def main():
torch.set_grad_enabled(False)
torch.backends.cudnn.benchmark = True
test_dir = "./input/deepfake-detection-challenge/test_videos"
csv_path = "./input/deepfake-detection-challenge/sample_submission.csv"
face_detector = FaceDetector()
face_detector.load_checkpoint(
"./input/dfdc-pretrained-2/RetinaFace-Resnet50-fixed.pth")
loader = DFDCLoader(test_dir, face_detector, T.ToTensor())
model1 = xception(num_classes=2, pretrained=False)
ckpt = torch.load("./input/dfdc-pretrained-2/xception-hg-2.pth",
map_location=torch.device('cpu'))
model1.load_state_dict(ckpt["state_dict"])
model1 = model1.cpu()
model1.eval()
model2 = WSDAN(num_classes=2, M=8, net="xception", pretrained=False).cpu()
ckpt = torch.load("./input/dfdc-pretrained-2/ckpt_x.pth",
map_location=torch.device('cpu'))
model2.load_state_dict(ckpt["state_dict"])
model2.eval()
model3 = WSDAN(num_classes=2, M=8, net="efficientnet",
pretrained=False).cpu()
ckpt = torch.load("./input/dfdc-pretrained-2/ckpt_e.pth",
map_location=torch.device('cpu'))
model3.load_state_dict(ckpt["state_dict"])
model3.eval()
zhq_nm_avg = torch.Tensor([.4479, .3744, .3473]).view(1, 3, 1, 1).cpu()
zhq_nm_std = torch.Tensor([.2537, .2502, .2424]).view(1, 3, 1, 1).cpu()
for batch in loader:
batch = batch.cpu()
i1 = F.interpolate(batch, size=299, mode="bilinear")
i1.sub_(0.5).mul_(2.0)
o1 = model1(i1).softmax(-1)[:, 1].cpu().numpy()
i2 = (batch - zhq_nm_avg) / zhq_nm_std
o2, _, _ = model2(i2)
o2 = o2.softmax(-1)[:, 1].cpu().numpy()
i3 = F.interpolate(i2, size=300, mode="bilinear")
o3, _, _ = model3(i3)
o3 = o3.softmax(-1)[:, 1].cpu().numpy()
out = 0.2 * o1 + 0.7 * o2 + 0.1 * o3
loader.feedback(out)
with open(csv_path) as fin, open("submission.csv", "w") as fout:
fout.write(next(fin))
for line in fin:
fname = line.split(",", 1)[0]
pred = loader.score[fname]
print("%s,%.6f" % (fname, pred), file=fout)
def main():
torch.set_grad_enabled(False)
torch.backends.cudnn.benchmark = True
# test_dir = "../input/deepfake-detection-challenge/test_videos"
# csv_path = "../input/deepfake-detection-challenge/sample_submission.csv"
test_dir = "./data/train_sample_videos"
csv_path = "./dfdc-data.csv"
face_detector = FaceDetector()
# face_detector.load_checkpoint("../input/dfdc-pretrained-2/RetinaFace-Resnet50-fixed.pth")
face_detector.load_checkpoint("./RetinaFace-Resnet50-fixed.pth")
loader = DFDCLoader(test_dir, face_detector, T.ToTensor())
model1 = xception(num_classes=2, pretrained=False)
# ckpt = torch.load("../input/dfdc-pretrained-2/xception-hg-2.pth")
ckpt = torch.load("./xception-hg-2.pth")
model1.load_state_dict(ckpt["state_dict"])
model1 = model1.cuda()
model1.eval()
model2 = WSDAN(num_classes=2, M=8, net="xception", pretrained=False).cuda()
# ckpt = torch.load("../input/dfdc-pretrained-2/ckpt_x.pth")
ckpt = torch.load("./ckpt_x.pth")
model2.load_state_dict(ckpt["state_dict"])
model2.eval()
model3 = WSDAN(num_classes=2, M=8, net="efficientnet",
pretrained=False).cuda()
# ckpt = torch.load("../input/dfdc-pretrained-2/ckpt_e.pth")
ckpt = torch.load("./ckpt_e.pth")
model3.load_state_dict(ckpt["state_dict"])
model3.eval()
zhq_nm_avg = torch.Tensor([.4479, .3744, .3473]).view(1, 3, 1, 1).cuda()
zhq_nm_std = torch.Tensor([.2537, .2502, .2424]).view(1, 3, 1, 1).cuda()
for batch in loader:
batch = batch.cuda(non_blocking=True)
i1 = F.interpolate(batch, size=299, mode="bilinear")
i1.sub_(0.5).mul_(2.0)
o1 = model1(i1).softmax(-1)[:, 1].cpu().numpy()
i2 = (batch - zhq_nm_avg) / zhq_nm_std
o2, _, _ = model2(i2)
o2 = o2.softmax(-1)[:, 1].cpu().numpy()
i3 = F.interpolate(i2, size=300, mode="bilinear")
o3, _, _ = model3(i3)
o3 = o3.softmax(-1)[:, 1].cpu().numpy()
out = 0.2 * o1 + 0.7 * o2 + 0.1 * o3
loader.feedback(out)
with open("submission.csv", "w") as fout:
for fname in loader.file_list:
pred = loader.score[fname]
start_time = loader.infer_start[fname]
end_time = loader.infer_end[fname]
print("%s\t%.6f\t%d\t%d" %
(fname.split('.')[0], pred, start_time, end_time),
file=fout)
def main():
torch.backends.cudnn.benchmark = True
train_dataset = DFDCDataset(config.data_list,
"train",
config.data_root,
transform=train_transform)
val_dataset = DFDCDataset(config.data_list,
"val",
config.data_root,
transform=val_transform,
stable=True)
kwargs = dict(batch_size=config.batch_size,
num_workers=config.num_workers,
shuffle=True,
pin_memory=True)
train_loader = DataLoader(train_dataset, **kwargs)
val_loader = DataLoader(val_dataset, **kwargs)
# Model initialization
model = xception(num_classes=2, pretrained=None)
if hasattr(config, "resume") and os.path.isfile(config.resume):
ckpt = torch.load(config.resume, map_location="cpu")
start_epoch = ckpt.get("epoch", 0)
best_acc = ckpt.get("acc1", 0.0)
model.load_state_dict(ckpt["state_dict"])
else:
start_epoch = 0
best_acc = 0.0
model = model.cuda()
model = nn.DataParallel(model)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(),
0.01,
momentum=0.9,
weight_decay=1e-4)
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=2, gamma=0.2)
os.makedirs(config.save_dir, exist_ok=True)
for epoch in range(config.n_epoches):
if epoch < start_epoch:
scheduler.step()
continue
print("Epoch {}".format(epoch + 1))
model.train()
loss_record = []
acc_record = []
for count, (inputs, labels) in enumerate(train_loader):
inputs = inputs.cuda(non_blocking=True)
labels = labels.cuda(non_blocking=True)
outputs = model(inputs)
loss = criterion(outputs, labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
iter_loss = loss.item()
loss_record.append(iter_loss)
preds = torch.argmax(outputs.data, 1)
iter_acc = torch.sum(preds == labels).item() / len(preds)
acc_record.append(iter_acc)
if count and count % 100 == 0:
print("T-Iter %d: loss=%.4f, acc=%.4f" %
(count, iter_loss, iter_acc))
epoch_loss = np.mean(loss_record)
epoch_acc = np.mean(acc_record)
print("Training: loss=%.4f, acc=%.4f" % (epoch_loss, epoch_acc))
model.eval()
loss_record = []
acc_record = []
with torch.no_grad():
for count, (inputs, labels) in enumerate(val_loader):
inputs = inputs.cuda(non_blocking=True)
labels = labels.cuda(non_blocking=True)
outputs = model(inputs)
preds = torch.argmax(outputs, 1)
loss = criterion(outputs, labels)
iter_loss = loss.item()
loss_record.append(iter_loss)
preds = torch.argmax(outputs.data, 1)
iter_acc = torch.sum(preds == labels).item() / len(preds)
acc_record.append(iter_acc)
if count and count % 100 == 0:
print("V-Iter %d: loss=%.4f, acc=%.4f" %
(count, iter_loss, iter_acc))
epoch_loss = np.mean(loss_record)
epoch_acc = np.mean(acc_record)
print("Validation: loss=%.4f, acc=%.4f" % (epoch_loss, epoch_acc))
scheduler.step()
ckpt_path = os.path.join(config.save_dir, "ckpt-%d.pth" % epoch)
save_checkpoint(ckpt_path,
model.state_dict(),
epoch=epoch + 1,
acc1=epoch_acc)
if epoch_acc > best_acc:
print("Best accuracy!")
shutil.copy(ckpt_path, os.path.join(config.save_dir,
"best.pth"))
best_acc = epoch_acc
print()