KDD2021_CNFGNN icon indicating copy to clipboard operation
KDD2021_CNFGNN copied to clipboard

Official PyTorch implementation of "Cross-Node Federated Graph Neural Network for Spatio-Temporal Modeling".

Results 3 KDD2021_CNFGNN issues
Sort by recently updated
recently updated
newest added

您好,我在跑实验结果的时候,使用您给的参数: # CNFGNN (64K + 1M) python main.py --dataset METR-LA --seed 42 --model_name SplitFedAvgNodePredictor --base_model_name GRUSeq2SeqWithGraphNet --batch_size 128 --server_batch_size 48 --hidden_size 64 --suffix mp --use_curriculum_learning --mp_worker_num 16 --sync_every_n_epoch 1 --server_epoch...

File "D:\KDD_CNFGNN\models\base_models\GraphNets.py", line 128, in forward u = x.new_zeros(*([batch[-1] + 1] + list(x.shape[1:-1]) + [self.global_input_size])) TypeError: 'NoneType' object is not subscriptable hi, mr.Meng. i run your code but i found...

"trainer.fit(model)" report an error "wandb.errors.UsageError: api_key not configured (no-tty). call wandb.login(key=[your_api_key])"