes, 1. / 3)))
colors = [
_to_color(x, base) for x in range(cfg.model.m2det_config.num_classes)
def setup(self):
f = open(
"Monk_Object_Detection/15_pytorch_peleenet/lib/configs/Pelee_VOC.py"
)
lines = f.read()
f.close()
lines = lines.replace(
"save_epochs=10",
"save_epochs=" + str(self.system_dict["params"]["num_epochs"]))
lines = lines.replace(
"print_epochs=10",
"print_epochs=" + str(self.system_dict["params"]["num_epochs"]))
lines = lines.replace(
"weights_save='weights/'", "weights_save='" +
self.system_dict["params"]["model_output_dir"] + "/'")
if (self.system_dict["params"]["use_gpu"]):
lines = lines.replace("cuda=True", "cuda=True")
else:
lines = lines.replace("cuda=True", "cuda=False")
lines = lines.replace(
"per_batch_size=64",
"per_batch_size=" + str(self.system_dict["params"]["batch_size"]))
lines = lines.replace(
"num_workers=8",
"num_workers=" + str(self.system_dict["params"]["num_workers"]))
f = open("config.py", 'w')
f.write(lines)
f.close()
self.system_dict["local"]["cfg"] = Config.fromfile("config.py")
print_info('===> Loading Dataset...', ['yellow', 'bold'])
self.system_dict["local"]["dataset"] = get_dataloader(
self.system_dict["local"]["cfg"],
train_img_dir=self.system_dict["params"]["train_img_dir"],
train_anno_dir=self.system_dict["params"]["train_anno_dir"],
class_file=self.system_dict["params"]["class_file"])
print_info('===> Done...', ['yellow', 'bold'])
print_info('===> Setting up epoch details...', ['yellow', 'bold'])
self.system_dict["local"]["epoch_size"] = len(
self.system_dict["local"]["dataset"]) // (
self.system_dict["local"]["cfg"].train_cfg.per_batch_size *
self.system_dict["params"]["ngpu"])
self.system_dict["local"]["max_iter"] = self.system_dict["local"][
"epoch_size"] * self.system_dict["params"]["num_epochs"]
self.system_dict["local"]["stepvalues"] = [
self.system_dict["local"]["max_iter"] // 3,
2 * self.system_dict["local"]["max_iter"] // 3
]
f = open("config.py")
lines = f.read()
f.close()
lines = lines.replace(
"step_lr=[80000, 100000, 120000,160000]",
"step_lr=" + str(self.system_dict["local"]["stepvalues"]))
lines = lines.replace(
"num_classes=21", "num_classes=" +
str(len(self.system_dict["local"]["dataset"].class_to_ind)))
lines = lines.replace("lr=5e-3",
"lr=" + str(self.system_dict["params"]["lr"]))
lines = lines.replace(
"gamma=0.1", "gamma=" + str(self.system_dict["params"]["gamma"]))
lines = lines.replace(
"momentum=0.9",
"momentum=" + str(self.system_dict["params"]["momentum"]))
lines = lines.replace(
"weight_decay=0.0005",
"weight_decay=" + str(self.system_dict["params"]["weight_decay"]))
f = open("config_final.py", 'w')
f.write(lines)
f.close()
print_info('===> Done...', ['yellow', 'bold'])
self.system_dict["local"]["cfg"] = Config.fromfile("config_final.py")
#print(self.system_dict["local"]["cfg"])
self.system_dict["local"]["net"] = build_net(
'train', self.system_dict["local"]["cfg"].model.input_size,
self.system_dict["local"]["cfg"].model)
if (self.system_dict["params"]["resume_net"]):
init_net(self.system_dict["local"]["net"],
self.system_dict["local"]["cfg"],
self.system_dict["params"]
["resume_net"]) # init the network with pretrained
if self.system_dict["params"]["ngpu"] > 1:
self.system_dict["local"]["net"] = torch.nn.DataParallel(
self.system_dict["local"]["net"])
if self.system_dict["local"]["cfg"].train_cfg.cuda:
self.system_dict["local"]["net"].cuda()
cudnn.benckmark = True
self.system_dict["local"]["optimizer"] = set_optimizer(
self.system_dict["local"]["net"], self.system_dict["local"]["cfg"])
self.system_dict["local"]["criterion"] = set_criterion(
self.system_dict["local"]["cfg"])
self.system_dict["local"]["priorbox"] = PriorBox(
anchors(self.system_dict["local"]["cfg"].model))
with torch.no_grad():
self.system_dict["local"]["priors"] = self.system_dict["local"][
"priorbox"].forward()
if self.system_dict["local"]["cfg"].train_cfg.cuda:
self.system_dict["local"]["priors"] = self.system_dict[
"local"]["priors"].cuda()
def detect_parking_spaces(dir,
threshold=0.2,
save=False,
show=False,
cam=-1,
gpu=False,
config='training/m2det/configs/m2det512_vgg.py',
weights='training/m2det/weights/m2det512_vgg.pth'):
print('Detect Parking Spaces Programe')
cfg = Config.fromfile(config)
anchor_config = anchors(cfg)
priorbox = PriorBox(anchor_config)
net = build_net('test',
size=cfg.model.input_size,
config=cfg.model.m2det_config)
init_net(net, cfg, weights)
net.eval()
if not gpu:
cfg.test_cfg.cuda = False
with torch.no_grad():
priors = priorbox.forward()
if cfg.test_cfg.cuda:
net = net.cuda()
priors = priors.cuda()
cudnn.benchmark = True
else:
net = net.cpu()
print_info('===> Finished constructing and loading model')
_preprocess = BaseTransform(cfg.model.input_size, cfg.model.rgb_means,
(2, 0, 1))
detector = Detect(cfg.model.m2det_config.num_classes, cfg.loss.bkg_label,
anchor_config)
base = int(np.ceil(pow(cfg.model.m2det_config.num_classes, 1. / 3)))
colors = [
_to_color(x, base) for x in range(cfg.model.m2det_config.num_classes)
]
cats = [
_.strip().split(',')[-1]
for _ in open('training/m2det/data/coco_labels.txt', 'r').readlines()
]
labels = tuple(['__background__'] + cats)
im_path = dir + '/images'
cam = cam
if cam >= 0:
capture = cv2.VideoCapture(cam)
im_fnames = sorted((fname for fname in os.listdir(im_path)
if os.path.splitext(fname)[-1] == '.jpg'))
im_fnames = (os.path.join(im_path, fname) for fname in im_fnames)
im_iter = iter(im_fnames)
save_dir = dir + '/detection_images'
os.makedirs(save_dir, exist_ok=True)
locs_list = {}
while True:
if cam < 0:
try:
fname = next(im_iter)
except StopIteration:
break
image = cv2.imread(fname, cv2.IMREAD_COLOR)
else:
ret, image = capture.read()
if not ret:
cv2.destroyAllWindows()
capture.release()
break
loop_start = time.time()
w, h = image.shape[1], image.shape[0]
img = _preprocess(image).unsqueeze(0)
if cfg.test_cfg.cuda:
img = img.cuda()
scale = torch.Tensor([w, h, w, h])
out = net(img)
if not gpu:
priors = priors.cpu()
boxes, scores = detector.forward(out, priors)
boxes = (boxes[0] * scale).cpu().numpy()
scores = scores[0].cpu().numpy()
allboxes = []
for j in range(1, cfg.model.m2det_config.num_classes):
inds = np.where(scores[:, j] > cfg.test_cfg.score_threshold)[0]
if len(inds) == 0:
continue
c_bboxes = boxes[inds]
c_scores = scores[inds, j]
c_dets = np.hstack(
(c_bboxes, c_scores[:, np.newaxis])).astype(np.float32,
copy=False)
soft_nms = cfg.test_cfg.soft_nms
keep = nms(
c_dets, cfg.test_cfg.iou, force_cpu=soft_nms
) #min_thresh, device_id=0 if cfg.test_cfg.cuda else None)
keep = keep[:cfg.test_cfg.keep_per_class]
c_dets = c_dets[keep, :]
allboxes.extend([_.tolist() + [j] for _ in c_dets])
loop_time = time.time() - loop_start
allboxes = np.array(allboxes)
boxes = allboxes[:, :4]
scores = allboxes[:, 4]
cls_inds = allboxes[:, 5]
# print('\n'.join(['pos:{}, ids:{}, score:{:.3f}'.format('(%.1f,%.1f,%.1f,%.1f)' % (o[0],o[1],o[2],o[3]) \
# ,labels[int(oo)],ooo) for o,oo,ooo in zip(boxes,cls_inds,scores)]))
fps = 1.0 / float(loop_time) if cam >= 0 else -1
im2show, loc = draw_detection(image,
boxes,
scores,
cls_inds,
fps,
threshold,
colors=colors,
labels=labels)
locs_list[fname] = loc
if im2show.shape[0] > 1100:
im2show = cv2.resize(im2show, (int(
1000. * float(im2show.shape[1]) / im2show.shape[0]), 1000))
if show:
cv2.imshow('test', im2show)
if cam < 0:
cv2.waitKey(1000)
else:
if cv2.waitKey(1) & 0xFF == ord('q'):
cv2.destroyAllWindows()
capture.release()
break
if save:
name = fname.split('.')[0]
name = name.split('/')[-1]
cv2.imwrite(f"{save_dir}/{name}.jpg", im2show)
save_name = dir + '/labels/split.txt'
f = open(save_name, 'wb')
pickle.dump(locs_list, f)
f.close()
def train(cfg):
cfg = Config.fromfile(cfg)
net = build_net(
'train',
size=cfg.model.input_size, # Only 320, 512, 704 and 800 are supported
config=cfg.model.m2det_config)
net.to(device)
if os.path.exists(checkpoint_path):
checkpoints = torch.load(checkpoint_path)
net.load_state_dict(checkpoints)
logging.info('checkpoint loaded.')
optimizer = optim.SGD(net.parameters(),
lr=cfg.train_cfg.lr[0],
momentum=cfg.optimizer.momentum,
weight_decay=cfg.optimizer.weight_decay)
criterion = MultiBoxLoss(cfg.model.m2det_config.num_classes,
overlap_thresh=cfg.loss.overlap_thresh,
prior_for_matching=cfg.loss.prior_for_matching,
bkg_label=cfg.loss.bkg_label,
neg_mining=cfg.loss.neg_mining,
neg_pos=cfg.loss.neg_pos,
neg_overlap=cfg.loss.neg_overlap,
encode_target=cfg.loss.encode_target)
priorbox = PriorBox(anchors(cfg))
with torch.no_grad():
priors = priorbox.forward().to(device)
net.train()
dataset = get_dataloader(cfg, 'COCO', 'train_sets')
train_ds = DataLoader(dataset,
cfg.train_cfg.per_batch_size,
shuffle=True,
num_workers=0,
collate_fn=detection_collate)
logging.info('dataset loaded, start to train...')
for epoch in range(cfg.model.epochs):
for i, data in enumerate(train_ds):
try:
lr = adjust_learning_rate_v2(optimizer, epoch, i, 10320, cfg)
images, targets = data
images = images.to(device)
targets = [anno.to(device) for anno in targets]
out = net(images)
optimizer.zero_grad()
loss_l, loss_c = criterion(out, priors, targets)
loss = loss_l + loss_c
loss.backward()
optimizer.step()
if i % 30 == 0:
logging.info(
'Epoch: {}, iter: {}, loc_loss: {}, conf_loss: {}, loss: {}, lr: {}'
.format(epoch, i, loss_l.item(), loss_c.item(),
loss.item(), lr))
if iter % 2000 == 0:
torch.save(net.state_dict(), checkpoint_path)
logging.info('model saved.')
except KeyboardInterrupt:
torch.save(net.state_dict(), checkpoint_path)
logging.info('model saved.')
exit(0)
torch.save(net.state_dict(), checkpoint_path)