def main():
parser = argparse.ArgumentParser()
arg = parser.add_argument
arg('--batch-size', type=int, default=32)
arg('--lr', type=float, default=2e-3)
arg('--workers', type=int, default=4)
arg('--epochs', type=int, default=5)
arg('--mixup-alpha', type=float, default=0)
arg('--cutmix-alpha', type=float, default=0)
arg('--arch', type=str, default='seresnext50')
arg('--amp', type=str, default='')
arg('--size', type=int, default=192)
arg('--debug', action='store_true')
arg('--radam', action='store_true')
arg('--run-name', type=str, default='')
arg('--lookahead-k', type=int, default=-1)
arg('--lookahead-alpha', type=float, default=0.5)
arg('--from-checkpoint', type=str, default='')
arg('--find-lr', action='store_true')
args = parser.parse_args()
train_dir = DATA_ROOT / 'train'
valid_dir = DATA_ROOT / 'val'
use_cuda = cuda.is_available()
model = get_model(args.arch)
if use_cuda:
model = model.cuda()
criterion = MixUpSoftmaxLoss(nn.CrossEntropyLoss())
(CACHE_DIR / 'params.json').write_text(
json.dumps(vars(args), indent=4, sort_keys=True))
df_train, class_map = build_dataframe_from_folder(train_dir)
df_valid = build_dataframe_from_folder(valid_dir, class_map)
train_transform = get_train_transform(int(args.size * 1.25), args.size)
test_transform = get_test_transform(int(args.size * 1.25), args.size)
train_loader = make_loader(args,
TrainDataset,
df_train,
train_transform,
drop_last=True,
shuffle=True)
valid_loader = make_loader(args,
TrainDataset,
df_valid,
test_transform,
shuffle=False)
print(f'{len(train_loader.dataset):,} items in train, '
f'{len(valid_loader.dataset):,} in valid')
if args.find_lr:
find_lr(args, model, train_loader, criterion)
else:
if args.from_checkpoint:
resume_training(args, model, train_loader, valid_loader)
else:
train_from_scratch(args, model, train_loader, valid_loader,
criterion)
def main():
parser = argparse.ArgumentParser()
arg = parser.add_argument
arg('--batch-size', type=int, default=32)
arg('--lr', type=float, default=2e-3)
arg('--workers', type=int, default=4)
arg('--epochs', type=int, default=5)
arg('--mixup-alpha', type=float, default=0)
arg('--arch', type=str, default='seresnext50')
arg('--amp', type=str, default='')
arg('--debug', action='store_true')
args = parser.parse_args()
train_dir = DATA_ROOT / 'train'
valid_dir = DATA_ROOT / 'val'
use_cuda = cuda.is_available()
if args.arch == 'seresnext50':
model = get_seresnet_model(arch="se_resnext50_32x4d",
n_classes=N_CLASSES,
pretrained=False)
elif args.arch == 'seresnext101':
model = get_seresnet_model(arch="se_resnext101_32x4d",
n_classes=N_CLASSES,
pretrained=False)
elif args.arch.startswith("densenet"):
model = get_densenet_model(arch=args.arch)
else:
raise ValueError("No such model")
if use_cuda:
model = model.cuda()
criterion = MixUpSoftmaxLoss(nn.CrossEntropyLoss())
(CACHE_DIR / 'params.json').write_text(
json.dumps(vars(args), indent=4, sort_keys=True))
df_train, class_map = build_dataframe_from_folder(train_dir)
df_valid = build_dataframe_from_folder(valid_dir, class_map)
train_loader = make_loader(args,
TrainDataset,
df_train,
train_transform,
drop_last=True,
shuffle=True)
valid_loader = make_loader(args,
TrainDataset,
df_valid,
test_transform,
shuffle=False)
print(f'{len(train_loader.dataset):,} items in train, '
f'{len(valid_loader.dataset):,} in valid')
train_from_scratch(args, model, train_loader, valid_loader, criterion)
def main():
parser = argparse.ArgumentParser()
arg = parser.add_argument
arg('--batch-size', type=int, default=32)
arg('--workers', type=int, default=4)
arg('--arch', type=str, default='seresnext50')
arg('--amp', type=str, default='')
arg('--size', type=int, default=192)
arg('--debug', action='store_true')
arg('--model-path', type=str, default='')
args = parser.parse_args()
train_dir = DATA_ROOT / 'train'
valid_dir = DATA_ROOT / 'val'
use_cuda = cuda.is_available()
model = get_model(args.arch)
model.load_state_dict(torch.load(args.model_path, map_location="cpu"))
if use_cuda:
model = model.cuda()
if args.amp:
if not APEX_AVAILABLE:
raise ValueError("Apex is not installed!")
model = amp.initialize(model, opt_level=args.amp)
# The first line is to make sure we have the same class_map as in training
_, class_map = build_dataframe_from_folder(train_dir)
df_valid = build_dataframe_from_folder(valid_dir, class_map)
idx_to_name = get_class_idx_to_class_name_mapping(class_map)
# Export the mapping for later use
with open(CACHE_DIR / "id_to_name_map.json", "w") as fout:
json.dump(idx_to_name, fout)
test_transform = get_test_transform(int(args.size * 1.25), args.size)
valid_loader = make_loader(args,
TrainDataset,
df_valid,
test_transform,
shuffle=False)
print(f'{len(valid_loader.dataset):,} in valid')
bot = ImageClassificationBot(model=model,
train_loader=None,
valid_loader=None,
clip_grad=0,
optimizer=None,
echo=True,
criterion=None,
callbacks=[],
pbar=True,
use_tensorboard=False,
use_amp=(args.amp != ''))
logits, truths = bot.predict(valid_loader, return_y=True)
probs = torch.softmax(logits, dim=-1)
preds = torch.argmax(probs, dim=1)
print(
f"Validation accuracy: {np.mean(preds.numpy() == truths.numpy()) * 100:.2f}%"
)
df_out = pd.DataFrame({
"truth":
truths.numpy(),
"max_prob":
np.max(probs.numpy(), axis=1),
"truth_prob":
torch.gather(probs, 1, truths[:, None]).numpy()[:, 0],
"pred":
preds,
"path": [
valid_loader.dataset._df.iloc[i].image_path
for i in range(len(valid_loader.dataset))
]
})
df_out.to_csv(CACHE_DIR / "valid_preds.csv", index=False)