pytorch 学习之：使用 torchRay 来完成指定神经网络层的可视化

代码from torchray.attribution.grad_cam import grad_camfrom torchray.benchmark import get_example_data, plot_example# Obtain example data.model, x, category_id, _ = get_example_data()# Grad-CAM backprop.

暖仔会飞

1297人浏览 · 2022-01-31 02:01:45

暖仔会飞 · 2022-01-31 02:01:45 发布

代码

from torchray.attribution.grad_cam import grad_cam
from torchray.benchmark import get_example_data, plot_example

# Obtain example data.
model, x, category_id, _ = get_example_data()

# Grad-CAM backprop.
saliency = grad_cam(model, x, category_id, saliency_layer='features.29')

# Plots.
plot_example(x, saliency, 'grad-cam backprop', category_id)