Pytorch:如何计算用于语义分割的IoU(Jaccard索引)
有人能提供一个玩具例子来说明如何在pytorch中为语义分段计算IoU(联合交集)吗?我在某处找到了这个,并对它进行了修改。如果我能再次找到它,我会发布链接。很抱歉,这是一个错误。Pytorch:如何计算用于语义分割的IoU(Jaccard索引),pytorch,Pytorch,有人能提供一个玩具例子来说明如何在pytorch中为语义分段计算IoU(联合交集)吗?我在某处找到了这个,并对它进行了修改。如果我能再次找到它,我会发布链接。很抱歉,这是一个错误。 这里的关键函数是名为iou的函数。包装函数evaluate\u performance不是通用的,但它表明在计算IoU之前需要迭代所有结果 import torch import pandas as pd # For filelist reading import myPytorchDatasetClass #
这里的关键函数是名为
iou
的函数。包装函数evaluate\u performance
不是通用的,但它表明在计算IoU
之前需要迭代所有结果
import torch
import pandas as pd # For filelist reading
import myPytorchDatasetClass # Custom dataset class, inherited from torch.utils.data.dataset
def iou(pred, target, n_classes = 12):
ious = []
pred = pred.view(-1)
target = target.view(-1)
# Ignore IoU for background class ("0")
for cls in xrange(1, n_classes): # This goes from 1:n_classes-1 -> class "0" is ignored
pred_inds = pred == cls
target_inds = target == cls
intersection = (pred_inds[target_inds]).long().sum().data.cpu()[0] # Cast to long to prevent overflows
union = pred_inds.long().sum().data.cpu()[0] + target_inds.long().sum().data.cpu()[0] - intersection
if union == 0:
ious.append(float('nan')) # If there is no ground truth, do not include in evaluation
else:
ious.append(float(intersection) / float(max(union, 1)))
return np.array(ious)
def evaluate_performance(net):
# Dataloader for test data
batch_size = 1
filelist_name_test = '/path/to/my/test/filelist.txt'
data_root_test = '/path/to/my/data/'
dset_test = myPytorchDatasetClass.CustomDataset(filelist_name_test, data_root_test)
test_loader = torch.utils.data.DataLoader(dataset=dset_test,
batch_size=batch_size,
shuffle=False,
pin_memory=True)
data_info = pd.read_csv(filelist_name_test, header=None)
num_test_files = data_info.shape[0]
sample_size = num_test_files
# Containers for results
preds = Variable(torch.zeros((sample_size, 60, 36, 60)))
gts = Variable(torch.zeros((sample_size, 60, 36, 60)))
dataiter = iter(test_loader)
for i in xrange(sample_size):
images, labels, filename = dataiter.next()
images = Variable(images).cuda()
labels = Variable(labels)
gts[i:i+batch_size, :, :, :] = labels
outputs = net(images)
outputs = outputs.permute(0, 2, 3, 4, 1).contiguous()
val, pred = torch.max(outputs, 4)
preds[i:i+batch_size, :, :, :] = pred.cpu()
acc = iou(preds, gts)
return acc
假设您的输出是形状
[32,256,256]
#32是小批量大小,256x256是图像的高度和宽度,标签也是相同的形状
然后你可以使用sklearn的jaccard\u相似度\u分数
,在一些重塑之后
如果两者都是火炬张量,则:
lbl = labels.cpu().numpy().reshape(-1)
target = output.cpu().numpy().reshape(-1)
现在:
演示如何在tensorflow中实现它。将其移植到PyTorch应该是很容易的。在最新的Sklearn中,如0.24.1,函数名已更改为jaccard_score。
from sklearn.metrics import jaccard_similarity_score as jsc
print(jsc(target,lbl))