Does anyone know how to get the polygon masks from the inference results so I can then send some simple json across the wire to callers? I’m very unfamiliar with the Tensor output for the masks of the image during the segmentation inference.
model = torch.load(model_file)
model.to(device)
n_threads = torch.get_num_threads()
torch.set_num_threads(1)
model.eval()
def load_dataset():
train_dataset = torchvision.datasets.ImageFolder(
root="images",
transform=torchvision.transforms.ToTensor()
)
train_loader = torch.utils.data.DataLoader(
train_dataset,
batch_size=1,
num_workers=1,
shuffle=True
)
return train_loader
for batch_idx, (data, target) in enumerate(load_dataset()):
data = data.cuda()
output = model(data)
boxes = output[0]["boxes"]
labels = output[0]["labels"]
scores = output[0]["scores"]
masks = output[0]["masks"]
# how can I find the polygons for the masks in the tensors
print(masks)
torch.cuda.empty_cache()