我正在尝试使用 MC Dropout 方法和此链接中提出的解决方案来计算图像分类任务的数据集的每一类的熵,以测量 pytorch 上的不确定性
在 pytorch 上使用 MC Dropout 测量不确定性 https://stackoverflow.com/questions/63285197/measuring-uncertainty-using-mc-dropout-on-pytorch
首先,我计算了不同前向传递中每批每个类的平均值 (class_mean_batch),然后计算了所有测试加载程序 (classes_mean),然后进行了一些转换以获取 (total_mean) 以使用它来计算熵,如下面的代码所示
def mcdropout_test(batch_size,n_classes,model,T):
#set non-dropout layers to eval mode
model.eval()
#set dropout layers to train mode
enable_dropout(model)
softmax = nn.Softmax(dim=1)
classes_mean = []
for images,labels in testloader:
images = images.to(device)
labels = labels.to(device)
classes_mean_batch = []
with torch.no_grad():
output_list = []
#getting outputs for T forward passes
for i in range(T):
output = model(images)
output = softmax(output)
output_list.append(torch.unsqueeze(output, 0))
concat_output = torch.cat(output_list,0)
# getting mean of each class per batch across multiple MCD forward passes
for i in range (n_classes):
mean = torch.mean(concat_output[:, : , i])
classes_mean_batch.append(mean)
# getting mean of each class for the testloader
classes_mean.append(torch.stack(classes_mean_batch))
total_mean = []
concat_classes_mean = torch.stack(classes_mean)
for i in range (n_classes):
concat_classes = concat_classes_mean[: , i]
total_mean.append(concat_classes)
total_mean = torch.stack(total_mean)
total_mean = np.asarray(total_mean.cpu())
epsilon = sys.float_info.min
# Calculating entropy across multiple MCD forward passes
entropy = (- np.sum(total_mean*np.log(total_mean + epsilon), axis=-1)).tolist()
for i in range(n_classes):
print(f'The uncertainty of class {i+1} is {entropy[i]:.4f}')
任何人都可以纠正或确认我用来计算每个类的熵的实现。
None
本文内容由网友自发贡献,版权归原作者所有,本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容,请联系:hwhale#tublm.com(使用前将#替换为@)