You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
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?
The text was updated successfully, but these errors were encountered:
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?
The text was updated successfully, but these errors were encountered: