|
MSE-CNN Implementation 1
Code database with the implementation of MSE-CNN, from the paper 'DeepQTMT: A Deep Learning Approach for Fast QTMT-based CU Partition of Intra-mode VVC'
|
Namespaces | |
| namespace | eval_model_stg6 |
Functions | |
| eval_model_stg6.test (dataloader, model, device, loss_name) | |
| eval_model_stg6.val_setup (dataloader_val, model, device) | |
| eval_model_stg6.main () | |
Variables | |
| eval_model_stg6.parser = argparse.ArgumentParser(description=constants.script_description) | |
| eval_model_stg6.type | |
| eval_model_stg6.args = parser.parse_args() | |
| eval_model_stg6.loss_threshold = float("-inf") | |
| int | eval_model_stg6.qp = 32 |
| eval_model_stg6.batch_size = args.batch | |
| eval_model_stg6.device = args.dev | |
| eval_model_stg6.num_workers = args.workers | |
| eval_model_stg6.rs = args.thres | |
| eval_model_stg6.n_mod = args.nmod | |
| eval_model_stg6.l_path_val = args.labels | |
| str | eval_model_stg6.files_mod_name_stats = "_multi_batch_val_batch_{batch}_QP_{QP}".format(batch=batch_size, QP=qp) |
1.9.7