Python影像辨識筆記(三十一):Zero-Shot Classification — CADA-VAE-PyTorch
Mar 15, 2021
介紹
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders的程式碼實現
安裝
官方建議的套件版本
torch==0.4.1
numpy==1.14.3
scipy==1.1.0
scikit_learn==0.20.3
networkx==1.11
建議使用conda建立虛擬環境,避免與原本的環境衝突
git clone https://github.com/edgarschnfld/CADA-VAE-PyTorchcd CADA-VAE-PyTorchpip install -r requirements.txtmkdir data && cd datawget -O data https://www.dropbox.com/sh/btoc495ytfbnbat/AAAaurkoKnnk0uV-swgF-gdSa?dl=1
訓練
python single_experiment.py --dataset CUB --num_shots 0 --generalized True# 可使用的參數:
datasets: CUB, SUN, AWA1, AWA2
num_shots: any number
generalized: True, False