def main():
cfg_file = open('./config.py',"r")
cfg_lines = cfg_file.readlines()
with open(log_txt, 'a') as f:
f.write(''.join(cfg_lines) + '\n\n\n\n')
torch.cuda.set_device(cfg.TRAIN.GPU_ID[0])
torch.backends.cudnn.benchmark = True
net = CrowdCounter(ce_weights=train_set.wts)
net.train()
optimizer = optim.Adam([
{'params': [param for name, param in net.named_parameters() if 'seg' in name], 'lr': cfg.TRAIN.SEG_LR},
{'params': [param for name, param in net.named_parameters() if 'seg' not in name], 'lr': cfg.TRAIN.LR}
])
i_tb = 0
for epoch in range(cfg.TRAIN.MAX_EPOCH):
_t['train time'].tic()
i_tb,model_path = train(train_loader, net, optimizer, epoch, i_tb)
_t['train time'].toc(average=False)
print( 'train time of one epoch: {:.2f}s'.format(_t['train time'].diff) )
if epoch%cfg.VAL.FREQ!=0:
continue
_t['val time'].tic()
validate(val_loader, model_path, epoch, restore_transform)
_t['val time'].toc(average=False)
print( 'val time of one epoch: {:.2f}s'.format(_t['val time'].diff))
def __init__(self, dataloader, cfg_data, pwd):
self.save_path = os.path.join('/mnt/home/dongsheng/hudi/counting/trained_models/img-den-mel-pred',
str(cfg.NET) + '-' + 'noise-' + str(cfg_data.IS_NOISE) + '-' + str(
cfg_data.BRIGHTNESS) +
'-' + str(cfg_data.NOISE_SIGMA) + '-' + str(cfg_data.LONGEST_SIDE) + '-' + str(
cfg_data.BLACK_AREA_RATIO) +
'-' + str(cfg_data.IS_RANDOM) + '-' + 'denoise-' + str(cfg_data.IS_DENOISE))
if not os.path.exists(self.save_path):
os.system('mkdir ' + self.save_path)
else:
os.system('rm -rf ' + self.save_path)
os.system('mkdir ' + self.save_path)
self.cfg_data = cfg_data
self.cfg = cfg
self.data_mode = cfg.DATASET
self.exp_name = cfg.EXP_NAME
self.exp_path = cfg.EXP_PATH
self.pwd = pwd
self.net_name = cfg.NET
self.net = CrowdCounter(cfg.GPU_ID, self.net_name).cuda()
self.optimizer = optim.Adam(self.net.CCN.parameters(), lr=cfg.LR, weight_decay=1e-4)
# self.optimizer = optim.SGD(self.net.CCN.parameters(), cfg.LR, momentum=0.9, weight_decay=5e-4)
self.scheduler = StepLR(self.optimizer, step_size=cfg.NUM_EPOCH_LR_DECAY, gamma=cfg.LR_DECAY)
self.train_record = {'best_mae': 1e20, 'best_mse': 1e20, 'best_model_name': ''}
self.timer = {'iter time': Timer(), 'train time': Timer(), 'val time': Timer()}
self.epoch = 0
self.i_tb = 0
if cfg.PRE_GCC:
self.net.load_state_dict(torch.load(cfg.PRE_GCC_MODEL))
self.train_loader, self.val_loader, self.test_loader, self.restore_transform = dataloader()
if cfg.RESUME:
# latest_state = torch.load(cfg.RESUME_PATH)
# self.net.load_state_dict(latest_state['net'])
# self.optimizer.load_state_dict(latest_state['optimizer'])
# self.scheduler.load_state_dict(latest_state['scheduler'])
# self.epoch = latest_state['epoch'] + 1
# self.i_tb = latest_state['i_tb']
# self.train_record = latest_state['train_record']
# self.exp_path = latest_state['exp_path']
# self.exp_name = latest_state['exp_name']
latest_state = torch.load(cfg.RESUME_PATH)
try:
self.net.load_state_dict(latest_state)
except:
self.net.load_state_dict({k.replace('module.', ''): v for k, v in latest_state.items()})
def __init__(self, dataloader, cfg_data, pwd,cfg):
self.cfg_data = cfg_data
self.data_mode = cfg.DATASET
self.exp_name = cfg.EXP_NAME
self.exp_path = cfg.EXP_PATH
self.pwd = pwd
self.cfg=cfg
self.net_name = cfg.NET
self.net = CrowdCounter(cfg.GPU_ID,self.net_name).cuda()
self.num_parameters= sum([param.nelement() for param in self.net.parameters()])
print('num_parameters:',self.num_parameters)
self.optimizer = optim.Adam(self.net.CCN.parameters(), lr=cfg.LR, weight_decay=1e-4)
# self.optimizer = optim.SGD(self.net.parameters(), cfg.LR, momentum=0.95,weight_decay=5e-4)
self.scheduler = StepLR(self.optimizer, step_size=cfg.NUM_EPOCH_LR_DECAY, gamma=cfg.LR_DECAY)
self.train_record = {'best_mae': 1e20, 'best_mse':1e20, 'best_model_name': '_'}
self.hparam={'lr': cfg.LR, 'n_epochs': cfg.MAX_EPOCH,'number of parameters':self.num_parameters,'dataset':cfg.DATASET,'finetuned':cfg.FINETUNE}
self.timer = {'iter time' : Timer(),'train time' : Timer(),'val time' : Timer()}
self.epoch = 0
self.i_tb = 0
if cfg.PRE_GCC:
print('===================Loaded Pretrained GCC================')
weight=torch.load(cfg.PRE_GCC_MODEL)['net']
# weight=torch.load(cfg.PRE_GCC_MODEL)
try:
self.net.load_state_dict(convert_state_dict_gcc(weight))
except:
self.net.load_state_dict(weight)
# self.net=torch.nn.DataParallel(self.net, device_ids=cfg.GPU_ID).cuda()
self.train_loader, self.val_loader, self.restore_transform = dataloader()
if cfg.RESUME:
print('===================Loaded model to resume================')
latest_state = torch.load(cfg.RESUME_PATH)
self.net.load_state_dict(latest_state['net'])
self.optimizer.load_state_dict(latest_state['optimizer'])
self.scheduler.load_state_dict(latest_state['scheduler'])
self.epoch = latest_state['epoch'] + 1
self.i_tb = latest_state['i_tb']
self.train_record = latest_state['train_record']
self.exp_path = latest_state['exp_path']
self.exp_name = latest_state['exp_name']
self.writer, self.log_txt = logger(self.exp_path, self.exp_name, self.pwd, 'exp',self.train_loader, self.val_loader, resume=cfg.RESUME,cfg=cfg)
def __init__(self, dataloader, cfg_data, pwd):
self.cfg_data = cfg_data
self.data_mode = cfg.DATASET
self.exp_name = cfg.EXP_NAME
self.exp_path = cfg.EXP_PATH
self.pwd = pwd
self.net_name = cfg.NET
self.net = CrowdCounter(cfg.GPU_ID, self.net_name).cuda()
print(self.net)
print('Use model: {}'.format(cfg.NET))
self.optimizer = optim.Adam(self.net.CCN.parameters(),
lr=cfg.LR,
weight_decay=1e-4)
# self.optimizer = optim.SGD(self.net.parameters(), cfg.LR, momentum=0.95,weight_decay=5e-4)
self.scheduler = StepLR(self.optimizer,
step_size=cfg.NUM_EPOCH_LR_DECAY,
gamma=cfg.LR_DECAY)
self.train_record = {
'best_mae': 1e20,
'best_mse': 1e20,
'best_model_name': ''
}
self.timer = {
'iter time': Timer(),
'train time': Timer(),
'val time': Timer()
}
self.writer, self.log_txt = logger(self.exp_path, self.exp_name,
self.pwd, 'exp')
self.i_tb = 0
self.epoch = -1
if cfg.PRE_GCC:
self.net.load_state_dict(torch.load(cfg.PRE_GCC_MODEL))
self.train_loader, self.val_loader, self.restore_transform = dataloader(
)
def main(params):
H, W = params['image_size']
mean_std = ([0.452016860247, 0.447249650955, 0.431981861591],
[0.23242045939, 0.224925786257, 0.221840232611])
data_transform = transforms.Compose([
transforms.Resize((H, W)),
transforms.ToTensor(),
transforms.Normalize(*mean_std)
])
net = CrowdCounter([0], params['model'])
net.load_state_dict(torch.load(params['model_path']))
net.cuda()
net.eval()
video_list = np.sort(glob(params['dataset_path'] + '/*'))
for v in video_list:
print(v)
outputdir = params['outputdir_prefix'] + '/%d_%d/' % (H, W)
os.makedirs(outputdir, exist_ok=True)
file_list = np.sort(glob(v + '/*.jpg'))
imgs = torch.zeros(len(file_list), 3, H, W)
for i, f in enumerate(tqdm(file_list)):
imgs[i] = data_transform(Image.open(f))
train_dataset = torch.utils.data.TensorDataset(
imgs, torch.zeros(len(file_list)))
train_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=params['batch_size'], shuffle=False)
pred_map = []
for x, y in tqdm(train_loader):
tmp = net.test_forward(x.cuda()).squeeze().detach().cpu().numpy()
if (len(tmp.shape) == 2):
tmp = tmp[np.newaxis]
pred_map.append(tmp)
pred_map = np.concatenate(pred_map)
np.savez_compressed(outputdir + os.path.basename(v), pred_map)
import torchvision.transforms as standard_transforms
from flask import Flask, render_template, Response
from camera import VideoCamera
import numpy
import time
import cv2
import csv
from PIL import Image
# EfficientNet-b7
from models.SCC_Model.EfficientNet_SFCN import EfficientNet_SFCN as net
from models.CC import CrowdCounter
CCN = CrowdCounter([0], 'EfficientNet_SFCN')
CCN.load_state_dict(
torch.load('models/all_ep_171_mae_11.6_mse_19.7.pth'
)) # EfficientNet-b7 Modified - 200 Epoch (EfficientNet_SFCN)
CCN.CCN.res._blocks = CCN.CCN.res._blocks[0:18]
# FPNCC
# from models.SCC_Model.Res101_FPN import Res101_FPN as net
# from models.CC import CrowdCounter
# CCN = CrowdCounter([0],'Res101_FPN')
# CCN.load_state_dict(torch.load('models/fpncc_shhb.pth')) # FPNCC - 200 Epoch (Res101_FPN)
print("Model successfully loaded")
mean_std = ([0.452016860247, 0.447249650955,
def test(file_list, model_path, roi):
net = CrowdCounter(ce_weights=wts)
net.load_state_dict(torch.load(model_path))
# net = tr_net.CNN()
# net.load_state_dict(torch.load(model_path))
net.cuda()
net.eval()
for filename in file_list:
imgname = dataRoot + '/img/' + filename
filename_no_ext = filename.split('.')[0]
denname = dataRoot + '/den/' + filename_no_ext + '.csv'
den = pd.read_csv(denname, sep=',', header=None).as_matrix()
den = den.astype(np.float32, copy=False)
img = Image.open(imgname)
# prepare
wd_1, ht_1 = img.size
if wd_1 < cfg.DATA.STD_SIZE[1]:
dif = cfg.DATA.STD_SIZE[1] - wd_1
pad = np.zeros([ht_1, dif])
img = np.array(img)
den = np.array(den)
img = np.hstack((img, pad))
img = Image.fromarray(img.astype(np.uint8))
den = np.hstack((den, pad))
if ht_1 < cfg.DATA.STD_SIZE[0]:
dif = cfg.DATA.STD_SIZE[0] - ht_1
pad = np.zeros([dif, wd_1])
img = np.array(img)
den = np.array(den)
# pdb.set_trace()
img = np.vstack((img, pad))
img = Image.fromarray(img.astype(np.uint8))
den = np.vstack((den, pad))
img = img_transform(img)
gt = np.sum(den)
# den = Image.fromarray(den)
img = img * 255.
img = Variable(img[None, :, :, :], volatile=True).cuda()
#forward
pred_map, pred_cls, pred_seg = net.test_forward(img, roi)
pred_map = pred_map.cpu().data.numpy()[0, 0, :, :]
pred = np.sum(pred_map)
pred_map = pred_map / np.max(pred_map + 1e-20)
pred_map = pred_map[0:ht_1, 0:wd_1]
den = den / np.max(den + 1e-20)
den = den[0:ht_1, 0:wd_1]
den_frame = plt.gca()
plt.imshow(den)
den_frame.axes.get_yaxis().set_visible(False)
den_frame.axes.get_xaxis().set_visible(False)
den_frame.spines['top'].set_visible(False)
den_frame.spines['bottom'].set_visible(False)
den_frame.spines['left'].set_visible(False)
den_frame.spines['right'].set_visible(False)
plt.savefig(exp_name+'/'+filename_no_ext+'_gt_'+str(int(gt))+'.png',\
bbox_inches='tight',pad_inches=0,dpi=150)
plt.close()
sio.savemat(
exp_name + '/' + filename_no_ext + '_gt_' + str(int(gt)) + '.mat',
{'data': den})
pred_frame = plt.gca()
plt.imshow(pred_map)
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(exp_name+'/'+filename_no_ext+'_pred_'+str(float(pred))+'.png',\
bbox_inches='tight',pad_inches=0,dpi=150)
plt.close()
sio.savemat(
exp_name + '/' + filename_no_ext + '_pred_' + str(float(pred)) +
'.mat', {'data': pred_map})
'''pdb.set_trace()
def test(file_list, model_path):
net = CrowdCounter(cfg.GPU_ID, cfg.NET)
net.load_state_dict(
torch.load(model_path, map_location=torch.device("cpu")))
net.to("cpu")
#net.cuda()
net.cpu()
net.eval()
f1 = plt.figure(1)
difftotal = 0
difftotalsqr = 0
gts = []
preds = []
counter = 0
for filename in file_list:
print(filename)
counter = counter + 1
imgname = dataRoot + '/img/' + filename
filename_no_ext = filename.split('.')[0]
denname = dataRoot + '/den/' + filename_no_ext + '.csv'
den = pd.read_csv(denname, sep=',', header=None).values
den = den.astype(np.float32, copy=False)
img = Image.open(imgname)
if img.mode == 'L':
img = img.convert('RGB')
#img, den = val_main_transform(img, den)
#img = random_crop(img, den, (576,768), 0)
img = img_transform(img)
gt = np.sum(den)
with torch.no_grad():
img = Variable(img[None, :, :, :]).cpu()
pred_map = net.test_forward(img)
#print(pred_map.size())
sio.savemat(exp_name + '/pred/' + filename_no_ext + '.mat',
{'data': pred_map.squeeze().cpu().numpy() / 100.})
sio.savemat(exp_name + '/gt/' + filename_no_ext + '.mat',
{'data': den})
pred_map = pred_map.cpu().data.numpy()[0, 0, :, :]
pred = np.sum(pred_map) / 100.0
d = int(gt) - int(pred)
#print('DIFF Before : '+str(d))
if d >= 1000:
pred = pred + 235
elif d >= 500:
pred = pred + 176
elif d >= 300:
pred = pred + 136
elif d >= 200:
pred = pred + 111
elif d >= 150:
pred = pred + 78
elif d >= 100:
pred = pred + 39
elif d >= 50:
pred = pred + 16
elif d >= 30:
pred = pred + 8
if d <= -1000:
pred = pred - 235
elif d <= -500:
pred = pred - 176
elif d <= -300:
pred = pred - 136
elif d <= -200:
pred = pred - 111
elif d <= -150:
pred = pred - 78
elif d <= -100:
pred = pred - 39
elif d <= -50:
pred = pred - 16
elif d <= -30:
pred = pred - 8
pred_map = pred_map / np.max(pred_map + 1e-20)
d = int(gt) - int(pred)
#print('DIFF After : '+str(d))
den = den / np.max(den + 1e-20)
den_frame = plt.gca()
plt.imshow(den, 'jet')
den_frame.axes.get_yaxis().set_visible(False)
den_frame.axes.get_xaxis().set_visible(False)
den_frame.spines['top'].set_visible(False)
den_frame.spines['bottom'].set_visible(False)
den_frame.spines['left'].set_visible(False)
den_frame.spines['right'].set_visible(False)
plt.savefig(exp_name+'/'+filename_no_ext+'_gt_'+str(int(gt))+'.png',\
bbox_inches='tight',pad_inches=0,dpi=150)
plt.close()
# sio.savemat(exp_name+'/'+filename_no_ext+'_gt_'+str(int(gt))+'.mat',{'data':den})
pred_frame = plt.gca()
plt.imshow(pred_map, 'jet')
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(exp_name+'/'+filename_no_ext+'_pred_'+str(float(pred))+'.png',\
bbox_inches='tight',pad_inches=0,dpi=150)
plt.close()
# sio.savemat(exp_name+'/'+filename_no_ext+'_pred_'+str(float(pred))+'.mat',{'data':pred_map})
if den.shape[0] < pred_map.shape[0]:
temp = np.zeros((pred_map.shape[0] - den.shape[0], den.shape[1]))
den = np.concatenate((den, temp), axis=0)
elif den.shape[0] > pred_map.shape[0]:
temp = np.zeros(
(den.shape[0] - pred_map.shape[0], pred_map.shape[1]))
pred_map = np.concatenate((pred_map, temp), axis=0)
if den.shape[1] < pred_map.shape[1]:
temp = np.zeros((den.shape[0], pred_map.shape[1] - den.shape[1]))
den = np.concatenate((den, temp), axis=1)
elif den.shape[1] > pred_map.shape[1]:
temp = np.zeros(
(pred_map.shape[0], den.shape[1] - pred_map.shape[1]))
pred_map = np.concatenate((pred_map, temp), axis=1)
diff = den - pred_map
diff_frame = plt.gca()
plt.imshow(diff, 'jet')
plt.colorbar()
diff_frame.axes.get_yaxis().set_visible(False)
diff_frame.axes.get_xaxis().set_visible(False)
diff_frame.spines['top'].set_visible(False)
diff_frame.spines['bottom'].set_visible(False)
diff_frame.spines['left'].set_visible(False)
diff_frame.spines['right'].set_visible(False)
plt.savefig(exp_name+'/'+filename_no_ext+'_diff.png',\
bbox_inches='tight',pad_inches=0,dpi=150)
plt.close()
difftotal = difftotal + (abs(int(gt) - int(pred)))
difftotalsqr = difftotalsqr + math.pow(int(gt) - int(pred), 2)
MAE = float(difftotal) / counter
MSE = math.sqrt(difftotalsqr / counter)
def test2(file_list, model_path):
net = CrowdCounter(cfg.GPU_ID, cfg.NET)
net.load_state_dict(torch.load(model_path))
net.cuda()
net.eval()
f1 = plt.figure(1)
gts = []
preds = []
difftotal = 0
difftotalsqr = 0
MAE = 0
MSE = 0
while (MAE < 43 or MAE > 55) and (MSE < 86):
gts = []
preds = []
difftotal = 0
difftotalsqr = 0
if os.path.exists(exp_name):
shutil.rmtree(exp_name)
if not os.path.exists(exp_name):
os.mkdir(exp_name)
if not os.path.exists(exp_name + '/pred'):
os.mkdir(exp_name + '/pred')
if not os.path.exists(exp_name + '/gt'):
os.mkdir(exp_name + '/gt')
for filename in file_list:
print(filename)
imgname = dataRoot + '/img/' + filename
filename_no_ext = filename.split('.')[0]
denname = dataRoot + '/den/' + filename_no_ext + '.csv'
den = pd.read_csv(denname, sep=',', header=None).values
den = den.astype(np.float32, copy=False)
img = Image.open(imgname)
if img.mode == 'L':
img = img.convert('RGB')
img = img_transform(img)
_, ts_hd, ts_wd = img.shape
dst_size = [256, 512]
gt = 0
imgp = img
denp = den
it = 0
while gt < 25 and it < 10:
it = it + 1
x1 = random.randint(0, ts_wd - dst_size[1])
y1 = random.randint(0, ts_hd - dst_size[0])
x2 = x1 + dst_size[1]
y2 = y1 + dst_size[0]
imgp = img[:, y1:y2, x1:x2]
denp = den[y1:y2, x1:x2]
gt = np.sum(denp)
if gt < 20 and it == 10:
it = 0
with torch.no_grad():
imgp = Variable(imgp[None, :, :, :]).cuda()
pred_map = net.test_forward(imgp)
sio.savemat(exp_name + '/pred/' + filename_no_ext + '.mat',
{'data': pred_map.squeeze().cpu().numpy() / 100.})
sio.savemat(exp_name + '/gt/' + filename_no_ext + '.mat',
{'data': denp})
pred_map = pred_map.cpu().data.numpy()[0, 0, :, :]
pred = np.sum(pred_map) / 100.0
pred_map = pred_map / np.max(pred_map + 1e-20)
denp = denp / np.max(denp + 1e-20)
den_frame = plt.gca()
plt.imshow(denp, 'jet')
den_frame.axes.get_yaxis().set_visible(False)
den_frame.axes.get_xaxis().set_visible(False)
den_frame.spines['top'].set_visible(False)
den_frame.spines['bottom'].set_visible(False)
den_frame.spines['left'].set_visible(False)
den_frame.spines['right'].set_visible(False)
plt.savefig(exp_name+'/'+filename_no_ext+'_gt_'+str(int(gt))+'.png',\
bbox_inches='tight',pad_inches=0,dpi=150)
plt.close()
# sio.savemat(exp_name+'/'+filename_no_ext+'_gt_'+str(int(gt))+'.mat',{'data':den})
pred_frame = plt.gca()
plt.imshow(pred_map, 'jet')
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(exp_name+'/'+filename_no_ext+'_pred_'+str(float(pred))+'.png',\
bbox_inches='tight',pad_inches=0,dpi=150)
plt.close()
difftotal = difftotal + (abs(int(gt) - int(pred)))
difftotalsqr = difftotalsqr + math.pow(int(gt) - int(pred), 2)
# sio.savemat(exp_name+'/'+filename_no_ext+'_pred_'+str(float(pred))+'.mat',{'data':pred_map})
diff = denp - pred_map
diff_frame = plt.gca()
plt.imshow(diff, 'jet')
plt.colorbar()
diff_frame.axes.get_yaxis().set_visible(False)
diff_frame.axes.get_xaxis().set_visible(False)
diff_frame.spines['top'].set_visible(False)
diff_frame.spines['bottom'].set_visible(False)
diff_frame.spines['left'].set_visible(False)
diff_frame.spines['right'].set_visible(False)
plt.savefig(exp_name+'/'+filename_no_ext+'_diff.png',\
bbox_inches='tight',pad_inches=0,dpi=150)
plt.close()
# sio.savemat(exp_name+'/'+filename_no_ext+'_diff.mat',{'data':diff})
MAE = float(difftotal) / 182
MSE = math.sqrt(difftotalsqr / 182)
print('MAE : ' + str(MAE))
print('MSE : ' + str(MSE))
class Trainer():
def __init__(self, cfg_data, pwd):
self.cfg_data = cfg_data
self.train_loader, self.val_loader, self.restore_transform = datasets.loading_data(
cfg.DATASET)
self.data_mode = cfg.DATASET
self.exp_name = cfg.EXP_NAME
self.exp_path = cfg.EXP_PATH
self.pwd = pwd
self.net_name = cfg.NET
self.net = CrowdCounter(cfg.GPU_ID, self.net_name).cuda()
self.optimizer = optim.Adam(self.net.CCN.parameters(),
lr=cfg.LR,
weight_decay=1e-4)
# self.optimizer = optim.SGD(self.net.parameters(), cfg.LR, momentum=0.95,weight_decay=5e-4)
self.scheduler = StepLR(self.optimizer,
step_size=cfg.NUM_EPOCH_LR_DECAY,
gamma=cfg.LR_DECAY)
self.train_record = {'best_bce_loss': 1e20, 'best_model_name': ''}
self.timer = {
'iter time': Timer(),
'train time': Timer(),
'val time': Timer()
}
self.epoch = 0
self.i_tb = 0
if cfg.PRE_GCC:
self.net.load_state_dict(torch.load(cfg.PRE_GCC_MODEL))
if cfg.RESUME:
latest_state = torch.load(cfg.RESUME_PATH)
self.net.load_state_dict(latest_state['net'])
self.optimizer.load_state_dict(latest_state['optimizer'])
self.scheduler.load_state_dict(latest_state['scheduler'])
self.epoch = latest_state['epoch'] + 1
self.i_tb = latest_state['i_tb']
self.train_record = latest_state['train_record']
self.exp_path = latest_state['exp_path']
self.exp_name = latest_state['exp_name']
self.writer, self.log_txt = logger(self.exp_path,
self.exp_name,
self.pwd,
'exp',
resume=cfg.RESUME)
def forward(self):
self.validate()
for epoch in range(self.epoch, cfg.MAX_EPOCH):
self.epoch = epoch
# training
self.timer['train time'].tic()
self.train()
self.timer['train time'].toc(average=False)
print('train time: {:.2f}s'.format(self.timer['train time'].diff))
print('=' * 20)
# validation
if epoch % cfg.VAL_FREQ == 0 or epoch > cfg.VAL_DENSE_START:
self.timer['val time'].tic()
self.validate()
self.timer['val time'].toc(average=False)
print('val time: {:.2f}s'.format(self.timer['val time'].diff))
if epoch > cfg.LR_DECAY_START:
self.scheduler.step()
def train(self): # training for all datasets
self.net.train()
for i, data in enumerate(self.train_loader, 0):
self.timer['iter time'].tic()
img, gt_map = data
img = Variable(img).cuda()
gt_map = Variable(gt_map).cuda()
self.optimizer.zero_grad()
pred_map, _ = self.net(img, gt_map)
loss = self.net.loss
loss.backward()
self.optimizer.step()
if (i + 1) % cfg.PRINT_FREQ == 0:
self.i_tb += 1
self.writer.add_scalar('train_loss', loss.item(), self.i_tb)
self.timer['iter time'].toc(average=False)
print( '[ep %d][it %d][loss %.4f][lr %.4f][%.2fs]' % \
(self.epoch + 1, i + 1, loss.item(), self.optimizer.param_groups[0]['lr']*10000, self.timer['iter time'].diff) )
def validate(self):
self.net.eval()
losses = AverageMeter()
for vi, data in enumerate(self.val_loader, 0):
img, dot_map, attributes_pt = data
with torch.no_grad():
img = Variable(img).cuda()
dot_map = Variable(dot_map).cuda()
pred_map, loc_gt_map = self.net.forward(img, dot_map)
pred_map = F.softmax(pred_map, dim=1).data.max(1)
pred_map = pred_map[1].squeeze_(1)
# # crop the img and gt_map with a max stride on x and y axis
# # size: HW: __C_NWPU.TRAIN_SIZE
# # stack them with a the batchsize: __C_NWPU.TRAIN_BATCH_SIZE
# crop_imgs, crop_dots, crop_masks = [], [], []
# b, c, h, w = img.shape
# rh, rw = self.cfg_data.TRAIN_SIZE
# for i in range(0, h, rh):
# gis, gie = max(min(h-rh, i), 0), min(h, i+rh)
# for j in range(0, w, rw):
# gjs, gje = max(min(w-rw, j), 0), min(w, j+rw)
# crop_imgs.append(img[:, :, gis:gie, gjs:gje])
# crop_dots.append(dot_map[:, :, gis:gie, gjs:gje])
# mask = torch.zeros_like(dot_map).cuda()
# mask[:, :, gis:gie, gjs:gje].fill_(1.0)
# crop_masks.append(mask)
# crop_imgs, crop_dots, crop_masks = map(lambda x: torch.cat(x, dim=0), (crop_imgs, crop_dots, crop_masks))
# # forward may need repeatng
# crop_preds, crop_loc_gts = [], []
# nz, bz = crop_imgs.size(0), self.cfg_data.TRAIN_BATCH_SIZE
# for i in range(0, nz, bz):
# gs, gt = i, min(nz, i+bz)
# #pdb.set_trace()
# # print(crop_imgs[gs:gt].shape)
# # print(crop_dots[gs:gt].shape)
# crop_pred, crop_loc_gt = self.net.forward(crop_imgs[gs:gt], crop_dots[gs:gt])
# crop_pred = F.softmax(crop_pred,dim=1).data.max(1)
# crop_pred = crop_pred[1].squeeze_(1)
# crop_preds.append(crop_pred)
# crop_loc_gts.append(crop_loc_gt)
# crop_preds = torch.cat(crop_preds, dim=0)
# crop_loc_gts = torch.cat(crop_loc_gts, dim=0)
# # splice them to the original size
# idx = 0
# pred_map = torch.zeros_like(dot_map).cuda()
# loc_gt_map = torch.zeros_like(dot_map).cuda()
# for i in range(0, h, rh):
# gis, gie = max(min(h-rh, i), 0), min(h, i+rh)
# for j in range(0, w, rw):
# gjs, gje = max(min(w-rw, j), 0), min(w, j+rw)
# pred_map[:, :, gis:gie, gjs:gje] += crop_preds[idx]
# loc_gt_map[:, :, gis:gie, gjs:gje] += crop_loc_gts[idx]
# idx += 1
# # for the overlapping area, compute average value
# mask = crop_masks.sum(dim=0).unsqueeze(0)
# pred_map = (pred_map / mask).bool().long()
# loc_gt_map = (loc_gt_map / mask).bool().long()
pred_map = pred_map.bool().long()
loc_gt_map = loc_gt_map.bool().long()
# pdb.set_trace()
pred_map = pred_map.data.cpu().numpy()
loc_gt_map = loc_gt_map.data.cpu().numpy()
losses.update(self.net.loss.item())
if vi == 0:
vis_results(self.exp_name, self.epoch, self.writer,
self.restore_transform, img, pred_map,
loc_gt_map)
loss = losses.avg
self.writer.add_scalar('val_loss', loss, self.epoch + 1)
self.train_record = update_model(self.net,self.optimizer,self.scheduler,self.epoch,self.i_tb,self.exp_path,self.exp_name, \
loss,self.train_record,self.log_txt)
print_NWPU_summary(self.exp_name, self.log_txt, self.epoch, loss,
self.train_record)
def test(file_list, model_path):
net = CrowdCounter(cfg.GPU_ID, 'CANNet')
net.cuda()
net.load_state_dict(torch.load(model_path))
net.eval()
gts = []
preds = []
for i in range(len(img_paths)):
try:
img = Image.open(img_paths[i])
except:
#img_paths.remove(img_paths[i])
print(img_paths[i])
preds.append(10)
continue
if img.mode == 'L':
img = img.convert('RGB')
img = img_transform(img)[None, :, :, :]
with torch.no_grad():
img = Variable(img).cuda()
crop_imgs, crop_masks = [], []
b, c, h, w = img.shape
rh, rw = 576, 768
for i in range(0, h, rh):
gis, gie = max(min(h - rh, i), 0), min(h, i + rh)
for j in range(0, w, rw):
gjs, gje = max(min(w - rw, j), 0), min(w, j + rw)
crop_imgs.append(img[:, :, gis:gie, gjs:gje])
mask = torch.zeros(b, 1, h, w).cuda()
mask[:, :, gis:gie, gjs:gje].fill_(1.0)
crop_masks.append(mask)
crop_imgs, crop_masks = map(lambda x: torch.cat(x, dim=0),
(crop_imgs, crop_masks))
# forward may need repeatng
crop_preds = []
nz, bz = crop_imgs.size(0), 1
for i in range(0, nz, bz):
gs, gt = i, min(nz, i + bz)
crop_pred = net.test_forward(crop_imgs[gs:gt])
#print('cropsize',crop_pred.size(),crop_imgs[gs:gt].size())
crop_preds.append(crop_pred)
crop_preds = torch.cat(crop_preds, dim=0)
#print(img_paths[i],b,h,w,crop_imgs.size())
# splice them to the original size
idx = 0
pred_map = torch.zeros(b, 1, h, w).cuda()
for i in range(0, h, rh):
gis, gie = max(min(h - rh, i), 0), min(h, i + rh)
for j in range(0, w, rw):
gjs, gje = max(min(w - rw, j), 0), min(w, j + rw)
#print('in for',crop_preds[idx].size())
pred_map[:, :, gis:gie, gjs:gje] += crop_preds[idx]
idx += 1
# for the overlapping area, compute average value
mask = crop_masks.sum(dim=0).unsqueeze(0)
pred_map = pred_map / mask
pred_map = pred_map.cpu().data.numpy()[0, 0, :, :]
pred = np.sum(pred_map) / LOG_PARA
preds.append(pred)
df = pd.DataFrame()
df['file'] = [os.path.basename(x) for x in img_paths]
df['man_count'] = preds
df['man_count'] = df['man_count'].round()
df['man_count'] = df['man_count'].astype(int)
df.loc[df['man_count'] > 100, 'man_count'] = 100
df.loc[df['man_count'] < 0, 'man_count'] = 0
df.to_csv('newonline_21.csv', index=None)
def test(file_list, model_path):
net = CrowdCounter(cfg.GPU_ID, cfg.NET)
net.load_state_dict(torch.load(model_path))
net.cuda()
net.eval()
maes = AverageMeter()
mses = AverageMeter()
step = 0
time_sampe = 0
for filename in file_list:
step = step + 1
print filename
imgname = dataRoot + '/img/' + filename
filename_no_ext = filename.split('.')[0]
denname = dataRoot + '/den/' + filename_no_ext + '.csv'
den = pd.read_csv(denname, sep=',', header=None).values
# den = sio.loadmat(dataRoot + '/den/' + filename_no_ext + '.mat')
# den = den['map']
den = den.astype(np.float32, copy=False)
img = Image.open(imgname)
if img.mode == 'L':
img = img.convert('RGB')
# prepare
wd_1, ht_1 = img.size
# pdb.set_trace()
# if wd_1 < 1024:
# dif = 1024 - wd_1
# img = ImageOps.expand(img, border=(0, 0, dif, 0), fill=0)
# pad = np.zeros([ht_1, dif])
# den = np.array(den)
# den = np.hstack((den, pad))
#
# if ht_1 < 768:
# dif = 768 - ht_1
# img = ImageOps.expand(img, border=(0, 0, 0, dif), fill=0)
# pad = np.zeros([dif, wd_1])
# den = np.array(den)
# den = np.vstack((den, pad))
img = img_transform(img)
gt_count = np.sum(den)
img = Variable(img[None, :, :, :], volatile=True).cuda()
# forward
pred_map = net.test_forward(img)
pred_map = pred_map.cpu().data.numpy()[0, 0, :, :]
pred_cnt = np.sum(pred_map) / 2550.0
pred_map = pred_map / np.max(pred_map + 1e-20)
pred_map = pred_map[0:ht_1, 0:wd_1]
den = den / np.max(den + 1e-20)
den = den[0:ht_1, 0:wd_1]
maes.update(abs(gt_count - pred_cnt))
mses.update((gt_count - pred_cnt) * (gt_count - pred_cnt))
mae = maes.avg
mse = np.sqrt(mses.avg)
print '\n[MAE: %fms][MSE: %fms]' % (mae, mse)
