https://github.com/dragen1860/LearningToCompare-Pytorch

Pytorch Implementation for CVPR2018 Paper: Learning to Compare: Relation Network for Few-Shot Learning
https://github.com/dragen1860/LearningToCompare-Pytorch

Last synced: 13 days ago
JSON representation

Pytorch Implementation for CVPR2018 Paper: Learning to Compare: Relation Network for Few-Shot Learning

• Host: GitHub
• URL: https://github.com/dragen1860/LearningToCompare-Pytorch
• Owner: dragen1860
• Created: 2018-01-22T12:16:26.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2018-02-15T06:50:45.000Z (over 6 years ago)
• Last Synced: 2024-10-22T23:30:41.732Z (17 days ago)
• Language: Python
• Homepage:
• Size: 30.3 KB
• Stars: 250
• Watchers: 10
• Forks: 48
• Open Issues: 2
• Metadata Files:
  • Readme: Readme.md

Awesome Lists containing this project

• awesome-few-shot-meta-learning - code (PyTorch)

README

        
# LearningToCompare

Pytorch Implementation for Paper: Learning to Compare: Relation Network for Few-Shot Learning

# Howto

download mini-imagenet and make it looks like:

```shell

mini-imagenet/

├── images

	├── n0210891500001298.jpg  

	├── n0287152500001298.jpg 

	...

├── test.csv

├── val.csv

└── train.csv

LearningToCompare-Pytorch/

├── compare.py

├── MiniImagenet.py

├── Readme.md

├── repnet.py

├── train.py

└── utils.py

```

```python

python train.py

```

# NOTICE

current code support multi-gpus on single machine training, to disable it and train on single machine, 

just set device_ids=[0] and downsize batch size according to your gpu memory capacity.

make sure `ckpt` directory exists, otherwise `mkdir ckpt`.

# mini-Imagenet

| Model                               | Fine Tune | 5-way Acc. |        | 20-way Acc |        |

|-------------------------------------|-----------|------------|--------|------------|--------|

|                                     |           | 1-shot     | 5-shot | 1-shot     | 5-shot |

| Matching Nets                       | N         | 43.56%     | 55.31% | 17.31%     | 22.69% |

| Meta-LSTM                           |           | 43.44%     | 60.60% | 16.70%     | 26.06% |

| MAML                                | Y         | 48.7%      | 63.11% | 16.49%     | 19.29% |

| Meta-SGD                            |           | 50.49%     | 64.03% | 17.56%     | 28.92% |

| TCML                                |           | 55.71%     | 68.88% | -          | -      |

| Learning to Compare            | N         | 57.02%     | 71.07% | -          | -      |

| **Ours, similarity ensemble**				      | N         |  55.2%     |    68.8%      |          |        | 

| **Ours, feature ensemble**				      | N         |  55.2%     |    70.1%      |          |        |