Grad-CAM: Why did you say that?
Visual Explanations from Deep Networks via Gradient-based Localization
1. 简介
Gradient-weighted Class Activation
Mapping (Grad-CAM),卷积神经网络可视化的工具
2.实现
class GradCam:
def __init__(self, model, target_layer_names, use_cuda):
self.model = model
self.model.eval()
self.cuda = use_cuda
if self.cuda:
self.model = model.cuda()
self.extractor = ModelOutputs(self.model, target_layer_names)
def forward(self, input):
return self.model(input)
def __call__(self, input, index=None):
if self.cuda:
features, output = self.extractor(input.cuda())
else:
features, output = self.extractor(input)
if index == None:
index = np.argmax(output.cpu().data.numpy())
one_hot = np.zeros((1, output.size()[-1]), dtype=np.float32)
one_hot[0][index] = 1
one_hot = torch.from_numpy(one_hot).requires_grad_(True)
if self.cuda:
one_hot = torch.sum(one_hot.cuda() * output)
else:
one_hot = torch.sum(one_hot * output)
self.model.features.zero_grad()
self.model.classifier.zero_grad()
one_hot.backward(retain_graph=True)
grads_val = self.extractor.get_gradients()[-1].cpu().data.numpy()
target = features[-1]
target = target.cpu().data.numpy()[0, :]
weights = np.mean(grads_val, axis=(2, 3))[0, :]
cam = np.zeros(target.shape[1:], dtype=np.float32)
for i, w in enumerate(weights):
cam += w * target[i, :, :]
cam = np.maximum(cam, 0)
cam = cv2.resize(cam, (224, 224))
cam = cam - np.min(cam)
cam = cam / np.max(cam)
return cam
参考: