Skip to content
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

KeyError: <QuantScheme.post_training_tf_enhanced: 2> #3735

Open
ziFan99 opened this issue Jan 17, 2025 · 0 comments
Open

KeyError: <QuantScheme.post_training_tf_enhanced: 2> #3735

ziFan99 opened this issue Jan 17, 2025 · 0 comments

Comments

@ziFan99
Copy link

ziFan99 commented Jan 17, 2025

When running the following code:

I encountered the error KeyError: <QuantScheme.post_training_tf_enhanced: 2>. I have checked /root/autodl-tmp/aimet-1.32.0/TrainingExtensions/common/src/python/aimet_common/defs.py, and the code contains the corresponding QuantScheme.post_training_tf_enhanced. Why is this error still occurring?
`import onnx
from TrainingExtensions.onnx.src.python.aimet_onnx.batch_norm_fold import fold_all_batch_norms_to_weight
from TrainingExtensions.common.src.python.aimet_common.defs import QuantScheme
from TrainingExtensions.onnx.src.python.aimet_onnx.quantsim import QuantizationSimModel
from TrainingExtensions.onnx.src.python.aimet_onnx.cross_layer_equalization import equalize_model

import numpy as np
import onnxruntime as ort

filename = "/root/autodl-tmp/aimet-1.32.0/onnx/rec_mv3_none_bilstm_ctc_crnn_32X100.onnx"

model = onnx.load_model(filename)

dummy_input = {"x": np.random.randn(1, 3, 32, 100).astype(np.float32)}
_ = fold_all_batch_norms_to_weight(model)

sim = QuantizationSimModel(
model=model,
quant_scheme=QuantScheme.post_training_tf_enhanced,
default_activation_bw=8,
default_param_bw=8,
dummy_input=dummy_input,
use_cuda=True
)`
I encountered the error KeyError: <QuantScheme.post_training_tf_enhanced: 2>.
I have checked TrainingExtensions/common/src/python/aimet_common/defs.py, and the code contains the corresponding QuantScheme.post_training_tf_enhanced. Why is this error still occurring?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant