def remove_background(img):
device = torch.device(
'cuda') if torch.cuda.is_available() else torch.device('cpu')
segmentation_model_path = './models/people_segmentation.pth'
num_classes = 2
model = get_instance_segmentation_model(num_classes)
model.load_state_dict(torch.load(segmentation_model_path))
model.to(device)
trans = transforms.ToTensor()
img = trans(img)
model.eval()
with torch.no_grad():
prediction = model([img.to(device)])
img = img.mul(255).permute(1, 2, 0).byte().numpy()
pred_mask = prediction[0]['masks'][0, 0].mul(255).byte().cpu().numpy()
if prediction[0]['scores'][0] < 0.8:
return img
pred = np.squeeze(pred_mask)
background = pred > 0.6 * 255
background = np.expand_dims(background, 2)
removed = background * img
b, g, r = cv2.split(removed)
rimg = cv2.merge([r, g, b])
return removed
rle = rle_encode(m)
lines.append((rle, labels[o]))
return lines
num_classes = 46 + 1
dataset_test = FashionDataset("../input/test/", "../input/sample_submission.csv", 1024, 1024,
folds=[], transforms=None)
sample_df = pd.read_csv("../input/sample_submission.csv")
model_ft = get_instance_segmentation_model(num_classes)
model_ft.load_state_dict(torch.load("model.bin"))
model_ft = model_ft.to(device)
for param in model_ft.parameters():
param.requires_grad = False
model_ft.eval()
sub_list = []
missing_count = 0
submission = []
ctr = 0
tk0 = tqdm(range(3200))
# define training and validation data loaders
data_loader = torch.utils.data.DataLoader(
dataset, batch_size=4, shuffle=True, num_workers=0,
collate_fn=utils.collate_fn)
data_loader_test = torch.utils.data.DataLoader(
dataset_test, batch_size=1, shuffle=True, num_workers=0,
collate_fn=utils.collate_fn)
# the dataset has two classes only - background and person
num_classes = 2
# get the model using the helper function
#bone: 'resnet50'/'mobilenet_v2'/'googlenet'/'densenet121'/'resnet50'/'shufflenet_v2_x1_0'/'inception_v3'/'squeezenet1_0'/
#attention：True/False
model = get_instance_segmentation_model(bone='resnet50',attention=True)
model.cuda()
model = nn.DataParallel(model)
# move model to the right device
#model.load_state_dict(torch.load('/disk2/yzy_cell/cell_model_densenet'))
model.to(device)
# construct an optimizer
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params, lr=0.0005,
momentum=0.9, weight_decay=0.0005)
# the learning rate scheduler decreases the learning rate by 10x every 3 epochs
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=20,
counts = {}
for i in range(sequence.shape[0]):
for x in sequence[i]:
if x in counts:
counts[x] += 1
else:
counts[x] = 1
return counts
# the dataset has two classes only - background and person
num_classes = 2
# get the model using the helper function
#bone: 'resnet50'/'mobilenet_v2'/'googlenet'/'densenet121'/'resnet50'/'shufflenet_v2_x1_0'/'inception_v3'/'squeezenet1_0'/
model = get_instance_segmentation_model(bone='densenet121', attention=False)
model.cuda()
model = nn.DataParallel(model)
# move model to the right device
model.to(device)
def test(img, m):
with torch.no_grad():
prediction = model([img.to(device)])
Image.fromarray(img.mul(255).permute(
1, 2, 0).byte().numpy()).save('./eval/image/' + str(m) + '.png')
mask = prediction[0]['masks'].mul(255).byte().cpu().numpy()
collate_fn=utils.collate_fn)
data_loader_test = torch.utils.data.DataLoader(dataset_test,
batch_size=2,
shuffle=False,
num_workers=2,
collate_fn=utils.collate_fn)
device = torch.device(
f'cuda:{args.GPU}') if torch.cuda.is_available() else torch.device('cpu')
# our dataset has two classes only - background and person
num_classes = 21
# get the model using our helper function
model = get_instance_segmentation_model(num_classes, args.backbone,
args.dropout)
# move model to the right device
model.to(device)
# construct an optimizer
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params,
lr=0.005,
momentum=0.9,
weight_decay=0.0005)
# and a learning rate scheduler which decreases the learning rate by
# 10x every 3 epochs
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=3,
gamma=0.1)
def main():
print("Torch version:", torch.__version__)
# get command-line arguments
parser = argparse.ArgumentParser()
parser.add_argument('--model_name',
type=str,
default="pytorch-peds.pt",
help='name with which to register your model')
parser.add_argument('--output_dir',
default="local-outputs",
type=str,
help='output directory')
parser.add_argument('--n_epochs',
type=int,
default=10,
help='number of epochs')
args = parser.parse_args()
# In case user inputs a nested output directory
os.makedirs(name=args.output_dir, exist_ok=True)
# Get a dataset by name
root_dir = download_data()
# use our dataset and defined transformations
dataset = PennFudanDataset(root=root_dir,
transforms=get_transform(train=True))
dataset_test = PennFudanDataset(root=root_dir,
transforms=get_transform(train=False))
# split the dataset in train and test set
torch.manual_seed(1)
indices = torch.randperm(len(dataset)).tolist()
dataset = torch.utils.data.Subset(dataset, indices[:-50])
dataset_test = torch.utils.data.Subset(dataset_test, indices[-50:])
# define training and validation data loaders
data_loader = torch.utils.data.DataLoader(dataset,
batch_size=2,
shuffle=True,
num_workers=4,
collate_fn=utils.collate_fn)
data_loader_test = torch.utils.data.DataLoader(dataset_test,
batch_size=1,
shuffle=False,
num_workers=4,
collate_fn=utils.collate_fn)
if torch.cuda.is_available():
print('Using GPU')
device = torch.device('cuda')
else:
print('Using CPU')
device = torch.device('cpu')
# our dataset has two classes only - background and person
num_classes = NUM_CLASSES
# get the model using our helper function
model = get_instance_segmentation_model(num_classes)
# move model to the right device
model.to(device)
# construct an optimizer
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params,
lr=0.005,
momentum=0.9,
weight_decay=0.0005)
# and a learning rate scheduler which decreases the learning rate by
# 10x every 3 epochs
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=3,
gamma=0.1)
for epoch in range(args.n_epochs):
# train for one epoch, printing every 10 iterations
train_one_epoch(model,
optimizer,
data_loader,
device,
epoch,
print_freq=10)
# update the learning rate
lr_scheduler.step()
# evaluate on the test dataset
evaluate(model, data_loader_test, device=device)
# Saving the state dict is recommended method, per
# https://pytorch.org/tutorials/beginner/saving_loading_models.html
torch.save(model.state_dict(),
os.path.join(args.output_dir, args.model_name))