'sinkhorn_iterations': opt.sinkhorn_iterations,
'match_threshold': opt.match_threshold,
}
}
# load training data
train_set = SparseDataset(opt.train_path, opt.max_keypoints)
train_loader = torch.utils.data.DataLoader(dataset=train_set,
shuffle=False,
batch_size=opt.batch_size,
drop_last=True)
superglue = SuperGlue(config.get('superglue', {}))
if torch.cuda.is_available():
superglue.cuda() # make sure it trains on GPU
else:
print("### CUDA not available ###")
optimizer = torch.optim.Adam(superglue.parameters(), lr=opt.learning_rate)
mean_loss = []
# start training
for epoch in range(1, opt.epoch + 1):
epoch_loss = 0
superglue.double().train()
for i, pred in enumerate(train_loader):
for k in pred:
if k != 'file_name' and k != 'image0' and k != 'image1':
if type(pred[k]) == torch.Tensor:
pred[k] = Variable(pred[k].cuda())
else:
},
'superglue': {
'weights': opt.superglue,
'sinkhorn_iterations': opt.sinkhorn_iterations,
'match_threshold': opt.match_threshold,
}
}
train_set = SparseDataset(opt.train_path, opt.max_keypoints)
train_loader = torch.utils.data.DataLoader(dataset=train_set, shuffle=False, batch_size=opt.batch_size, drop_last=True)
# superpoint = SuperPoint(config.get('superpoint', {}))
superglue = SuperGlue(config.get('superglue', {}))
if torch.cuda.is_available():
# superpoint.cuda()
superglue.cuda()
else:
print("### CUDA not available ###")
optimizer = torch.optim.Adam(superglue.parameters(), lr=opt.learning_rate)
mean_loss = []
for epoch in range(1, opt.epoch+1):
epoch_loss = 0
superglue.double().train()
train_loader = tqdm(train_loader)
for i, pred in enumerate(train_loader):
for k in pred:
if k != 'file_name' and k!='image0' and k!='image1':
if type(pred[k]) == torch.Tensor:
pred[k] = Variable(pred[k].cuda())
else: