def main():
args = tools.get_args(parser)
config = tools.get_config(args)
tools.init(config)
tb_logger, logger = tools.get_logger(config)
tools.check_dist_init(config, logger)
checkpoint = tools.get_checkpoint(config)
runner = tools.get_model(config, checkpoint)
loaders = tools.get_data_loader(config)
if dist.is_master():
logger.info(config)
if args.mode == 'train':
train(config, runner, loaders, checkpoint, tb_logger)
elif args.mode == 'evaluate':
evaluate(runner, loaders)
elif args.mode == 'calc_flops':
if dist.is_master():
flops = tools.get_model_flops(config, runner.get_model())
logger.info('flops: {}'.format(flops))
elif args.mode == 'calc_params':
if dist.is_master():
params = tools.get_model_parameters(runner.get_model())
logger.info('params: {}'.format(params))
else:
assert checkpoint is not None
from models.dmcp.utils import sample_model
sample_model(config, runner.get_model())
if dist.is_master():
logger.info('Done')
def main():
check_folder()
args = get_args()
# Can work with any model, but it assumes that the model has a
# feature method, and a classifier method,
# model = models.resnet50(pretrained=True)
model = models.resnet50(pretrained=True).to(device)
model.fc = nn.Sequential(
nn.Linear(2048, 2),
).to(device)
model.load_state_dict(torch.load(
'./models/resnet50-epoch6-Acc9715.h5'))
grad_cam = GradCam(
model=model,
feature_module=model.layer4,
target_layer_names=['2'],
use_cuda=args.use_cuda
)
img = cv2.imread(args.image_path, 1)
img = np.float32(cv2.resize(img, (224, 224))) / 255
input = preprocess_image(img)
# If None, returns the map for the highest scoring category.
# Otherwise, targets the requested index.
target_index = None
mask = grad_cam(input, target_index)
out_path_cam = './out/{}_cam.jpg'.format(args.out_prefix)
show_cam_on_image(img, mask, out_path_cam)
gb_model = GuidedBackpropReLUModel(model=model, use_cuda=args.use_cuda)
# print(model._modules.items())
gb = gb_model(input, index=target_index)
gb = gb.transpose((1, 2, 0))
cam_mask = cv2.merge([mask, mask, mask])
cam_gb = deprocess_image(cam_mask*gb)
gb = deprocess_image(gb)
cv2.imwrite('./out/{}_gb.jpg'.format(args.out_prefix), gb)
cv2.imwrite('./out/{}_cam_gb.jpg'.format(args.out_prefix), cam_gb)
os.system('cp {} ./out/{}_orig.jpg'.format(args.image_path, args.out_prefix))
return triplet_datasets
def main(args):
triplet_save_path = p.join(args.path.train_data_dir, "triplet_dataset")
args.model.tokenizer_name = "xlm-roberta-large"
args.model.retriever_name = "BM25"
bm25 = BM25Retrieval(args)
bm25.get_embedding()
train_dataset = get_train_dataset(args)
triplet_datasets = make_triplet_dataset(bm25, train_dataset)
df = pd.DataFrame(triplet_datasets)
f = Features({
"question": Value(dtype="string", id=None),
"context": Value(dtype="string", id=None),
"negative": Value(dtype="string", id=None),
})
triplet_datasets = Dataset.from_pandas(df, features=f)
triplet_datasets.save_to_disk(triplet_save_path)
if __name__ == "__main__":
args = get_args()
main(args)