cfchen-duke/ProtoPNet
This code package implements the prototypical part network (ProtoPNet) from the paper "This Looks Like That: Deep Learning for Interpretable Image Recognition" (to appear at NeurIPS 2019), by Chaofan Chen* (Duke University), Oscar Li* (Duke University), Chaofan Tao (Duke University), Alina Jade Barnett (Duke University), Jonathan Su (MIT Lincoln Laboratory), and Cynthia Rudin (Duke University) (* denotes equal contribution).
PythonNOASSERTION
Issues
- 3
Augmentor Error
#23 opened by Yung-zi - 3
Augmentor error on rotate
#21 opened by smdabdoub - 0
- 1
100% accuracy on CUB with VGG-19
#28 opened by xinmiaolin - 0
How is the baseline resnet34 model trained?
#27 opened by TADanton - 1
For local_analysis a push or no_push model?
#26 opened by Ron12234 - 4
Augmenting Dataset
#20 opened by EoinKenny - 0
Number of params ProtoPNet
#25 opened by Ron12234 - 1
if I want to prune prototype, what should I do?
#24 opened by boileddd - 3
- 5
Is it real that 1000 epochs are need
#8 opened by lovekeyczw - 0
Torch warning after warm-up epochs: `lr_scheduler.step()` before `optimizer.step()`
#22 opened by smdabdoub - 1
Reproducibility
#11 opened by dafei-qin - 2
Pretrained weights
#19 opened by elias-ramzi - 3
Pre-trained models?
#9 opened by anguyen8 - 0
Package Requirements
#17 opened by pedroalopes - 0
model.eval() in local_analysis.py
#12 opened by jxllp - 1
DEAULT TEST ACCURACY IS SO LOW
#10 opened by Dadatata-JZ - 1
The model cannot handle a single picture
#5 opened by yanghedada