When I convert the model, I can't get the Conv weight ? I am confused about it.

[GuardSkill]

[GuardSkill]

The initializers dict don't have the weight key

[Nueractive]

this is my net

[fumihwh]

@GuardSkill A hypothesis is that model's weight is not stored in initializer field. You can print model.graph.initializer to confirm it.

[GuardSkill]

Thanks for your reply, I have solved this problem. This issue is raised by the Conv's weight inferred by the conv operation in the forward process, I modify the op_code_generator/Conv.py and op_code_generator/ConvTranspose.py for the support the 'F.conv2d()". Your contribution is great,