SSD中的预测图像id和框

Question

如何从SSD中找到预测的图像id和Box，我正在使用这个GitHub链接这里是我想要保存图像id和框的测试功能

def test(loader, net, criterion, device):
net.eval()
running_loss = 0.0
running_regression_loss = 0.0
running_classification_loss = 0.0
num = 0
for _, data in enumerate(loader):
images, boxes, labels = data
images = images.to(device)
boxes = boxes.to(device)
labels = labels.to(device)
num += 1
with torch.no_grad():
confidence, locations = net(images)
regression_loss, classification_loss = criterion(confidence, locations, labels, boxes)
loss = regression_loss + classification_loss
running_loss += loss.item()
running_regression_loss += regression_loss.item()
running_classification_loss += classification_loss.item()
return running_loss / num, running_regression_loss / num, run

Answer 1

假设

y = net(x)
detections = y.data

您可以使用以下打印检测信息

# this will loop over predictions class by class
for i in range(detections.size(1)): 
# this will loop over each detection in the class
for j in range(detections.size(2)):
score = detection[0,i,j,0]
coords = detections[0,i,j,1:]
print(f"Class id: {i} t Score: {score} t Coords: {coords}")

有关更多详细信息，请参阅演示。