lab-emi / OpenDPD

OpenDPD is an end-to-end learning framework built in PyTorch for power amplifier (PA) modeling and digital pre-distortion (DPD). You are cordially invited to contribute to this project by providing your own backbone neural networks, pretrained models or measured PA datasets.
https://www.tudemi.com
Apache License 2.0
43 stars 13 forks source link

May I ask why I encountered an error when running main.py #2

Closed Pt2Mu closed 5 months ago

Pt2Mu commented 5 months ago

::: Are Deterministic Algorithms Enabled: False

####################################################################################################

Step: Train PA

#################################################################################################### ::: Available GPUs: 1 ::: Using GPU 0: NVIDIA GeForce RTX 2060

Backbone Initialized... ::: Number of PA Model Parameters: 486 ::: Best Model Save Path: ./save\DPA_100MHz\train_pa\PA_S_0_M_DGRU_H_8_F_50_P_486.pt ::: Log-History Path: ./log\DPA_100MHz\train_pa\history\PA_S_0_M_DGRU_H_8_F_50_P_486.csv ::: Log-Best Path: ./log\DPA_100MHz\train_pa\best\PA_S_0_M_DGRU_H_8_F_50_P_486.csv Starting training... 100%|██████████| 360/360 [00:01<00:00, 237.45it/s] 100%|██████████| 1/1 [00:00<?, ?it/s] Traceback (most recent call last): File "E:\文献\OpenDPD-main\main.py", line 16, in train_pa.main(proj) File "E:\文献\OpenDPD-main\steps\train_pa.py", line 50, in main proj.train(net=net, File "E:\文献\OpenDPD-main\project.py", line 289, in train self.log_val = calculate_metrics(self.args, self.log_val, prediction, ground_truth) File "E:\文献\OpenDPD-main\modules\train_funcs.py", line 95, in calculate_metrics stat['EVM'] = metrics.EVM(prediction, ground_truth, bw_main_ch=args.bw_main_ch, n_sub_ch=args.n_sub_ch, nperseg=args.nperseg) AttributeError: 'Namespace' object has no attribute 'bw_main_ch'

进程已结束,退出代码为 1