incorrect shape when loading model checkpoints

[neurosynapse]

Hello,

I have trained several models vgg16-ssd and mb1-ssd-lite. However when I try to run inference on single image and load the model I always get incorrect shapes and weight names. What could cause that?

Examples of incorrect shape and weight names when loading model checkpoints for vgg16-ssd:

Best regards,
Roberts

[theATM]

The same error here :(

[jennib3]

This is obviously old, but in case anyone is still running into this ensure that you have the same number of classes when resuming training as when it was first trained.