train_loss = framework.train(network,
train_loader,
loss_fn,
optim,
epoch,
writer=writer,
early_stop=args.early_stop)
prec_rec = PrecRec(n_thresholds=100)
framework.test(
network,
val_loader,
loss_fn,
[prec_rec],
epoch,
writer=writer,
early_stop=args.early_stop,
)
results = prec_rec.get_dict()
for key in results:
writer.add_scalar(f'Test/{key}', results[key], epoch)
scheduler.step(train_loss)
framework.save_checkpoint(epoch,
0.,
network,
optim,
path=args.artifacts)
for epoch in range(start_epoch, args.epochs):
train_loss = framework.train(network,
train_loader,
loss_fn,
optim,
epoch,
early_stop=args.early_stop,
logger=logger)
score = framework.test(network,
val_loader,
criteria,
early_stop=args.early_stop,
logger=logger)
scheduler.step(train_loss)
framework.save_checkpoint(epoch,
score,
network,
optim,
path=args.artifacts)
if score > best_score:
best_score = score
fname = 'model_best_{:.2f}.pth.tar'.format(best_score)
framework.save_checkpoint(epoch,
best_score,
network,
optim,
path=args.artifacts,
fname=fname)