python - Pytorch“upsample_bilinear2d_out_frame”未为“字节”实现

问题描述

我已经使用此链接中描述的步骤训练了一个自定义对象检测模型。我能够训练我的模型，但是当我尝试在一个时期结束时对其进行评估时，我收到以下错误

Epoch: [0] Total time: 0:00:06 (0.2223 s / it)
creating index...
index created!
Traceback (most recent call last):
  File "train.py", line 106, in <module>
    evaluate(model, data_loader_test, device=device)
  File "/home/sarvani/anaconda3/envs/flir_env/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 49, in decorate_no_grad
    return func(*args, **kwargs)
  File "/home/sarvani/Desktop/flir/test_frcnn/custom/engine.py", line 107, in evaluate
    outputs = model(image)
  File "/home/sarvani/anaconda3/envs/flir_env/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/sarvani/anaconda3/envs/flir_env/lib/python3.7/site-packages/torchvision/models/detection/generalized_rcnn.py", line 47, in forward
    images, targets = self.transform(images, targets)
  File "/home/sarvani/anaconda3/envs/flir_env/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/sarvani/anaconda3/envs/flir_env/lib/python3.7/site-packages/torchvision/models/detection/transform.py", line 41, in forward
    image, target = self.resize(image, target)
  File "/home/sarvani/anaconda3/envs/flir_env/lib/python3.7/site-packages/torchvision/models/detection/transform.py", line 70, in resize
    image[None], scale_factor=scale_factor, mode='bilinear', align_corners=False)[0]
  File "/home/sarvani/anaconda3/envs/flir_env/lib/python3.7/site-packages/torch/nn/functional.py", line 2503, in interpolate
    return torch._C._nn.upsample_bilinear2d(input, _output_size(2), align_corners)
RuntimeError: "upsample_bilinear2d_out_frame" not implemented for 'Byte'

我加载数据的代码如下

class CustomDataset(torch.utils.data.Dataset):

    def __init__(self, root_dir,transform=None):
        self.root = root_dir
        self.rgb_imgs = list(sorted(os.listdir(os.path.join(root_dir, "rgb/"))))
        self.annotations = list(sorted(os.listdir(os.path.join(root_dir, "annotations/"))))


        self._classes = ('__background__',  # always index 0
                         'car','person','bicycle','dog','other')

        self._class_to_ind = {'car':'1', 'person':'2', 'bicycle':'3', 'dog':'4','other':'5'}


    def __len__(self):
        return len(self.rgb_imgs)

    def __getitem__(self, idx):
        self.num_classes = 6

        img_rgb_path = os.path.join(self.root, "rgb/", self.rgb_imgs[idx])   
        img = Image.open(img_rgb_path)
        img = np.array(img)
        img = img.transpose((2, 0, 1))
        img = torch.from_numpy(img)

        filename = os.path.join(self.root,'annotations',self.annotations[idx])
        tree = ET.parse(filename)
        objs = tree.findall('object')

        num_objs = len(objs)
        labels = np.zeros((num_objs), dtype=np.float32)
        seg_areas = np.zeros((num_objs), dtype=np.float32)

        boxes = []
        for ix, obj in enumerate(objs):
            bbox = obj.find('bndbox')
            x1 = float(bbox.find('xmin').text)
            y1 = float(bbox.find('ymin').text)
            x2 = float(bbox.find('xmax').text)
            y2 = float(bbox.find('ymax').text)

            cls = self._class_to_ind[obj.find('name').text.lower().strip()]
            boxes.append([x1, y1, x2, y2])
            labels[ix] = cls

        boxes = torch.as_tensor(boxes, dtype=torch.float32)
        area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])
        image_id = torch.tensor([idx])
        iscrowd = torch.zeros((num_objs,), dtype=torch.int64)
        labels = torch.as_tensor(labels, dtype=torch.float32)

        target =  {'boxes': boxes,
                'labels': labels,
                'area': area,
                "image_id":image_id
                }
        target["iscrowd"] = iscrowd
        return img,target

我的 train.py 如下

num_classes = 6
model = fasterrcnn_resnet50_fpn(pretrained=True)
in_features = model.roi_heads.box_predictor.cls_score.in_features
model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)

device = torch.device('cuda')
model = model.cuda()

dataset_train = CustomDataset('FLIR/images/train')
dataset_val = CustomDataset('FLIR/images/val')


data_loader_train = torch.utils.data.DataLoader(
    dataset_train, batch_size=4, shuffle=True,collate_fn=utils.collate_fn)

data_loader_test = torch.utils.data.DataLoader(
    dataset_val, batch_size=4 shuffle=False,collate_fn=utils.collate_fn)

params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.Adam(params,lr=0.05,weight_decay=0.0005)
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
                                               step_size=3,
                                               gamma=0.1)

num_epochs = 30

for epoch in range(num_epochs):
    train_one_epoch(model, optimizer, data_loader_train, device, epoch, print_freq=1)
    lr_scheduler.step()
    evaluate(model, data_loader_test, device=device)

带有所需文件的评估函数位于此链接。

有人可以帮帮我吗。

标签： pythonpytorchobject-detectiontorchtorchvision

python - Pytorch“upsample_bilinear2d_out_frame”未为“字节”实现

问题描述

解决方案

推荐阅读