---
tags: NTU-IoT-Cow, FSL
---
# Few-shot learning (FSL) Experment

[](https://github.com/WesleyCh3n/FSL)
[](https://hackmd.io/ct3mDHTJR2CLHUrys-jv2A)

## Overview


## Baseline Model Training

In `baseline model training`, we use `Source domain dataset` (
<img src="https://render.githubusercontent.com/render/math?math=D_s">
).

### 1. Weight Initialization: `Cross-Entropy Loss`

- Edit `exp/sample_experiment/baseline_softmax/params.py`

        params = {
        'n_epochs': 50,
        'n_class': 19,  # TODO
        'size': [224, 224],
        'batch_size': 64,
        'lr': 'default',
        'early_stopping': 5,

        'train_ds': '/path/to/train_ds',  # TODO
        'test_ds': '/path/to/test_ds',  # TODO
        'save_every_n_epoch': 1
    }

- Start training:

    python3 train_softmax.py <path/to/params.py>

- During training, to visualize loss and accuracy:

    tensorboard --logdir <path/to/params.py parent>

- After training complete:
- Model `Checkpoint` directory is same as `path/to/params.py`

### 2. Baseline Feature Extractor: `Triplet Loss`

- Edit `exp/sample_experiment/baseline_triplet/params.py`

    params = {
        'n_epochs': 100,
        'n_class': 19,  # TODO
        'n_class_per_batch': 19,  # TODO
        'n_per_class': 10,  # TODO
        'size': [224, 224],
        'margin': 0.7,  # TODO
        'lr': 'default',
        'early_stopping': 20,

        'pretrained_weight': '/path/to/baseline_softmax/model',  # TODO
        'train_ds': '/path/to/train_ds',  # TODO
        'save_every_n_epoch': 1
    }

⚠️ *Caution: `pretrained_weight` should left `model` in the last in order to read `checkpoint` properly*

- During training, to visualize triplet loss, hardest negative distance (*HND*) and hardest positive distance (*HPD*):

    tensorboard --logdir <path/to/params.py parent>

- Start training:

    python3 train_softmax2triplet.py <path/to/params.py>

## FSL Update Training

In `FSL update training`, we use `Target domain dataset` (
<img src="https://render.githubusercontent.com/render/math?math=D_t">
).

- Edit `exp/sample_experiment/fewshot-triplet/params.py`

    params = {
        'n_epochs': 100,
        'n_class': 23,  # TODO
        'n_class_per_batch': 23,  # TODO
        'n_per_class': 10,  # TODO
        'size': [224, 224],
        'margin': 0.7,  # TODO
        'lr': 'default',
        'early_stopping': 20,

        'pretrained_weight': '/path/to/baseline_triplet/model',  # TODO
        'train_ds': '/path/to/train_ds',  # TODO
        'save_every_n_epoch': 1
    }

- During training, to visualize triplet loss, hardest negative distance (*HND*) and hardest positive distance (*HPD*):

    tensorboard --logdir <path/to/params.py parent>

- Start training:

    python3 train_triplet_fine_tune.py <path/to/params.py>