def main():
batch_size = 20
# model = models.resnet18(pretrained=False)
model = get_model("xception", pretrained=False)
model = nn.Sequential(*list(
model.children())[:-1]) # Remove original output layer
model[0].final_block.pool = nn.Sequential(nn.AdaptiveAvgPool2d(1)) # xcep
model = FCN(model, 2048)
model.cuda()
train_data = Task1_loader("./Task_1/train.csv", phase='train')
test_data = Task1_loader("./Task_1/test.csv", phase='test')
train_loader = DataLoader(train_data,
batch_size=batch_size,
shuffle=True,
num_workers=8)
valid_loader = DataLoader(test_data,
batch_size=batch_size,
shuffle=False,
num_workers=8)
criterion = nn.BCELoss()
# optimizer = optim.SGD(model.parameters(), lr=0.0018, momentum=0.27)
optimizer = optim.Adam(model.parameters(), lr=1e-4, weight_decay=1e-5)
train(model,
train_loader,
valid_loader,
criterion,
optimizer,
100,
device='cuda')
def __init__(self, pretrained=True, latent_layer_num=20):
super().__init__()
model = get_model("mobilenet_w1", pretrained=pretrained)
model.features.final_pool = nn.AvgPool2d(4)
all_layers = []
remove_sequential(model, all_layers)
all_layers = remove_DwsConvBlock(all_layers)
lat_list = []
end_list = []
for i, layer in enumerate(all_layers[:-1]):
if i <= latent_layer_num:
lat_list.append(layer)
else:
# ABB: Canviar estructura!
end_list.append(layer)
self.lat_features = nn.Sequential(*lat_list)
self.end_features = nn.Sequential(*end_list)
self.output = nn.Linear(1024, 50, bias=False)
self.rf = nn.Linear(1024, 1, bias=False)
self.sig = nn.Sigmoid()
def xception2(pretrained=False):
model = get_model("xception", pretrained=pretrained)
model = nn.Sequential(*list(
model.children())[:-1]) # Remove original output layer
model[0].final_block.pool = nn.Sequential(nn.Flatten())
model = FCN2(model)
return model
def xception(pretrained=False):
model = get_model("xception", pretrained=pretrained)
model = nn.Sequential(*list(
model.children())[:-1]) # Remove original output layer
model[0].final_block.pool = nn.Sequential(nn.AdaptiveAvgPool2d((1, 1)))
model = FCN(model, 2048)
return model
def create_model(predict_only: bool, dropout: float) -> Any:
logger.info(f'creating a model {opt.MODEL.ARCH}')
model = get_model(opt.MODEL.ARCH,
pretrained=not predict_only,
root=opt.PRETRAINED_PATH)
if 'ception' not in opt.MODEL.ARCH:
model.features[-1] = nn.AdaptiveAvgPool2d(1)
if opt.MODEL.ARCH == 'pnasnet5large':
if dropout < 0.1:
model.output = nn.Linear(model.output[-1].in_features,
opt.MODEL.NUM_CLASSES)
else:
model.output = nn.Sequential(
nn.Dropout(dropout),
nn.Linear(model.output[-1].in_features, opt.MODEL.NUM_CLASSES))
elif 'ception' in opt.MODEL.ARCH:
model.output[-1] = nn.Linear(model.output[-1].in_features,
opt.MODEL.NUM_CLASSES)
else:
if dropout < 0.1:
model.output = nn.Linear(model.output.in_features,
opt.MODEL.NUM_CLASSES)
else:
model.output = nn.Sequential(
nn.Dropout(dropout),
nn.Linear(model.output.in_features, opt.MODEL.NUM_CLASSES))
model = torch.nn.DataParallel(model).cuda()
model.cuda()
return model
def __init__(self, model_name, dropout):
super().__init__()
model = get_model(model_name, pretrained='imagenet')
self.backbone = model.features
_, n_features, *_ = self.backbone(torch.rand(1, 3, 256, 256)).size()
self.linear = nn.Sequential(nn.Dropout(dropout),
nn.Linear(n_features, 4),
)
def __init__(self):
super(CNNModel, self).__init__()
# Load pretrained network as backbone
pretrained = get_model(opt.classifier, pretrained=True)
self.backbone = pretrained.features
self.output = pretrained.output
self.classifier = nn.Linear(1000, 7)
del pretrained
def load_net(self, back_bone, weight_path):
net = get_model(back_bone, pretrained=True)
net.features.final_pool = nn.AdaptiveAvgPool2d(1)
net.output = nn.Sequential()
state_dict = torch.load(weight_path)
net.load_state_dict(state_dict, strict=False)
net.cuda()
net.eval()
return net
def load_net(load_pth='../../Fancy.1e-2.mobilenet/models/step_100000.pth'):
net = get_model('mobilenet_w1', pretrained=True)
net.features.final_pool = nn.AdaptiveAvgPool2d(1)
net.output = nn.Sequential()
state_dict = torch.load(load_pth)
net.load_state_dict(state_dict, strict=False)
return net
def GetPretrainedXception(
path='{}/../weights/xception/best_model.pth.tar'.format(abspath)):
model = get_model("xception", pretrained=False)
model = nn.Sequential(*list(model.children())[:-1])
model[0].final_block.pool = nn.Sequential(nn.AdaptiveAvgPool2d(1))
model = FCN(model, 2048)
chpt = torch.load(path)
model.load_state_dict(chpt['model'])
return model
def load_net(load_pth='models/latest.pth'):
net = get_model('resnet50', pretrained=True)
net.features.final_pool = nn.AdaptiveAvgPool2d(1)
net.output = nn.Linear(2048, 228)
if os.path.isfile(load_pth):
state_dict = torch.load(load_pth)
net.load_state_dict(state_dict)
return net
def load_net(load_pth='../../../Naive/models/step_99500.pth'):
net = get_model('resnet50', pretrained=True)
net.features.final_pool = nn.AdaptiveAvgPool2d(1)
net.output = nn.Sequential()
if os.path.isfile(load_pth):
state_dict = torch.load(load_pth)
net.load_state_dict(state_dict, strict=False)
return net
def load_net(load_pth='models/step_100000.pth'):
net = get_model('mobilenet_w1', pretrained=True)
net.features.final_pool = nn.AdaptiveAvgPool2d(1)
net.output = nn.Linear(1024, 228)
if os.path.isfile(load_pth):
state_dict = torch.load(load_pth)
net.load_state_dict(state_dict)
return net
def load_net(load_pth=''):
net = get_model('mobilenet_w1', pretrained=True)
net.features.final_pool = nn.AdaptiveAvgPool2d(1)
net.output = nn.Sequential()
if os.path.isfile(load_pth):
state_dict = torch.load(load_pth)
net.load_state_dict(state_dict, strict=False)
return net
def load_model(name, checkpoint_path=None, pretrained=False):
model = get_model(name, pretrained=pretrained)
model = nn.Sequential(*list(
model.children())[:-1]) # Remove original output layer
model[0].final_pool = nn.Sequential(nn.AdaptiveAvgPool2d(1))
# model[0].final_pool = nn.Sequential(Pooling())
model = FCN(model, 2048)
if checkpoint_path is not None:
model.load_state_dict(torch.load(checkpoint_path))
return model
def __init__(self, model_name):
super(CNNModel, self).__init__()
# Load pretrained network as backbone
pretrained = get_model(model_name, pretrained=True)
# remove last layer of fc
self.backbone = pretrained.features
# pretrained.output.fc3 = nn.Linear(4096, 7)
self.output = pretrained.output
self.classifier = nn.Linear(1000, 7)
# nn.init.zeros_(self.classifier.fc3.bias)
# nn.init.normal_(self.classifier.fc3.weight, mean=0.0, std=0.02)
del pretrained
def build_model(args, device):
weight_path = args.weight_path
if args.model_type == 'lrcn':
assert args.batch_size <= 8
model = get_model("xception", pretrained=True)
model = nn.Sequential(*list(model.children())[:-1])
model[0].final_block.pool = nn.Sequential(nn.AdaptiveAvgPool2d((1, 1)))
freeze_until(model, 'base.0.stage4.unit1.identity_conv.conv.weight')
lrcn_model = LRCN(model, 300, 1)
lrcn_model.to(device)
return lrcn_model
if args.model == 'resnet50':
model = BaseCNN('resnet50',
pretrained='imagenet',
dropout_ratio=args.dropout,
GeM_pool=True)
freeze_until(model, "base_model.layer3.0.conv1.weight")
print("fine-tuning resnet50")
elif args.model == 'resnext':
model = MyResNeXt(checkpoint=weight_path)
freeze_until(model, "layer4.0.conv1.weight")
print("fine-tuning resnext")
elif args.model == 'xception':
assert args.batch_size <= 16
model = get_model("xception", pretrained=True)
model = nn.Sequential(*list(model.children())[:-1])
model[0].final_block.pool = nn.Sequential(nn.AdaptiveAvgPool2d((1, 1)))
model = FCN(model, 2048)
freeze_until(model, 'base.0.stage4.unit1.identity_conv.conv.weight')
print("fine-tuning xception")
model.to(device)
return model
def __init__(self,
encoder_params: dict,
num_classes: int,
dropout: float = 0.2):
super().__init__()
model = model_provider.get_model(**encoder_params)
self.backbone = model.features
self.backbone.final_pool = nn.AdaptiveAvgPool2d((1, 1))
_, n_features, *_ = self.backbone(torch.rand(
2, 3, 32, 32)).size() # backbone last layer `out_features`
self.linear = nn.Sequential(
collections.OrderedDict([
('dropout', nn.Dropout(dropout)),
('fc', nn.Linear(n_features, num_classes)),
]))
def evaluate_root(source_dir, output_dir, epsilon, eval_set, defenses,
**kwargs):
ori_dataset = OriginalDataset(data_dir=source_dir)
adv_dataset = OriginalDataset(data_dir=output_dir,
transform=build_transforms(defenses))
adv_dataloader = DataLoader(adv_dataset, batch_size=1)
if check_adv_validity(ori_dataset, adv_dataset, epsilon):
print('✓ Adversarial dataset validity passed!')
else:
print('❌ Adversarial dataset validity not passed!')
return
accuracies = np.empty((len(eval_models[eval_set]), 10))
for i, model_name in enumerate(eval_models[eval_set]):
model = get_model(model_name, pretrained=True)
accuracies[i] = evaluate_single_model(
model_name.replace('_cifar10', ''), model, adv_dataloader)
means = np.mean(accuracies, axis=1)
# Print markdown table
with (output_dir / f'result-{eval_set}{"-defense" if defenses else ""}.md'
).open('w') as f:
print('Evaluation results: ', file=f)
print(
f"| Models | {' | '.join(s.replace('_cifar10', '') for s in eval_models[eval_set])} |",
file=f)
print(f"| ---------- |{'|'.join('------' for _ in eval_models)}|",
file=f)
for i, label_name in enumerate(all_labels):
print(
f"| {label_name:10s} |{'|'.join(f' {k:.2f} ' for k in accuracies[:, i])}|",
file=f)
print(
f"| Mean |{'|'.join(f' {k:.2f} ' for k in means)}| {np.mean(means):.4f} | {np.std(means):.4f} |",
file=f)
print(f'\nCategory-wise accuracies', file=f)
print(f"{'|'.join(f' {k:.2f} ' for k in np.mean(accuracies, axis=0))}",
file=f)
print(
f"\n> Overall: mean = {np.mean(means):.4f}, std = {np.std(means):.4f}",
file=f)
def __init__(self) -> None:
super().__init__()
self.model = get_model(config.model.arch,
pretrained=not args.gen_predict)
assert config.model.input_size % 32 == 0
self.model.features[-1] = nn.AdaptiveAvgPool2d(1)
in_features = self.model.output.in_features
if config.model.bottleneck_fc is not None:
self.model.output = nn.Sequential(
nn.Linear(in_features, config.model.bottleneck_fc),
nn.Linear(config.model.bottleneck_fc,
config.model.num_classes))
else:
self.model.output = nn.Linear(in_features,
config.model.num_classes)
def load_net_opt(load_pth='models/latest.pth', base_lr=1e-1):
net = get_model('resnet50', pretrained=True)
net.features.final_pool = nn.AdaptiveAvgPool2d(1)
net.output = nn.Linear(2048, 228)
if os.path.isfile(load_pth):
state_dict = torch.load(load_pth)
net.load_state_dict(state_dict)
head_params = list(map(id, net.output.parameters()))
base_params = filter(lambda p: id(p) not in head_params, net.parameters())
opt = optim.SGD([
{'params': base_params, 'lr': base_lr / 10},
{'params': net.output.parameters(), 'lr': base_lr}
], lr=base_lr, momentum=0.9)
return net, opt
def build_model(args, device):
weight_path = args.weight_path
if args.model == 'resnet50':
model = BaseCNN('resnet50', pretrained='imagenet', dropout_ratio=args.dropout, GeM_pool=True)
freeze_until(model, "base_model.layer3.0.conv1.weight")
print("fine-tuning")
elif args.model == 'resnext':
model = MyResNeXt(checkpoint=weight_path)
freeze_until(model, "layer4.0.conv1.weight")
print("fine-tuning")
elif args.model == 'xception':
model = get_model("xception", pretrained=True)
model = nn.Sequential(*list(model.children())[:-1])
model[0].final_block.pool = nn.Sequential(nn.AdaptiveAvgPool2d((1,1)))
model = FCN(model, 2048)
else:
NotImplementedError
model.to(device)
return model
def __init__(self,
model_name,
num_classes,
loss='softmax',
IN_first=False,
pooling_type='avg',
**kwargs):
super().__init__(**kwargs)
assert self.is_classification(), f"{model_name} model is adapted for classification tasks only"
self.pooling_type = pooling_type
self.loss = loss
assert isinstance(num_classes, int)
model = get_model(model_name, num_classes=1000, pretrained=self.pretrained)
assert hasattr(model, 'features') and isinstance(model.features, nn.Sequential)
self.features = model.features
self.features = self.features[:-1] # remove pooling, since it can have a fixed size
if self.loss not in ['am_softmax']:
self.output_conv = nn.Conv2d(in_channels=model.output.in_channels, out_channels=num_classes, kernel_size=1, stride=1, bias=False)
else:
self.output_conv = AngleSimpleLinear(model.output.in_channels, num_classes)
self.num_features = self.num_head_features = model.output.in_channels
self.input_IN = nn.InstanceNorm2d(3, affine=True) if IN_first else None
def create_model(config: Any, pretrained: bool) -> Any:
dropout = config.model.dropout
# support the deprecated model
if config.version == '2b_se_resnext50':
model = se_resnext50_32x4d(
pretrained='imagenet' if pretrained else None)
model.avg_pool = nn.AdaptiveAvgPool2d(1)
model.last_linear = nn.Linear(model.last_linear.in_features,
config.model.num_classes)
model = torch.nn.DataParallel(model)
return model
if not IN_KERNEL:
model = get_model(config.model.arch, pretrained=pretrained)
else:
model = get_model(config.model.arch,
pretrained=pretrained,
root='../input/pytorchcv-models/')
if config.model.arch == 'xception':
model.features[-1].pool = nn.AdaptiveAvgPool2d(1)
else:
model.features[-1] = nn.AdaptiveAvgPool2d(1)
if config.model.arch == 'pnasnet5large':
if dropout == 0.0:
model.output = nn.Linear(model.output[-1].in_features,
config.model.num_classes)
else:
model.output = nn.Sequential(
nn.Dropout(dropout),
nn.Linear(model.output[-1].in_features,
config.model.num_classes))
elif config.model.arch == 'xception':
if dropout < 0.1:
model.output = nn.Linear(2048, config.model.num_classes)
else:
model.output = nn.Sequential(
nn.Dropout(dropout), nn.Linear(2048, config.model.num_classes))
elif config.model.arch.startswith('inception'):
if dropout < 0.1:
model.output = nn.Linear(model.output[-1].in_features,
config.model.num_classes)
else:
model.output = nn.Sequential(
nn.Dropout(dropout),
nn.Linear(model.output[-1].in_features,
config.model.num_classes))
else:
if dropout < 0.1:
model.output = nn.Linear(model.output.in_features,
config.model.num_classes)
else:
model.output = nn.Sequential(
nn.Dropout(dropout),
nn.Linear(model.output.in_features, config.model.num_classes))
model = torch.nn.DataParallel(model)
return model
from sklearn.model_selection import train_test_split
import sklearn.metrics
import torch
import torch.nn as nn
import torch.nn.functional as F
import warnings
warnings.filterwarnings("ignore")
from torch.utils.data import Dataset, DataLoader
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
from pytorchcv.model_provider import get_model
model = get_model("xception", pretrained=True)
#model = get_model("resnet18", pretrained=True)
#model = get_model("resnet50", pretrained=True)
model = nn.Sequential(*list(
model.children())[:-1]) # Remove original output layer
model[0].final_block.pool = nn.Sequential(nn.AdaptiveAvgPool2d(1))
class Head(torch.nn.Module):
def __init__(self, in_f, out_f):
super().__init__()
self.f = nn.Flatten()
self.b1 = nn.BatchNorm1d(in_f) #in_f=2048
return self.df.shape[0]
if __name__ == '__main__':
torch.multiprocessing.set_sharing_strategy('file_system')
cudnn.benchmark = True
test_df = pd.read_csv('../data/test.csv', dtype=str)
print('test_df', test_df.shape)
test_dataset = ImageDataset(test_df, mode='test')
test_loader = DataLoader(test_dataset,
batch_size=BATCH_SIZE,
shuffle=False,
num_workers=NUM_WORKERS)
model = get_model('seresnext50_32x4d').cuda()
model.eval()
results = []
softmax = nn.Softmax()
with torch.no_grad():
for i, input_ in enumerate(tqdm(test_loader, disable=IN_KERNEL)):
output = model(input_.cuda())
output = softmax(output, dim=1)
results.append(output.cpu().numpy())
with open('imagenet_classes.pkl', 'wb') as f:
pickle.dump(results, f)
def classifier(files):
# Open log file and begin to append
f = open("deepfakeLog.log", "a+")
# Sort videos
test_videos = sorted([x for x in files if x[-4:] == ".mp4"])
# Check for whether GPU is available.
gpu = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# Set up face detection
facedet = blazeface.BlazeFace().to(gpu)
facedet.load_weights(current_path +
"\\lib\\blazeface-pytorch\\blazeface.pth")
facedet.load_anchors(current_path +
"\\lib\\blazeface-pytorch\\anchors.npy")
_ = facedet.train(False)
from helpers.read_video_1 import VideoReader
from helpers.face_extract_1 import FaceExtractor
# Determine how many frames are analyzed per video
frames_per_video = 20
# Read in frames
video_reader = VideoReader()
video_read_fn = lambda x: video_reader.read_frames(
x, num_frames=frames_per_video)
face_extractor = FaceExtractor(video_read_fn, facedet)
# Size of images
input_size = 150
from torchvision.transforms import Normalize
# Mean/std deviation values from original code
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
normalize_transform = Normalize(mean, std)
# Resize image
def isotropically_resize_image(img, size, resample=cv2.INTER_AREA):
h, w = img.shape[:2]
if w > h:
h = h * size // w
w = size
else:
w = w * size // h
h = size
resized = cv2.resize(img, (w, h), interpolation=resample)
return resized
# Turn image into correct size
def make_square_image(img):
h, w = img.shape[:2]
size = max(h, w)
t = 0
b = size - h
l = 0
r = size - w
return cv2.copyMakeBorder(img,
t,
b,
l,
r,
cv2.BORDER_CONSTANT,
value=0)
# Setup to grab model
from pytorchcv.model_provider import get_model
model = get_model("xception", pretrained=False)
model = nn.Sequential(*list(
model.children())[:-1]) # Remove original output layer
model[0].final_block.pool = nn.Sequential(nn.AdaptiveAvgPool2d(1))
# Define model
class Head(torch.nn.Module):
def __init__(self, in_f, out_f):
super(Head, self).__init__()
self.f = nn.Flatten()
self.l = nn.Linear(in_f, 512)
self.d = nn.Dropout(0.5)
self.o = nn.Linear(512, out_f)
self.b1 = nn.BatchNorm1d(in_f)
self.b2 = nn.BatchNorm1d(512)
self.r = nn.ReLU()
def forward(self, x):
x = self.f(x)
x = self.b1(x)
x = self.d(x)
x = self.l(x)
x = self.r(x)
x = self.b2(x)
x = self.d(x)
out = self.o(x)
return out
# Define fully conv network
class FCN(torch.nn.Module):
def __init__(self, base, in_f):
super(FCN, self).__init__()
self.base = base
self.h1 = Head(in_f, 1)
def forward(self, x):
x = self.base(x)
return self.h1(x)
net = []
model = FCN(model, 2048)
if (gpu == "gpu"):
model = model.cuda()
# Load trained model
model.load_state_dict(
torch.load(current_path + '\\lib\\model.pth',
map_location=torch.device(gpu)))
net.append(model)
# Prediction
def predict_on_video(video_path, batch_size):
try:
facesList = []
# Find the faces for N frames in the video.
faces = face_extractor.process_video(video_path)
# Only look at one face per frame.
face_extractor.keep_only_best_face(faces)
#facesList = faces
if len(faces) > 0:
# NOTE: When running on the CPU, the batch size must be fixed
# or else memory usage will blow up. (Bug in PyTorch?)
x = np.zeros((batch_size, input_size, input_size, 3),
dtype=np.uint8)
# If we found any faces, prepare them for the model.
n = 0
frameNum = []
for frame_data in faces:
frameNum.append(frame_data["frame_idx"])
for face in frame_data["faces"]:
# Resize to the model's required input size.
# We keep the aspect ratio intact and add zero
# padding if necessary.
facesList.append(face)
resized_face = isotropically_resize_image(
face, input_size)
resized_face = make_square_image(resized_face)
if n < batch_size:
x[n] = resized_face
n += 1
else:
print(
"WARNING: have %d faces but batch size is %d" %
(n, batch_size))
# Test time augmentation: horizontal flips.
# TODO: not sure yet if this helps or not
#x[n] = cv2.flip(resized_face, 1)
#n += 1
if n > 0:
x = torch.tensor(x, device=gpu).float()
# Preprocess the images.
x = x.permute((0, 3, 1, 2))
for i in range(len(x)):
x[i] = normalize_transform(x[i] / 255.)
# x[i] = x[i] / 255.
# Make a prediction, then take the average.
with torch.no_grad():
y_pred = model(x)
y_pred = torch.sigmoid(y_pred.squeeze())
# Store highest three predictions in list
highestThree = sorted(range(len(y_pred)),
key=lambda i: y_pred[i])[-3:]
#lowestThree = sorted(range(len(y_pred)), key=lambda i: y_pred[i])[:3]
highestFrameNums = []
# Save frame numbers of highest 3 predictions
for index in highestThree:
highestFrameNums.append(frameNum[index])
# Log to file that prediction was created
time = datetime.now()
f.write(
time.strftime("%d/%m/%Y %H:%M:%S") +
" -- Entered {0} into CNN algorithm\n".format(
video_path))
f.write("\tPrediction: " +
str(y_pred[:n].mean().item()) + "\n\n")
# Use the list of frame numbers to save suspicious images
save_sus_frames(highestFrameNums, video_path)
# Return single prediction mean from prediction on each frame
return y_pred[:n].mean().item()
# Error handling
except Exception as e:
exc_type, exc_obj, tb = sys.exc_info()
lineno = tb.tb_lineno
time = datetime.now()
log.write("\n%s -- Prediction error on video %s: %s\n" %
(time.strftime("%d/%m/%Y %H:%M:%S"), video_path, str(e)))
print("Prediction error on video %s: %s %s" %
(video_path, lineno, str(e)))
# Return 0.5 if error (0.5 == Not Sure)
return 0.5
# Grabs the three most suspicious frames based on the y predictions and saves them
def save_sus_frames(highestFrameNums, video_path):
# Create a video capture instance
vid = cv2.VideoCapture(video_path)
video_name = os.path.basename(video_path)
video_name = os.path.splitext(video_name)[0]
# Sort highest frame num list
highestFrameNums = sorted(highestFrameNums)
total_frames = vid.get(7)
cd = os.getcwd()
# Make directory for video
if not os.path.isdir(video_name):
os.mkdir('{0}'.format(video_name))
# Set video to correct frame and save image frame
for value in highestFrameNums:
vid.set(1, value)
ret, frame = vid.read()
print('{0}/{1}/{1}_frame_{2}.jpg'.format(cd, video_name, value))
cv2.imwrite(
'{0}/{1}/{1}_frame_{2}.jpg'.format(cd, video_name, value),
frame)
from concurrent.futures import ThreadPoolExecutor
# Predict on multiple videos
def predict_on_video_set(videos, num_workers):
def process_file(i):
filename = videos[i]
y_pred = predict_on_video(filename, batch_size=frames_per_video)
return y_pred
with ThreadPoolExecutor(max_workers=num_workers) as ex:
predictions = ex.map(process_file, range(len(videos)))
return list(predictions)
# If True, will return a prediction of classification length
# Ultimately was not able to use this in GUI due to threading difficulty
speed_test = False
if speed_test:
start_time = time.time()
speedtest_videos = test_videos[:5]
predictions = predict_on_video_set(speedtest_videos, num_workers=4)
elapsed = time.time() - start_time
print("Elapsed %f sec. Average per video: %f sec." %
(elapsed, elapsed / len(speedtest_videos)))
model.eval()
predictions = predict_on_video_set(test_videos, num_workers=4)
f.close()
return predictions
def main():
global args, best_prec1
args = parser.parse_args()
if args.seed is not None:
random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.deterministic = True
warnings.warn('You have chosen to seed training. '
'This will turn on the CUDNN deterministic setting, '
'which can slow down your training considerably! '
'You may see unexpected behavior when restarting '
'from checkpoints.')
args.distributed = args.world_size > 1
if args.distributed:
dist.init_process_group(backend=args.dist_backend,
init_method=args.dist_url,
world_size=args.world_size)
# create model
print("=> creating model '{}'".format(args.arch))
model = get_model(args.arch,
in_size=(args.input_size, args.input_size),
num_classes=1000)
if not args.distributed:
model = torch.nn.DataParallel(model).cuda()
else:
model.cuda()
model = torch.nn.parallel.DistributedDataParallel(model)
# define loss function (criterion) and optimizer
criterion = nn.CrossEntropyLoss().cuda()
optimizer = torch.optim.SGD(model.parameters(),
args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
# optionally resume from a checkpoint
title = 'ImageNet-' + args.arch
if not os.path.isdir(args.checkpoint):
mkdir_p(args.checkpoint)
if args.resume:
if os.path.isfile(args.resume):
print("=> loading checkpoint '{}'".format(args.resume))
checkpoint = torch.load(args.resume)
args.start_epoch = checkpoint['epoch']
best_prec1 = checkpoint['best_prec1']
model.load_state_dict(checkpoint['state_dict'])
optimizer.load_state_dict(checkpoint['optimizer'])
print("=> loaded checkpoint '{}' (epoch {})".format(
args.resume, checkpoint['epoch']))
args.checkpoint = os.path.dirname(args.resume)
logger = Logger(os.path.join(args.checkpoint, 'log.txt'),
title=title,
resume=True)
else:
print("=> no checkpoint found at '{}'".format(args.resume))
else:
logger = Logger(os.path.join(args.checkpoint, 'log.txt'), title=title)
logger.set_names([
'Learning Rate', 'Train Loss', 'Valid Loss', 'Train Acc.',
'Valid Acc.'
])
cudnn.benchmark = True
get_train_loader = get_pytorch_train_loader
get_val_loader = get_pytorch_val_loader
train_loader, train_loader_len = get_train_loader(
args.data,
args.batch_size,
workers=args.workers,
input_size=args.input_size)
val_loader, val_loader_len = get_val_loader(args.data,
args.batch_size,
workers=args.workers,
input_size=args.input_size)
if args.evaluate:
from collections import OrderedDict
if os.path.isfile(args.weight):
print("=> loading pretrained weight '{}'".format(args.weight))
source_state = torch.load(args.weight)
if 'state_dict' in source_state:
source_state = source_state['state_dict']
if 'model' in source_state:
source_state = source_state['model']
target_state = OrderedDict()
for k, v in source_state.items():
#if k.startswith('module.attacker.model.'):
# k = k[len('module.attacker.model.'):]
#else:
# continue
if k[:7] != 'module.':
k = 'module.' + k
target_state[k] = v
model.load_state_dict(target_state, strict=True)
else:
print("=> no weight found at '{}'".format(args.weight))
validate(val_loader,
val_loader_len,
model,
criterion,
adv_eps=args.adv_eps,
euclidean_adv=args.euclidean)
return
# visualization
writer = SummaryWriter(os.path.join(args.checkpoint, 'logs'))
for epoch in range(args.start_epoch, args.epochs):
if args.distributed:
train_sampler.set_epoch(epoch)
print(f'\nEpoch: [{epoch + 1} | {args.epochs}]')
# train for one epoch
train_loss, train_acc = train(train_loader, train_loader_len, model,
criterion, optimizer, epoch)
# evaluate on validation set
val_loss, prec1, prec5, adv_prec1, adv_prec5 = validate(
val_loader,
val_loader_len,
model,
criterion,
adv_eps=args.adv_eps,
euclidean_adv=args.euclidean)
lr = optimizer.param_groups[0]['lr']
# append logger file
logger.append([lr, train_loss, val_loss, train_acc, prec1])
# tensorboardX
writer.add_scalar('learning rate', lr, epoch + 1)
writer.add_scalars('loss', {
'train loss': train_loss,
'validation loss': val_loss
}, epoch + 1)
writer.add_scalars('accuracy', {
'train accuracy': train_acc,
'validation accuracy': prec1
}, epoch + 1)
print(
f'Val results: {prec1:.2f} ; {prec5:.2f} ; {adv_prec1:.2f} ; {adv_prec5:.2f}'
)
is_best = prec1 > best_prec1
best_prec1 = max(prec1, best_prec1)
save_checkpoint(
{
'epoch': epoch + 1,
'arch': args.arch,
'state_dict': model.state_dict(),
'best_prec1': best_prec1,
'optimizer': optimizer.state_dict(),
},
is_best,
checkpoint=args.checkpoint)
logger.close()
logger.plot()
savefig(os.path.join(args.checkpoint, 'log.eps'))
writer.close()
print('Best accuracy:')
print(best_prec1)
steps = 0
running_loss = 0
print_every = 5000
checkpoint = "./resnet50_pytorch/"
if not os.path.exists(checkpoint):
os.makedirs(checkpoint)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# model = models.resnext50_32x4d(pretrained=True)
# model.fc = nn.Sequential(nn.Linear(2048, 1),
# nn.Sigmoid())
# model = model.cuda()
from pytorchcv.model_provider import get_model
model = get_model("xception", pretrained=False)
model = nn.Sequential(*list(
model.children())[:-1]) # Remove original output layer
class Pooling(nn.Module):
def __init__(self):
super(Pooling, self).__init__()
self.p1 = nn.AdaptiveAvgPool2d((1, 1))
self.p2 = nn.AdaptiveMaxPool2d((1, 1))
def forward(self, x):
x1 = self.p1(x)
x2 = self.p2(x)
return (x1 + x2) * 0.5
def prepare_model(model_name,
use_pretrained,
pretrained_model_file_path,
use_cuda,
use_data_parallel=True,
net_extra_kwargs=None,
load_ignore_extra=False,
num_classes=None,
in_channels=None,
remap_to_cpu=False,
remove_module=False):
"""
Create and initialize model by name.
Parameters
----------
model_name : str
Model name.
use_pretrained : bool
Whether to use pretrained weights.
pretrained_model_file_path : str
Path to file with pretrained weights.
use_cuda : bool
Whether to use CUDA.
use_data_parallel : bool, default True
Whether to use parallelization.
net_extra_kwargs : dict, default None
Extra parameters for model.
load_ignore_extra : bool, default False
Whether to ignore extra layers in pretrained model.
num_classes : int, default None
Number of classes.
in_channels : int, default None
Number of input channels.
remap_to_cpu : bool, default False
Whether to remape model to CPU during loading.
remove_module : bool, default False
Whether to remove module from loaded model.
Returns
-------
Module
Model.
"""
kwargs = {"pretrained": use_pretrained}
if num_classes is not None:
kwargs["num_classes"] = num_classes
if in_channels is not None:
kwargs["in_channels"] = in_channels
if net_extra_kwargs is not None:
kwargs.update(net_extra_kwargs)
net = get_model(model_name, **kwargs)
if pretrained_model_file_path:
assert (os.path.isfile(pretrained_model_file_path))
logging.info("Loading model: {}".format(pretrained_model_file_path))
checkpoint = torch.load(
pretrained_model_file_path,
map_location=(None if use_cuda and not remap_to_cpu else "cpu"))
if (type(checkpoint) == dict) and ("state_dict" in checkpoint):
checkpoint = checkpoint["state_dict"]
if load_ignore_extra:
pretrained_state = checkpoint
model_dict = net.state_dict()
pretrained_state = {
k: v
for k, v in pretrained_state.items() if k in model_dict
}
net.load_state_dict(pretrained_state)
else:
if remove_module:
net_tmp = torch.nn.DataParallel(net)
net_tmp.load_state_dict(checkpoint)
net.load_state_dict(net_tmp.module.cpu().state_dict())
else:
net.load_state_dict(checkpoint)
if use_data_parallel and use_cuda:
net = torch.nn.DataParallel(net)
if use_cuda:
net = net.cuda()
return net
