def __init__(self, flownet_backbone):
super(convAE, self).__init__()
self.generator = UNet(input_channels=12, output_channel=3)
self.discriminator = PixelDiscriminator(input_nc=3)
self.flownet_backbone = flownet_backbone
if flownet_backbone == '2sd':
self.flow_net = FlowNet2SD()
else:
self.flow_net = lite_flow.Network()
def train(frame_num,
layer_nums,
input_channels,
output_channels,
discriminator_num_filters,
bn=False,
pretrain=False,
generator_pretrain_path=None,
discriminator_pretrain_path=None):
generator = UNet(n_channels=input_channels,
layer_nums=layer_nums,
output_channel=output_channels,
bn=bn)
discriminator = PixelDiscriminator(output_channels,
discriminator_num_filters,
use_norm=False)
generator = generator.cuda()
discriminator = discriminator.cuda()
flow_network = Network()
flow_network.load_state_dict(torch.load(lite_flow_model_path))
flow_network.cuda().eval()
adversarial_loss = Adversarial_Loss().cuda()
discriminate_loss = Discriminate_Loss().cuda()
gd_loss = Gradient_Loss(alpha, num_channels).cuda()
op_loss = Flow_Loss().cuda()
int_loss = Intensity_Loss(l_num).cuda()
step = 0
if not pretrain:
generator.apply(weights_init_normal)
discriminator.apply(weights_init_normal)
else:
assert (generator_pretrain_path != None
and discriminator_pretrain_path != None)
generator.load_state_dict(torch.load(generator_pretrain_path))
discriminator.load_state_dict(torch.load(discriminator_pretrain_path))
step = int(generator_pretrain_path.split('-')[-1])
print('pretrained model loaded!')
print('initializing the model with Generator-Unet {} layers,'
'PixelDiscriminator with filters {} '.format(
layer_nums, discriminator_num_filters))
optimizer_G = torch.optim.Adam(generator.parameters(), lr=g_lr)
optimizer_D = torch.optim.Adam(discriminator.parameters(), lr=d_lr)
writer = SummaryWriter(writer_path)
dataset = img_dataset.ano_pred_Dataset(training_data_folder, frame_num)
dataset_loader = DataLoader(dataset=dataset,
batch_size=batch_size,
shuffle=True,
num_workers=1,
drop_last=True)
test_dataset = img_dataset.ano_pred_Dataset(testing_data_folder, frame_num)
test_dataloader = DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=1,
drop_last=True)
for epoch in range(epochs):
for (input, _), (test_input, _) in zip(dataset_loader,
test_dataloader):
# generator = generator.train()
# discriminator = discriminator.train()
target = input[:, -1, :, :, :].cuda()
input = input[:, :-1, ]
input_last = input[:, -1, ].cuda()
input = input.view(input.shape[0], -1, input.shape[-2],
input.shape[-1]).cuda()
test_target = test_input[:, -1, ].cuda()
test_input = test_input[:, :-1].view(test_input.shape[0], -1,
test_input.shape[-2],
test_input.shape[-1]).cuda()
#------- update optim_G --------------
G_output = generator(input)
pred_flow_esti_tensor = torch.cat([input_last, G_output], 1)
gt_flow_esti_tensor = torch.cat([input_last, target], 1)
flow_gt = batch_estimate(gt_flow_esti_tensor, flow_network)
flow_pred = batch_estimate(pred_flow_esti_tensor, flow_network)
g_adv_loss = adversarial_loss(discriminator(G_output))
g_op_loss = op_loss(flow_pred, flow_gt)
g_int_loss = int_loss(G_output, target)
g_gd_loss = gd_loss(G_output, target)
g_loss = lam_adv * g_adv_loss + lam_gd * g_gd_loss + lam_op * g_op_loss + lam_int * g_int_loss
optimizer_G.zero_grad()
g_loss.backward()
optimizer_G.step()
train_psnr = psnr_error(G_output, target)
#----------- update optim_D -------
optimizer_D.zero_grad()
d_loss = discriminate_loss(discriminator(target),
discriminator(G_output.detach()))
#d_loss.requires_grad=True
d_loss.backward()
optimizer_D.step()
#----------- cal psnr --------------
test_generator = generator.eval()
test_output = test_generator(test_input)
test_psnr = psnr_error(test_output, test_target).cuda()
if step % 10 == 0:
print("[{}/{}]: g_loss: {} d_loss {}".format(
step, epoch, g_loss, d_loss))
print('\t gd_loss {}, op_loss {}, int_loss {} ,'.format(
g_gd_loss, g_op_loss, g_int_loss))
print('\t train psnr{}，test_psnr {}'.format(
train_psnr, test_psnr))
writer.add_scalar('psnr/train_psnr',
train_psnr,
global_step=step)
writer.add_scalar('psnr/test_psnr',
test_psnr,
global_step=step)
writer.add_scalar('total_loss/g_loss',
g_loss,
global_step=step)
writer.add_scalar('total_loss/d_loss',
d_loss,
global_step=step)
writer.add_scalar('g_loss/adv_loss',
g_adv_loss,
global_step=step)
writer.add_scalar('g_loss/op_loss',
g_op_loss,
global_step=step)
writer.add_scalar('g_loss/int_loss',
g_int_loss,
global_step=step)
writer.add_scalar('g_loss/gd_loss',
g_gd_loss,
global_step=step)
writer.add_image('image/train_target',
target[0],
global_step=step)
writer.add_image('image/train_output',
G_output[0],
global_step=step)
writer.add_image('image/test_target',
test_target[0],
global_step=step)
writer.add_image('image/test_output',
test_output[0],
global_step=step)
step += 1
if step % 500 == 0:
utils.saver(generator.state_dict(),
model_generator_save_path,
step,
max_to_save=10)
utils.saver(discriminator.state_dict(),
model_discriminator_save_path,
step,
max_to_save=10)
if step >= 2000:
print('==== begin evaluate the model of {} ===='.format(
model_generator_save_path + '-' + str(step)))
auc = evaluate(frame_num=5,
layer_nums=4,
input_channels=12,
output_channels=3,
model_path=model_generator_save_path + '-' +
str(step),
evaluate_name='compute_auc')
writer.add_scalar('results/auc', auc, global_step=step)
def train(config):
#### set the save and log path ####
svname = args.name
if svname is None:
svname = config['train_dataset_type'] + '_' + config[
'generator'] + '_' + config['flow_model']
if args.tag is not None:
svname += '_' + args.tag
save_path = os.path.join('./save', svname)
utils.set_save_path(save_path)
utils.set_log_path(save_path)
writer = SummaryWriter(os.path.join(save_path, 'tensorboard'))
yaml.dump(config,
open(os.path.join(save_path, 'classifier_config.yaml'), 'w'))
#### make datasets ####
# train
train_folder = config['dataset_path'] + config[
'train_dataset_type'] + "/training/frames"
test_folder = config['dataset_path'] + config[
'train_dataset_type'] + "/testing/frames"
# Loading dataset
train_dataset_args = config['train_dataset_args']
test_dataset_args = config['test_dataset_args']
train_dataset = VadDataset(train_folder,
transforms.Compose([
transforms.ToTensor(),
]),
resize_height=train_dataset_args['h'],
resize_width=train_dataset_args['w'],
time_step=train_dataset_args['t_length'] - 1)
test_dataset = VadDataset(test_folder,
transforms.Compose([
transforms.ToTensor(),
]),
resize_height=test_dataset_args['h'],
resize_width=test_dataset_args['w'],
time_step=test_dataset_args['t_length'] - 1)
train_dataloader = DataLoader(
train_dataset,
batch_size=train_dataset_args['batch_size'],
shuffle=True,
num_workers=train_dataset_args['num_workers'],
drop_last=True)
test_dataloader = DataLoader(test_dataset,
batch_size=test_dataset_args['batch_size'],
shuffle=False,
num_workers=test_dataset_args['num_workers'],
drop_last=False)
# for test---- prepare labels
labels = np.load('./data/frame_labels_' + config['test_dataset_type'] +
'.npy')
if config['test_dataset_type'] == 'shanghai':
labels = np.expand_dims(labels, 0)
videos = OrderedDict()
videos_list = sorted(glob.glob(os.path.join(test_folder, '*')))
labels_list = []
label_length = 0
psnr_list = {}
for video in sorted(videos_list):
# video_name = video.split('/')[-1]
# windows
video_name = os.path.split(video)[-1]
videos[video_name] = {}
videos[video_name]['path'] = video
videos[video_name]['frame'] = glob.glob(os.path.join(video, '*.jpg'))
videos[video_name]['frame'].sort()
videos[video_name]['length'] = len(videos[video_name]['frame'])
labels_list = np.append(
labels_list,
labels[0][4 + label_length:videos[video_name]['length'] +
label_length])
label_length += videos[video_name]['length']
psnr_list[video_name] = []
# Model setting
num_unet_layers = 4
discriminator_num_filters = [128, 256, 512, 512]
# for gradient loss
alpha = 1
# for int loss
l_num = 2
pretrain = False
if config['generator'] == 'cycle_generator_convlstm':
ngf = 64
netG = 'resnet_6blocks'
norm = 'instance'
no_dropout = False
init_type = 'normal'
init_gain = 0.02
gpu_ids = []
generator = define_G(train_dataset_args['c'], train_dataset_args['c'],
ngf, netG, norm, not no_dropout, init_type,
init_gain, gpu_ids)
elif config['generator'] == 'unet':
# generator = UNet(n_channels=train_dataset_args['c']*(train_dataset_args['t_length']-1),
# layer_nums=num_unet_layers, output_channel=train_dataset_args['c'])
model = PreAE(train_dataset_args['c'], train_dataset_args['t_length'],
**config['model_args'])
else:
raise Exception('The generator is not implemented')
# generator = torch.load('save/avenue_cycle_generator_convlstm_flownet2_0103/generator-epoch-199.pth')
discriminator = PixelDiscriminator(train_dataset_args['c'],
discriminator_num_filters,
use_norm=False)
# discriminator = torch.load('save/avenue_cycle_generator_convlstm_flownet2_0103/discriminator-epoch-199.pth')
# if not pretrain:
# generator.apply(weights_init_normal)
# discriminator.apply(weights_init_normal)
# if use flownet
# if config['flow_model'] == 'flownet2':
# flownet2SD_model_path = 'flownet2/FlowNet2_checkpoint.pth.tar'
# flow_network = FlowNet2(args).eval()
# flow_network.load_state_dict(torch.load(flownet2SD_model_path)['state_dict'])
# elif config['flow_model'] == 'liteflownet':
# lite_flow_model_path = 'liteFlownet/network-sintel.pytorch'
# flow_network = Network().eval()
# flow_network.load_state_dict(torch.load(lite_flow_model_path))
# different range with the source version, should change
lam_int = 1.0 * 2
lam_gd = 1.0 * 2
# here we use no flow loss
lam_op = 0 # 2.0
lam_adv = 0.05
adversarial_loss = Adversarial_Loss()
discriminate_loss = Discriminate_Loss()
gd_loss = Gradient_Loss(alpha, train_dataset_args['c'])
op_loss = Flow_Loss()
int_loss = Intensity_Loss(l_num)
step = 0
utils.log('initializing the model with Generator-Unet {} layers,'
'PixelDiscriminator with filters {} '.format(
num_unet_layers, discriminator_num_filters))
g_lr = 0.0002
d_lr = 0.00002
optimizer_G = torch.optim.Adam(generator.parameters(), lr=g_lr)
optimizer_D = torch.optim.Adam(discriminator.parameters(), lr=d_lr)
# # optimizer setting
# params_encoder = list(generator.encoder.parameters())
# params_decoder = list(generator.decoder.parameters())
# params = params_encoder + params_decoder
# optimizer, lr_scheduler = utils.make_optimizer(
# params, config['optimizer'], config['optimizer_args'])
#
# loss_func_mse = nn.MSELoss(reduction='none')
# parallel if muti-gpus
if torch.cuda.is_available():
generator.cuda()
discriminator.cuda()
# # if use flownet
# flow_network.cuda()
adversarial_loss.cuda()
discriminate_loss.cuda()
gd_loss.cuda()
op_loss.cuda()
int_loss.cuda()
if config.get('_parallel'):
generator = nn.DataParallel(generator)
discriminator = nn.DataParallel(discriminator)
# if use flownet
# flow_network = nn.DataParallel(flow_network)
adversarial_loss = nn.DataParallel(adversarial_loss)
discriminate_loss = nn.DataParallel(discriminate_loss)
gd_loss = nn.DataParallel(gd_loss)
op_loss = nn.DataParallel(op_loss)
int_loss = nn.DataParallel(int_loss)
# Training
utils.log('Start train')
max_accuracy = 0
base_channel_num = train_dataset_args['c'] * (
train_dataset_args['t_length'] - 1)
save_epoch = 5 if config['save_epoch'] is None else config['save_epoch']
for epoch in range(config['epochs']):
generator.train()
for j, imgs in enumerate(
tqdm(train_dataloader, desc='train', leave=False)):
imgs = imgs.cuda()
input = imgs[:, :-1, ]
input_last = input[:, -1, ]
target = imgs[:, -1, ]
# input = input.view(input.shape[0], -1, input.shape[-2],input.shape[-1])
# only for debug
# input0=imgs[:, 0,]
# input1 = imgs[:, 1, ]
# gt_flow_esti_tensor = torch.cat([input0, input1], 1)
# flow_gt = batch_estimate(gt_flow_esti_tensor, flow_network)[0]
# objectOutput = open('./out_train.flo', 'wb')
# np.array([80, 73, 69, 72], np.uint8).tofile(objectOutput)
# np.array([flow_gt.size(2), flow_gt.size(1)], np.int32).tofile(objectOutput)
# np.array(flow_gt.detach().cpu().numpy().transpose(1, 2, 0), np.float32).tofile(objectOutput)
# objectOutput.close()
# break
# ------- update optim_G --------------
outputs = generator(input)
# pred_flow_tensor = torch.cat([input_last, outputs], 1)
# gt_flow_tensor = torch.cat([input_last, target], 1)
# flow_pred = batch_estimate(pred_flow_tensor, flow_network)
# flow_gt = batch_estimate(gt_flow_tensor, flow_network)
# if you want to use flownet2SD, comment out the part in front
# #### if use flownet ####
# pred_flow_esti_tensor = torch.cat([input_last.view(-1,3,1,input.shape[-2],input.shape[-1]),
# outputs.view(-1,3,1,input.shape[-2],input.shape[-1])], 2)
# gt_flow_esti_tensor = torch.cat([input_last.view(-1,3,1,input.shape[-2],input.shape[-1]),
# target.view(-1,3,1,input.shape[-2],input.shape[-1])], 2)
# flow_gt=flow_network(gt_flow_esti_tensor*255.0)
# flow_pred=flow_network(pred_flow_esti_tensor*255.0)
##############################
# g_op_loss = op_loss(flow_pred, flow_gt) ## flow loss
g_op_loss = 0
g_adv_loss = adversarial_loss(discriminator(outputs))
g_int_loss = int_loss(outputs, target)
g_gd_loss = gd_loss(outputs, target)
g_loss = lam_adv * g_adv_loss + lam_gd * g_gd_loss + lam_op * g_op_loss + lam_int * g_int_loss
optimizer_G.zero_grad()
g_loss.backward()
optimizer_G.step()
train_psnr = utils.psnr_error(outputs, target)
# ----------- update optim_D -------
optimizer_D.zero_grad()
d_loss = discriminate_loss(discriminator(target),
discriminator(outputs.detach()))
d_loss.backward()
optimizer_D.step()
# break
# lr_scheduler.step()
utils.log('----------------------------------------')
utils.log('Epoch:' + str(epoch + 1))
utils.log('----------------------------------------')
utils.log("g_loss: {} d_loss {}".format(g_loss, d_loss))
utils.log('\t gd_loss {}, op_loss {}, int_loss {} ,'.format(
g_gd_loss, g_op_loss, g_int_loss))
utils.log('\t train psnr{}'.format(train_psnr))
# Testing
utils.log('Evaluation of ' + config['test_dataset_type'])
for video in sorted(videos_list):
# video_name = video.split('/')[-1]
video_name = os.path.split(video)[-1]
psnr_list[video_name] = []
generator.eval()
video_num = 0
# label_length += videos[videos_list[video_num].split('/')[-1]]['length']
label_length = videos[os.path.split(
videos_list[video_num])[1]]['length']
for k, imgs in enumerate(
tqdm(test_dataloader, desc='test', leave=False)):
if k == label_length - 4 * (video_num + 1):
video_num += 1
label_length += videos[os.path.split(
videos_list[video_num])[1]]['length']
imgs = imgs.cuda()
input = imgs[:, :-1, ]
target = imgs[:, -1, ]
# input = input.view(input.shape[0], -1, input.shape[-2], input.shape[-1])
outputs = generator(input)
mse_imgs = int_loss((outputs + 1) / 2, (target + 1) / 2).item()
# psnr_list[videos_list[video_num].split('/')[-1]].append(utils.psnr(mse_imgs))
psnr_list[os.path.split(videos_list[video_num])[1]].append(
utils.psnr(mse_imgs))
# Measuring the abnormality score and the AUC
anomaly_score_total_list = []
for video in sorted(videos_list):
# video_name = video.split('/')[-1]
video_name = os.path.split(video)[1]
anomaly_score_total_list += utils.anomaly_score_list(
psnr_list[video_name])
anomaly_score_total_list = np.asarray(anomaly_score_total_list)
accuracy = utils.AUC(anomaly_score_total_list,
np.expand_dims(1 - labels_list, 0))
utils.log('The result of ' + config['test_dataset_type'])
utils.log('AUC: ' + str(accuracy * 100) + '%')
# Save the model
if epoch % save_epoch == 0 or epoch == config['epochs'] - 1:
# torch.save(model, os.path.join(
# save_path, 'model-epoch-{}.pth'.format(epoch)))
torch.save(
generator,
os.path.join(save_path,
'generator-epoch-{}.pth'.format(epoch)))
torch.save(
discriminator,
os.path.join(save_path,
'discriminator-epoch-{}.pth'.format(epoch)))
if accuracy > max_accuracy:
torch.save(generator, os.path.join(save_path, 'generator-max'))
torch.save(discriminator,
os.path.join(save_path, 'discriminator-max'))
utils.log('----------------------------------------')
utils.log('Training is finished')
def train(config):
#### set the save and log path ####
save_path = config['save_path']
utils.set_save_path(save_path)
utils.set_log_path(save_path)
writer = SummaryWriter(os.path.join(config['save_path'], 'tensorboard'))
yaml.dump(config, open(os.path.join(config['save_path'], 'classifier_config.yaml'), 'w'))
device = torch.device('cuda:' + args.gpu)
#### make datasets ####
# train
train_folder = config['dataset_path'] + config['train_dataset_type'] + "/training/frames"
test_folder = config['dataset_path'] + config['train_dataset_type'] + "/testing/frames"
# Loading dataset
train_dataset_args = config['train_dataset_args']
test_dataset_args = config['test_dataset_args']
train_dataset = VadDataset(args,video_folder= train_folder, bbox_folder = config['train_bboxes_path'], flow_folder=config['train_flow_path'],
transform=transforms.Compose([transforms.ToTensor()]),
resize_height=train_dataset_args['h'], resize_width=train_dataset_args['w'],
dataset=config['train_dataset_type'], time_step=train_dataset_args['t_length'] - 1,
device=device)
test_dataset = VadDataset(args,video_folder= test_folder, bbox_folder = config['test_bboxes_path'], flow_folder=config['test_flow_path'],
transform=transforms.Compose([transforms.ToTensor()]),
resize_height=train_dataset_args['h'], resize_width=train_dataset_args['w'],
dataset=config['train_dataset_type'], time_step=train_dataset_args['t_length'] - 1,
device=device)
train_dataloader = DataLoader(train_dataset, batch_size=train_dataset_args['batch_size'],
shuffle=True, num_workers=train_dataset_args['num_workers'], drop_last=True)
test_dataloader = DataLoader(test_dataset, batch_size=test_dataset_args['batch_size'],
shuffle=False, num_workers=test_dataset_args['num_workers'], drop_last=False)
# for test---- prepare labels
labels = np.load('./data/frame_labels_' + config['test_dataset_type'] + '.npy')
if config['test_dataset_type'] == 'shanghai':
labels = np.expand_dims(labels, 0)
videos = OrderedDict()
videos_list = sorted(glob.glob(os.path.join(test_folder, '*')))
labels_list = []
label_length = 0
psnr_list = {}
for video in sorted(videos_list):
video_name = video.split('/')[-1]
videos[video_name] = {}
videos[video_name]['path'] = video
videos[video_name]['frame'] = glob.glob(os.path.join(video, '*.jpg'))
videos[video_name]['frame'].sort()
videos[video_name]['length'] = len(videos[video_name]['frame'])
labels_list = np.append(labels_list, labels[0][4 + label_length:videos[video_name]['length'] + label_length])
label_length += videos[video_name]['length']
psnr_list[video_name] = []
# Model setting
num_unet_layers = 4
discriminator_num_filters = [128, 256, 512, 512]
# for gradient loss
alpha = 1
# for int loss
l_num = 2
pretrain = False
if config['generator'] == 'cycle_generator_convlstm':
ngf = 64
netG = 'resnet_6blocks'
norm = 'instance'
no_dropout = False
init_type = 'normal'
init_gain = 0.02
gpu_ids = []
model = define_G(train_dataset_args['c'], train_dataset_args['c'],
ngf, netG, norm, not no_dropout, init_type, init_gain, gpu_ids)
elif config['generator'] == 'unet':
# generator = UNet(n_channels=train_dataset_args['c']*(train_dataset_args['t_length']-1),
# layer_nums=num_unet_layers, output_channel=train_dataset_args['c'])
model = PreAE(train_dataset_args['c'], train_dataset_args['t_length'], **config['model_args'])
else:
raise Exception('The generator is not implemented')
# generator = torch.load('save/avenue_cycle_generator_convlstm_flownet2_0103/generator-epoch-199.pth')
if config['use_D']:
discriminator=PixelDiscriminator(train_dataset_args['c'],discriminator_num_filters,use_norm=False)
optimizer_D = torch.optim.Adam(discriminator.parameters(),lr=0.00002)
# optimizer setting
params_encoder = list(model.parameters())
params_decoder = list(model.parameters())
params = params_encoder + params_decoder
optimizer_G, lr_scheduler = utils.make_optimizer(
params, config['optimizer'], config['optimizer_args'])
# set loss, different range with the source version, should change
lam_int = 1.0 * 2
lam_gd = 1.0 * 2
# TODO here we use no flow loss
# lam_op = 0 # 2.0
# op_loss = Flow_Loss()
adversarial_loss = Adversarial_Loss()
# TODO if use adv
lam_adv = 0.05
discriminate_loss = Discriminate_Loss()
alpha = 1
l_num = 2
gd_loss = Gradient_Loss(alpha, train_dataset_args['c'])
int_loss = Intensity_Loss(l_num)
object_loss = ObjectLoss(device, l_num)
# parallel if muti-gpus
if torch.cuda.is_available():
model.cuda()
if config['use_D']:
discriminator.cuda()
if config.get('_parallel'):
model = nn.DataParallel(model)
if config['use_D']:
discriminator = nn.DataParallel(discriminator)
# Training
utils.log('Start train')
max_frame_AUC, max_roi_AUC = 0,0
base_channel_num = train_dataset_args['c'] * (train_dataset_args['t_length'] - 1)
save_epoch = 5 if config['save_epoch'] is None else config['save_epoch']
for epoch in range(config['epochs']):
model.train()
for j, (imgs, bbox, flow) in enumerate(tqdm(train_dataloader, desc='train', leave=False)):
imgs = imgs.cuda()
flow = flow.cuda()
# input = imgs[:, :-1, ].view(imgs.shape[0], -1, imgs.shape[-2], imgs.shape[-1])
input = imgs[:, :-1, ]
target = imgs[:, -1, ]
outputs = model(input)
if config['use_D']:
g_adv_loss = adversarial_loss(discriminator(outputs))
else:
g_adv_loss = 0
g_object_loss = object_loss(outputs, target, flow, bbox)
# g_int_loss = int_loss(outputs, target)
g_gd_loss = gd_loss(outputs, target)
g_loss = lam_adv * g_adv_loss + lam_gd * g_gd_loss + lam_int * g_object_loss
optimizer_G.zero_grad()
g_loss.backward()
optimizer_G.step()
train_psnr = utils.psnr_error(outputs,target)
# ----------- update optim_D -------
if config['use_D']:
optimizer_D.zero_grad()
d_loss = discriminate_loss(discriminator(target), discriminator(outputs.detach()))
d_loss.backward()
optimizer_D.step()
lr_scheduler.step()
utils.log('----------------------------------------')
utils.log('Epoch:' + str(epoch + 1))
utils.log('----------------------------------------')
utils.log('Loss: Reconstruction {:.6f}'.format(g_loss.item()))
# Testing
utils.log('Evaluation of ' + config['test_dataset_type'])
# Save the model
if epoch % save_epoch == 0 or epoch == config['epochs'] - 1:
if not os.path.exists(save_path):
os.makedirs(save_path)
if not os.path.exists(os.path.join(save_path, "models")):
os.makedirs(os.path.join(save_path, "models"))
# TODO
frame_AUC = ObjectLoss_evaluate(test_dataloader, model, labels_list, videos, dataset=config['test_dataset_type'],device = device,
frame_height = train_dataset_args['h'], frame_width=train_dataset_args['w'],
is_visual=False, mask_labels_path = config['mask_labels_path'], save_path = os.path.join(save_path, "./final"), labels_dict=labels)
torch.save(model.state_dict(), os.path.join(save_path, 'models/model-epoch-{}.pth'.format(epoch)))
if config['use_D']:
torch.save(discriminator.state_dict(), os.path.join(save_path, 'models/discrominator-epoch-{}.pth'.format(epoch)))
else:
frame_AUC = ObjectLoss_evaluate(test_dataloader, model, labels_list, videos, dataset=config['test_dataset_type'],device=device,
frame_height = train_dataset_args['h'], frame_width=train_dataset_args['w'])
utils.log('The result of ' + config['test_dataset_type'])
utils.log("AUC: {}%".format(frame_AUC*100))
if frame_AUC > max_frame_AUC:
max_frame_AUC = frame_AUC
# TODO
torch.save(model.state_dict(), os.path.join(save_path, 'models/max-frame_auc-model.pth'))
if config['use_D']:
torch.save(discriminator.state_dict(), os.path.join(save_path, 'models/discrominator-epoch-{}.pth'.format(epoch)))
# evaluate(test_dataloader, model, labels_list, videos, int_loss, config['test_dataset_type'], test_bboxes=config['test_bboxes'],
# frame_height = train_dataset_args['h'], frame_width=train_dataset_args['w'],
# is_visual=True, mask_labels_path = config['mask_labels_path'], save_path = os.path.join(save_path, "./frame_best"), labels_dict=labels)
utils.log('----------------------------------------')
utils.log('Training is finished')
utils.log('max_frame_AUC: {}'.format(max_frame_AUC))
parser.add_argument('--iters', default=40000, type=int, help='The total iteration number.')
parser.add_argument('--resume', default=None, type=str,
help='The pre-trained model to resume training with, pass \'latest\' or the model name.')
parser.add_argument('--save_interval', default=1000, type=int, help='Save the model every [save_interval] iterations.')
parser.add_argument('--val_interval', default=1000, type=int,
help='Evaluate the model every [val_interval] iterations, pass -1 to disable.')
parser.add_argument('--show_flow', default=False, action='store_true',
help='If True, the first batch of ground truth optic flow could be visualized and saved.')
parser.add_argument('--flownet', default='lite', type=str, help='lite: LiteFlownet, 2sd: FlowNet2SD.')
args = parser.parse_args()
train_cfg = update_config(args, mode='train')
train_cfg.print_cfg()
generator = UNet(input_channels=12, output_channel=3).cuda()
discriminator = PixelDiscriminator(input_nc=3).cuda()
optimizer_G = torch.optim.Adam(generator.parameters(), lr=train_cfg.g_lr)
optimizer_D = torch.optim.Adam(discriminator.parameters(), lr=train_cfg.d_lr)
if train_cfg.resume:
generator.load_state_dict(torch.load(train_cfg.resume)['net_g'])
discriminator.load_state_dict(torch.load(train_cfg.resume)['net_d'])
optimizer_G.load_state_dict(torch.load(train_cfg.resume)['optimizer_g'])
optimizer_D.load_state_dict(torch.load(train_cfg.resume)['optimizer_d'])
print(f'Pre-trained generator and discriminator have been loaded.\n')
else:
generator.apply(weights_init_normal)
discriminator.apply(weights_init_normal)
print('Generator and discriminator are going to be trained from scratch.\n')
assert train_cfg.flownet in ('lite', '2sd'), 'Flow net only supports LiteFlownet or FlowNet2SD currently.'