test.py

[ps-star]

We use the scale: 1 -------test----------- Load the model from ./model\ft_ResNet50\net_119.pth 1 -> 3: We use the scale: 1 -------test----------- Load the model from ./model\ft_ResNet50\net_119.pth 1 -> 3: We use the scale: 1 -------test----------- Load the model from ./model\ft_ResNet50\net_119.pth 1 -> 3: We use the scale: 1 -------test----------- Load the model from ./model\ft_ResNet50\net_119.pth 1 -> 3: Continuously looping

[layumi]

Are you running test.py? Please check https://github.com/layumi/University1652-Baseline/blob/master/test.py#L229 Did you modify the code? There are no any for or while loop functions.

[ps-star]

Hello, 229 represents' query_statellite '1->' gallery-drone '3, but there is still a loop problem in the image when running test.by

[ps-star]

def extract_feature(model,dataloaders, view_index = 1): features = torch.FloatTensor() count = 0 for data in dataloaders: img, label = data n, c, h, w = img.size() count += n print(count) ff = torch.FloatTensor(n,512).zero_().cuda()

    for i in range(2):
        if(i==1):
            img = fliplr(img)
        input_img = Variable(img.cuda())
        for scale in ms:
            if scale != 1:
                # bicubic is only  available in pytorch>= 1.1
                input_img = nn.functional.interpolate(input_img, scale_factor=scale, mode='bilinear', align_corners=False)
            if opt.views ==2:
                if view_index == 1:
                    outputs, _ = model(input_img, None) 
                elif view_index ==2:
                    _, outputs = model(None, input_img) 
            elif opt.views ==3:
                if view_index == 1:
                    outputs, _, _ = model(input_img, None, None)
                elif view_index ==2:
                    _, outputs, _ = model(None, input_img, None)
                elif view_index ==3:
                    _, _, outputs = model(None, None, input_img)
            ff += outputs
    # norm feature
    if opt.PCB:
        # feature size (n,2048,6)
        # 1. To treat every part equally, I calculate the norm for every 2048-dim part feature.
        # 2. To keep the cosine score==1, sqrt(6) is added to norm the whole feature (2048*6).
        fnorm = torch.norm(ff, p=2, dim=1, keepdim=True) * np.sqrt(6) 
        ff = ff.div(fnorm.expand_as(ff))
        ff = ff.view(ff.size(0), -1)
    else:
        fnorm = torch.norm(ff, p=2, dim=1, keepdim=True)
        ff = ff.div(fnorm.expand_as(ff))

    features = torch.cat((features,ff.data.cpu()), 0)
return features

UnboundLocalError: local variable 'outputs' referenced before assignment

[qwqwqer233]

def extract_feature(model,dataloaders, view_index = 1): features = torch.FloatTensor() count = 0 for data in dataloaders: img, label = data n, c, h, w = img.size() count += n print(count) ff = torch.FloatTensor(n,512).zero_().cuda()

    for i in range(2):
        if(i==1):
            img = fliplr(img)
        input_img = Variable(img.cuda())
        for scale in ms:
            if scale != 1:
                # bicubic is only  available in pytorch>= 1.1
                input_img = nn.functional.interpolate(input_img, scale_factor=scale, mode='bilinear', align_corners=False)
            if opt.views ==2:
                if view_index == 1:
                    outputs, _ = model(input_img, None) 
                elif view_index ==2:
                    _, outputs = model(None, input_img) 
            elif opt.views ==3:
                if view_index == 1:
                    outputs, _, _ = model(input_img, None, None)
                elif view_index ==2:
                    _, outputs, _ = model(None, input_img, None)
                elif view_index ==3:
                    _, _, outputs = model(None, None, input_img)
            ff += outputs
    # norm feature
    if opt.PCB:
        # feature size (n,2048,6)
        # 1. To treat every part equally, I calculate the norm for every 2048-dim part feature.
        # 2. To keep the cosine score==1, sqrt(6) is added to norm the whole feature (2048*6).
        fnorm = torch.norm(ff, p=2, dim=1, keepdim=True) * np.sqrt(6) 
        ff = ff.div(fnorm.expand_as(ff))
        ff = ff.view(ff.size(0), -1)
    else:
        fnorm = torch.norm(ff, p=2, dim=1, keepdim=True)
        ff = ff.div(fnorm.expand_as(ff))

    features = torch.cat((features,ff.data.cpu()), 0)
return features

UnboundLocalError: local variable 'outputs' referenced before assignment

[qwqwqer233]

i have the same problem,how did you fix it

[ps-star]

Make numw_workers=0，but when count=701, there will still be an UnboundLocalError: local variable 'outputs' referenced before assignment，which remains unresolved

[layumi]

Hi @Mayuzhuo0323 @ckmessi @hominsu

Thank you @ps-star

If you use Windows, please make sure your numw_workers=0. This is a well-kown case for pytorch on Windows.

@ps-star Could you provide more information about bug logs and your system?