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
Error when converting pretrained model: (raise ValueError("'%s' is not a valid scope name" % name) and 'functional_9/conv1/conv/Conv2D__6:0' is not a valid scope name
#134
Open
Lad4life opened this issue
Nov 17, 2021
· 1 comment
I tried to use the following code to change my onnx model to a keras model. I am using tensorflow version 2.1.0. My model is a densenet model that has been retrained for a new dataset. Let me know if additional information would be helpful. Thank you for your help!
#%% Load packages
import tensorflow as tf
import tf2onnx
import onnx
#%%
from onnx2keras import onnx_to_keras
#%% Load onnx model
onnx_model=onnx.load("Test_10_DC_R_Image.onnx")
#%% Convert to keras model
k_model = onnx_to_keras(onnx_model, input_names=['input'])
This is the error I recieved:
raise ValueError("'%s' is not a valid scope name" % name)
ValueError: 'functional_9/conv1/conv/Conv2D__6:0' is not a valid scope name
The text was updated successfully, but these errors were encountered:
I tried to use the following code to change my onnx model to a keras model. I am using tensorflow version 2.1.0. My model is a densenet model that has been retrained for a new dataset. Let me know if additional information would be helpful. Thank you for your help!
This is the error I recieved:
The text was updated successfully, but these errors were encountered: