runlongyu / cels Goto Github PK

(clip) charles@mac main % python train.py --dataset='criteo' --strategy='1+1'
Traceback (most recent call last):
File "/Users/charles/Desktop/CELS_github/main/train.py", line 22, in
train(params=args)
File "/Users/charles/Desktop/CELS_github/run/run_criteo_cels.py", line 53, in train
evolution_search(feature_columns=fixlen_feature_columns, feature_index=feature_index,
File "/Users/charles/Desktop/CELS_github/trainer/cels_s1_trainer.py", line 44, in evolution_search
cels_model.fit_1_plus_1(train_model_input, data_train[label_name].values,
File "/Users/charles/Desktop/CELS_github/model/CELS_Model.py", line 249, in fit_1_plus_1
torch.from_numpy(y))
TypeError: can't convert np.ndarray of type numpy.object_. The only supported types are: float64, float32, float16, complex64, complex128, int64, int32, int16, int8, uint8, and bool.

criteo
├── bucket
├── feature_map
└── processed

avazu
└── processed

fintech
├── bucket
├── feature_map
└── processed

CELS_github\model\CELS_Model.py", line 372, in fit_n_1
torch.from_numpy(y))
TypeError: can't convert np.ndarray of type numpy.object_. The only supported types are: float64, float32, float16, complex64, complex128, int64, int32, int16, int8, uint8, and bool.