TypeError: string indices must be integers

vision
1

I try to use rcnn to train my model,. I follow the guidence to create my dataset and put it into the model, but it seems that I got something wrong in my model and I don’t know why. Who can tell me what is wrong since I have been frustrated by this part.

Here is my dataloader

import os
import numpy as np
import torch
from PIL import Image
import xml.dom.minidom as xmldom
from torchvision import transforms as T


def parse_xml(fn):
    xml_file = xmldom.parse(fn)
    eles = xml_file.documentElement
    print(eles.tagName)
    xmin = eles.getElementsByTagName("xmin")[0].firstChild.data
    xmax = eles.getElementsByTagName("xmax")[0].firstChild.data
    ymin = eles.getElementsByTagName("ymin")[0].firstChild.data
    ymax = eles.getElementsByTagName("ymax")[0].firstChild.data
    return xmin, xmax, ymin, ymax

class MaskDataset(object):
    def __init__(self, pic_root, mask_root ,transforms):
        
        self.pic_root = pic_root
        self.mask_root = mask_root
        self.transforms = transforms
        self.imgs = list(sorted(os.listdir(os.path.join(pic_root, "image_mask/"))))
        self.loc = list(sorted(os.listdir(os.path.join(mask_root, "location/"))))
        
    def __getitem__(self, idx):
        # load images ad masks
        img_path = os.path.join(self.pic_root, "image_mask", self.imgs[idx])
        loc_path = os.path.join(self.mask_root, "location", self.loc[idx])
        img = Image.open(img_path).convert("RGB")
        # note that we haven't converted the mask to RGB,
        # because each color corresponds to a different instance
        # with 0 being background
        xmin,xmax,ymin,ymax= parse_xml(loc_path)
        xmin = int(xmin)
        xmax = int(xmax)
        ymin = int(ymin)
        ymax = int(ymax)
        boxes = []
        boxes.append([xmin, ymin, xmax, ymax])
        boxes = torch.as_tensor(boxes, dtype=torch.float32)
        labels = torch.ones(1,dtype=torch.int64)
        
        target = {}
        target["boxes"] = boxes
        target["labels"] = labels
        target["image_id"] = torch.tensor([idx])

        if self.transforms is not None:
            img = self.transforms(img)
        return img, target

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

path = 'C:/Users/msi/Desktop/Final/image/'
transforms=T.Compose([
                T.Resize((256,256),Image.BICUBIC),
                T.ToTensor(),
                T.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
            ])
dataset=MaskDataset(path,path,transforms)

image,target=dataset.__getitem__(0)
for key in target:
    print(key)
    print(target[key])
data_loader = torch.utils.data.DataLoader(dataset, batch_size=2, shuffle=True,num_workers=0)

Here is my model

import torchvision
from torchvision.models.detection.faster_rcnn import FastRCNNPredictor

# load a model pre-trained pre-trained on COCO
model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)

# replace the classifier with a new one, that has
# num_classes which is user-defined
num_classes = 2  # 1 class (person) + background
# get number of input features for the classifier
in_features = model.roi_heads.box_predictor.cls_score.in_features
# replace the pre-trained head with a new one
model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)

device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
model.to(device)

params = [p for p in model.parameters() if p.requires_grad]

optimizer = torch.optim.SGD(params, lr=0.005,
                                momentum=0.9, weight_decay=0.0005)
    # and a learning rate scheduler
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
                                                   step_size=3,
                                                   gamma=0.1)

    # let's train it for 10 epochs
num_epochs = 10

And every time I try to train my model, it shows the error like this

from tqdm import tqdm
model.train()
for epoch in range(num_epochs):
        for image,target in tqdm(data_loader):
            image = image.to(device)
            for key in target:
                target[key].to(device)
            output = model(image,target)

>TypeError                                 Traceback (most recent call last)
<ipython-input-285-a118b838b79c> in <module>
      6             for key in target:
      7                 target[key].to(device)
----> 8             output = model(image,target)

E:\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
    720             result = self._slow_forward(*input, **kwargs)
    721         else:
--> 722             result = self.forward(*input, **kwargs)
    723         for hook in itertools.chain(
    724                 _global_forward_hooks.values(),

E:\Anaconda3\lib\site-packages\torchvision\models\detection\generalized_rcnn.py in forward(self, images, targets)
     61             assert targets is not None
     62             for target in targets:
---> 63                 boxes = target["boxes"]
     64                 if isinstance(boxes, torch.Tensor):
     65                     if len(boxes.shape) != 2 or boxes.shape[-1] != 4:

TypeError: string indices must be integers
2

OK, i have solve this problem by reading the turorial in detail.

3

https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html

4

TypeError: means that you are trying to perform an operation on a value whose type is not compatible with that operation. An Iterable is a collection of elements that can be accessed sequentially . In Python, iterable objects are indexed using numbers . When you try to access an iterable object using a string or a float as the index, an error will be returned as TypeError: string indices must be integers. This means that when you’re accessing an iterable object like a string or float value, you must do it using an integer value.

1 Like