def cal_mae(img_root,gt_dmap_root,model_param_path):
'''
Calculate the MAE of the test data.
img_root: the root of test image data.
gt_dmap_root: the root of test ground truth density-map data.
model_param_path: the path of specific mcnn parameters.
'''
device=torch.device("cpu")
model=CANNet()
model.load_state_dict(torch.load(model_param_path))
model.to(device)
dataset=CrowdDataset(img_root,gt_dmap_root,8,phase='test')
dataloader=torch.utils.data.DataLoader(dataset,batch_size=1,shuffle=False)
model.eval()
mae=0
with torch.no_grad():
for i,(img,gt_dmap) in enumerate(tqdm(dataloader)):
img=img.to(device)
gt_dmap=gt_dmap.to(device)
# forward propagation
et_dmap=model(img)
mae+=abs(et_dmap.data.sum()-gt_dmap.data.sum()).item()
del img,gt_dmap,et_dmap
print("model_param_path:"+model_param_path+" mae:"+str(mae/len(dataloader)))
def estimate_density_map(img_root,gt_dmap_root,model_param_path,index):
'''
Show one estimated density-map.
img_root: the root of test image data.
gt_dmap_root: the root of test ground truth density-map data.
model_param_path: the path of specific mcnn parameters.
index: the order of the test image in test dataset.
'''
device=torch.device("cuda")
model=CANNet().to(device)
model.load_state_dict(torch.load(model_param_path))
dataset=CrowdDataset(img_root,gt_dmap_root,8,phase='test')
dataloader=torch.utils.data.DataLoader(dataset,batch_size=1,shuffle=False)
model.eval()
for i,(img,gt_dmap) in enumerate(dataloader):
if i==index:
img=img.to(device)
gt_dmap=gt_dmap.to(device)
# forward propagation
et_dmap=model(img).detach()
et_dmap=et_dmap.squeeze(0).squeeze(0).cpu().numpy()
print(et_dmap.shape)
plt.imshow(et_dmap,cmap=CM.jet)
plt.show()
break
def main_live(args):
capture = cv2.VideoCapture(args.stream)
num_gpus = torch.cuda.device_count()
device = 'cuda' if num_gpus >= 1 else 'cpu'
model = CANNet().to(device)
model.load_state_dict(
torch.load(args.weights, map_location=torch.device(device)))
transform = transforms.Compose([transforms.ToTensor()])
model.eval()
while (capture.isOpened()):
ret, frame = capture.read()
if (ret):
key = cv2.waitKey(1) & 0xFF
copy_frame = copy.copy(frame)
copy_frame = transform(copy_frame)
# putting the batch dimension on tensor
copy_frame = copy_frame.unsqueeze(0)
copy_frame = copy_frame.to(device)
result = model(copy_frame)
crowd_count = int(result.data.sum().item())
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, "Crowd Couting: " + str(crowd_count), (10, 35),
font, 1.3, (0, 0, 255), 3, cv2.LINE_AA)
cv2.imshow("Frame", frame)
print(crowd_count)
if key == ord("q"):
break
def estimate_density_map(img_root,gt_dmap_root,model_param_path):
'''
Show one estimated density-map.
img_root: the root of test image data.
gt_dmap_root: the root of test ground truth density-map data.
model_param_path: the path of specific mcnn parameters.
index: the order of the test image in test dataset.
'''
model=CANNet().cuda()
model.load_state_dict(torch.load(model_param_path))
model.eval()
dataset=CrowdDataset(img_root,gt_dmap_root,8,phase='test')
dataloader=torch.utils.data.DataLoader(dataset,batch_size=1,shuffle=False)
print('dataloader = ',dataloader)
for img,gt_dmap,img_name in dataloader:
print('img_shape = ',img.shape)
st = time.time()
img=img.cuda()
gt_dmap=gt_dmap.cuda()
# forward propagation
et_dmap=model(img).detach()
et_dmap=et_dmap.squeeze(0).squeeze(0).cpu().numpy()
pred_frame = plt.gca()
plt.imshow(et_dmap,cmap=CM.jet)
plt.show()
pred_frame.axes.get_yaxis().set_visible(False)
pred_frame.axes.get_xaxis().set_visible(False)
pred_frame.spines['top'].set_visible(False)
pred_frame.spines['bottom'].set_visible(False)
pred_frame.spines['left'].set_visible(False)
pred_frame.spines['right'].set_visible(False)
plt.savefig( 'result/'+str(img_name)+'_out' + '.png',bbox_inches='tight', pad_inches=0, dpi=200)
plt.close()
print('tt = ',time.time()-st)
break
default=0.7,
type=float,
help="Opacity value for the density map overlap")
args = parser.parse_args()
# setup the model
if args.device == "cpu":
device = torch.device("cpu")
elif args.device == "gpu":
device = torch.device("cuda")
torch.backends.cudnn.enabled = True # use cudnn?
else:
raise Exception("Unknown device. Use \"cpu\" or \"gpu\".")
model = CANNet().to(device)
model.load_state_dict(torch.load(args.model))
model.eval()
torch.no_grad()
# open the video stream / file
cap = cv2.VideoCapture(args.video)
while (cap.isOpened()):
_, frame = cap.read()
# convert to pytorch tensor and normalize
tensor = torchvision.transforms.ToTensor()(cv2.cvtColor(
frame, cv2.COLOR_BGR2RGB))
# ---------- to change after new norm training ------------------------
tensor = torchvision.transforms.functional.normalize(
tensor, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
# ---------------------------------------------------------------------
tensor = tensor.unsqueeze(0).to(device)
def main(args):
wandb.init(project="crowd", config=args)
args = wandb.config
# print(args)
# vis=visdom.Visdom()
torch.cuda.manual_seed(args.seed)
model=CANNet().to(args.device)
criterion=nn.MSELoss(reduction='sum').to(args.device)
# optimizer=torch.optim.SGD(model.parameters(), args.lr,
# momentum=args.momentum,
# weight_decay=0)
optimizer=torch.optim.Adam(model.parameters(), args.lr, weight_decay=args.decay)
train_dataset = CrowdDataset(args.train_image_root, args.train_dmap_root, gt_downsample=8, phase='train')
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=args.batch_size, shuffle=True)
val_dataset = CrowdDataset(args.val_image_root, args.val_dmap_root, gt_downsample=8, phase='test')
val_loader = torch.utils.data.DataLoader(val_dataset, batch_size=args.batch_size, shuffle=False)
if not os.path.exists('./checkpoints'):
os.mkdir('./checkpoints')
min_mae = 10000
min_epoch = 0
for epoch in tqdm(range(0, args.epochs)):
# training phase
model.train()
model.zero_grad()
train_loss = 0
train_mae = 0
train_bar = tqdm(train_loader)
for i, (img,gt_dmap) in enumerate(train_bar):
# print(img.shape, gt_dmap.shape)
img = img.to(args.device)
gt_dmap = gt_dmap.to(args.device)
# forward propagation
et_dmap = model(img)
# calculate loss
# print(et_dmap.shape, gt_dmap.shape)
loss = criterion(et_dmap, gt_dmap)
train_loss += loss.item()
train_mae += abs(et_dmap.data.sum()-gt_dmap.data.sum()).item()
loss = loss/args.gradient_accumulation_steps
loss.backward()
if (i+1)%args.gradient_accumulation_steps == 0:
optimizer.step()
model.zero_grad()
train_bar.set_postfix(loss=train_loss/(i+1), mae=train_mae/(i+1))
optimizer.step()
model.zero_grad()
# print("epoch:",epoch,"loss:",epoch_loss/len(dataloader))
torch.save(model.state_dict(),'./checkpoints/epoch_'+str(epoch)+".pth")
# testing phase
model.eval()
val_loss = 0
val_mae = 0
for i, (img,gt_dmap) in enumerate((val_loader)):
img = img.to(args.device)
gt_dmap = gt_dmap.to(args.device)
# forward propagation
et_dmap = model(img)
loss = criterion(et_dmap, gt_dmap)
val_loss += loss.item()
val_mae += abs(et_dmap.data.sum()-gt_dmap.data.sum()).item()
del img,gt_dmap,et_dmap
if val_mae/len(val_loader) < min_mae:
min_mae = val_mae/len(val_loader)
min_epoch = epoch
# print("epoch:" + str(epoch) + " error:" + str(mae/len(val_loader)) + " min_mae:"+str(min_mae) + " min_epoch:"+str(min_epoch))
wandb.log({"loss/train": train_loss/len(train_loader),
"mae/train": train_mae/len(train_loader),
"loss/val": val_loss/len(val_loader),
"mae/val": val_mae/len(val_loader),
}, commit=False)
# show an image
index = random.randint(0, len(val_loader)-1)
img, gt_dmap = val_dataset[index]
gt_dmap = gt_dmap.squeeze(0).detach().cpu().numpy()
wandb.log({"image/img": [wandb.Image(img)]}, commit=False)
wandb.log({"image/gt_dmap": [wandb.Image(gt_dmap/(gt_dmap.max())*255, caption=str(gt_dmap.sum()))]}, commit=False)
img = img.unsqueeze(0).to(args.device)
et_dmap = model(img)
et_dmap = et_dmap.squeeze(0).detach().cpu().numpy()
wandb.log({"image/et_dmap": [wandb.Image(et_dmap/(et_dmap.max())*255, caption=str(et_dmap.sum()))]})
import time
print(time.strftime('%Y.%m.%d %H:%M:%S',time.localtime(time.time())))
