14.14. Dog Breed Identification (ImageNet Dogs) on Kaggle — Dive into Deep Learning 1.0.0-beta0 documentation
d2l.ai
Here, we choose a pretrained ResNet-34 model, where we simply reuse the input of this model’s output layer (i.e., the extracted features). Then we can replace the original output layer with a small custom output network that can be trained, such as stacking two fully connected layers.
1 Users
0 Comments
1 Highlights
0 Notes
Top Highlights
- Here, we choose a pretrained ResNet-34 model, where we simply reuse the input of this model’s output layer (i.e., the extracted features). Then we can replace the original output layer with a small custom output network that can be trained, such as stacking two fully connected layers.
Domain
Ready to highlight and find good content?
Glasp is a social web highlighter that people can highlight and organize quotes and thoughts from the web, and access other like-minded people’s learning.