2021-10

LightGBMでInput numpy.ndarray must be 2 dimensional lightgbm

LightGBMでnp.arrayを入力して回帰モデルを作ろうとした時に表題のエラー。X_train, X_test, y_train, y_test = train_test_split(X, y)model = lgb.LGBMRegr...

TPUでConv1Dのdilation_rateを指定するとReshape’s input dynamic dimension is decomposed into multiple output dynamic dimensions

ColabのTPUでdilation convolutionを使った時に表題のエラー。tf.keras.layers.Conv1D(32, kernel_size=3, dilation_rate=2)Reshape's input...