I have encountered some tough problems in the process of trying to improve EQTransformer. I hope to get your reply.
I can successfully run Tensorflow=2.0.0+EQTransformer=0.1.59, but I can't use the GPU because my GPU is RTX3060
It is found that RTX3060 only supports CUDA>=11.1, in which case Tensorflow>=2.4 is required. An error occurs when I try to use Tensorflow=2.5.0+EQTransformer=0.1.61: class_weight is only supported for Models with a single output.
The specific location of the error is:
trainer.py
history = model.fit_generator(generator=training_generator,
validation_data=validation_generator,
use_multiprocessing=args['use_multiprocessing'],
workers=multiprocessing.cpu_count(),
callbacks=callbacks,
epochs=args['epochs'],
class_weight={0: 0.11, 1: 0.89})
data_adapter.py
def _class_weights_map_fn(*data):
"""Convert class_weight to sample_weight."""
x, y, sw = unpack_x_y_sample_weight(data)
if nest.is_nested(y):
raise ValueError(
"class_weight is only supported for Models with a single output.")
I inquired the source code and found that this error was actually caused by TF update, but I had to use GPU again, so is there any good solution? Did you encounter this error with TF=2.5.0?
Dear Dr. S.Mostafa Mousavi, hello!
I have encountered some tough problems in the process of trying to improve EQTransformer. I hope to get your reply.
I can successfully run Tensorflow=2.0.0+EQTransformer=0.1.59, but I can't use the GPU because my GPU is RTX3060
It is found that RTX3060 only supports CUDA>=11.1, in which case Tensorflow>=2.4 is required. An error occurs when I try to use Tensorflow=2.5.0+EQTransformer=0.1.61:
class_weightis only supported for Models with a single output.The specific location of the error is: trainer.py history = model.fit_generator(generator=training_generator, validation_data=validation_generator, use_multiprocessing=args['use_multiprocessing'], workers=multiprocessing.cpu_count(), callbacks=callbacks, epochs=args['epochs'], class_weight={0: 0.11, 1: 0.89}) data_adapter.py def _class_weights_map_fn(*data): """Convert
class_weighttosample_weight.""" x, y, sw = unpack_x_y_sample_weight(data)if nest.is_nested(y): raise ValueError( "
class_weightis only supported for Models with a single output.")I inquired the source code and found that this error was actually caused by TF update, but I had to use GPU again, so is there any good solution? Did you encounter this error with TF=2.5.0?
Thank you very much!