search

wenjiaXu / APN-ZSL

This is a PyTorch implementation of the paper "Attribute Prototype Network for Zero-Shot Learning".
69 stars 8 forks source link

Question #20

Open lassloss opened 1 year ago

lassloss commented 1 year ago

The model of the global part and the local part in your code seems to be the same, and the pre-trained resnet101 you used seems to be fine-tuned. After I downloaded the pre-trained resnet101 from pytorch, the model’s results dropped by nearly ten points.

passer commented 9 months ago

The model of the global part and the local part in your code seems to be the same, and the pre-trained resnet101 you used seems to be fine-tuned. After I downloaded the pre-trained resnet101 from pytorch, the model’s results dropped by nearly ten points.

Have you reproduced the approaching situation?