search

penghu-cs / RONO

RONO: Robust Discriminative Learning with Noisy Labels for 2D-3D Cross-Modal Retrieval (CVPR 2023, PyTorch Code)
17 stars 2 forks source link

Confused about Pt_fc and HeadNet #7

Closed UnderTheMangoTree closed 1 month ago

UnderTheMangoTree commented 1 month ago

the output dim of Pt_fc is [B,10] but the input dim of HeadNet must be [B, 256]. Therefore, running open_source_train_mnist.py will generate errors.

Yangl1nFeng commented 1 month ago

Hello! Sorry, there is some redundant code here. You can see that self.linear3 in Pt_fc is not actually used, and its output is still 256-dimensional. Hope this helps you!

UnderTheMangoTree commented 1 month ago

Thank you for your response！