Shape mismatch during sanity check

[Akhilesh64]

Can the target size be changed. Currently when I try to change it throws mat1 and mat2 shapes cannot be multiplied (3072x768 and 192x128) . I tried with target size (1000, 768). Tried setting max_position_embeddings to 768 and it throws stack expects each tensor to be equal size, but got [767, 8] at entry 0 and [768, 8] at entry 2. I am trying to replicate document classification task from the notebook provided.

[uakarsh]

Yep, it is a bit hardcoded. You need to see the ResNet Feature Extractor in modeling.py for the changes. Rest all as far as I know, would be handled.