pytorch-speech-commands
pytorch-speech-commands copied to clipboard
operands could not be broadcast together with shapes (1,1025) (0,)
while running the train.py for speech_command dataseti get the above mentioned error when i run
python train_speech_commands.py --model=resnext29_8_64 --optim=sgd --lr-scheduler=plateau --learning-rate=0.01 --lr-scheduler-patience=5 --max-epochs=70 --batch-size=96
while running the train.py for speech_command dataseti get the above mentioned error when i run
python train_speech_commands.py --model=resnext29_8_64 --optim=sgd --lr-scheduler=plateau --learning-rate=0.01 --lr-scheduler-patience=5 --max-epochs=70 --batch-size=96
Update Librosa from 0.5 to 0.6.2 v, this solved the issue for me