-
Notifications
You must be signed in to change notification settings - Fork 146
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
TF2.5 class_weight error #162
Comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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_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
tosample_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?
Thank you very much!
The text was updated successfully, but these errors were encountered: