Saravanan Rajamanickam

Results 2 comments of Saravanan Rajamanickam

Hi, Even I have faced the same error when I try to run the model with same config. cuDNN version: /usr/local/cuda-10.0/lib64/libcudnn.so.7.6.0 Versions of relevant libraries: [pip3] pytorch-pretrained-bert==0.6.2 [pip3] torch==0.4.1.post2 [conda]...

I have tried this one and it worked : model.compile(optimizer=Adam(lr=self.learning_rate), loss=self.loss, metrics=['accuracy'])