>>> import torch
>>> import torchvision.transforms.functional as F
>>> F.get_image_size(torch.zeros((3, 300, 400)))
[400, 300]
          
Hello @datumbox I'm using the latest stable build v0.10 (pytorch version 1.9.0+cu10.2) (as per the installation section in getting started).
Regarding code, I am literally using the Pytorch tutorial as it is, with only tweaks being Google Drive paths to data and model checkpoint storage locations.
          
The latest stable version version of TorchVsion does not have the get_image_size() public. The change was made yesterday. If you want to access it along with other latest features, I advise you to either try the nightly or install from source.
If you continue having issues using the latest development version, send me a standalone minimal snippet that reproduces the issue so that we can investigate.
          
Okay, so I switched my environment to use the LTS version (pip install torch==1.8.2+cu102 torchvision==0.9.2+cu102 torchaudio===0.8.2 -f https://download.pytorch.org/whl/lts/1.8/torch_lts.html) and the error still persists.
As for standalone snippet, I think these specific cells of code should help:
Source - "https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html#writing-a-custom-dataset-for-pennfudan"
import os
import numpy as np
import torch
from PIL import Image
class PennFudanDataset(torch.utils.data.Dataset):
    def __init__(self, root, transforms):
        self.root = root
        self.transforms = transforms
        # load all image files, sorting them to
        # ensure that they are aligned
        self.imgs = list(sorted(os.listdir(os.path.join(root, "PNGImages"))))
        self.masks = list(sorted(os.listdir(os.path.join(root, "PedMasks"))))
    def __getitem__(self, idx):
        # load images and masks
        img_path = os.path.join(self.root, "PNGImages", self.imgs[idx])
        mask_path = os.path.join(self.root, "PedMasks", self.masks[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
        mask = Image.open(mask_path)
        # convert the PIL Image into a numpy array
        mask = np.array(mask)
        # instances are encoded as different colors
        obj_ids = np.unique(mask)
        # first id is the background, so remove it
        obj_ids = obj_ids[1:]
        # split the color-encoded mask into a set
        # of binary masks
        masks = mask == obj_ids[:, None, None]
        # get bounding box coordinates for each mask
        num_objs = len(obj_ids)
        boxes = []
        for i in range(num_objs):
            pos = np.where(masks[i])
            xmin = np.min(pos[1])
            xmax = np.max(pos[1])
            ymin = np.min(pos[0])
            ymax = np.max(pos[0])
            boxes.append([xmin, ymin, xmax, ymax])
        # convert everything into a torch.Tensor
        boxes = torch.as_tensor(boxes, dtype=torch.float32)
        # there is only one class
        labels = torch.ones((num_objs,), dtype=torch.int64)
        masks = torch.as_tensor(masks, dtype=torch.uint8)
        image_id = torch.tensor([idx])
        area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])
        # suppose all instances are not crowd
        iscrowd = torch.zeros((num_objs,), dtype=torch.int64)
        target = {}
        target["boxes"] = boxes
        target["labels"] = labels
        target["masks"] = masks
        target["image_id"] = image_id
        target["area"] = area
        target["iscrowd"] = iscrowd
        if self.transforms is not None:
            img, target = self.transforms(img, target)
        return img, target
    def __len__(self):
        return len(self.imgs)
Source - "vision/references/detection/transforms.py"
from torch import nn, Tensor
from torchvision.transforms import functional as F
from torchvision.transforms import transforms as T
from typing import List, Tuple, Dict, Optional
class RandomHorizontalFlip(T.RandomHorizontalFlip):
    def forward(self, image: Tensor,
                target: Optional[Dict[str, Tensor]] = None) -> Tuple[Tensor, Optional[Dict[str, Tensor]]]:
        if torch.rand(1) < self.p:
            image = F.hflip(image)
            if target is not None:
                width, _ = F.get_image_size(image)  ## This line is throwing an error
                target["boxes"][:, [0, 2]] = width - target["boxes"][:, [2, 0]]
                if "masks" in target:
                    target["masks"] = target["masks"].flip(-1)
                if "keypoints" in target:
                    keypoints = target["keypoints"]
                    keypoints = _flip_coco_person_keypoints(keypoints, width)
                    target["keypoints"] = keypoints
        return image, target
# Importing vision/references/detection/transforms.py (the file is located at same level as Jupyter notebook)
import transforms as Tf  
def get_transform(train):
    transforms = []
    transforms.append(Tf.ToTensor())
    if train:
        transforms.append(RandomHorizontalFlip(0.5))
    return Tf.Compose(transforms)
# Import the custom dataset defined previously,
dataset = PennFudanDataset(os.path.join('PennFudanPed'), get_transform(train=True))
print(dataset.__getitem__(45))
--------------------------------------------------------------------------

Error:
AttributeError                            Traceback (most recent call last)
<ipython-input-20-87a7b71fa365> in <module>()
      4 dataset_test = torch.utils.data.Subset(dataset_test, indices[-50:])
----> 6 print(dataset.__getitem__(45))
4 frames
/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataset.py in __getitem__(self, idx)
    329     def __getitem__(self, idx):
--> 330         return self.dataset[self.indices[idx]]
    332     def __len__(self):
<ipython-input-3-73612deaccc4> in __getitem__(self, idx)
     63         if self.transforms is not None:
---> 64             img, target = self.transforms(img, target)
     66         return img, target
/content/transforms.py in __call__(self, image, target)
     24     def __call__(self, image, target):
     25         for t in self.transforms:
---> 26             image, target = t(image, target)
     27         return image, target
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    887             result = self._slow_forward(*input, **kwargs)
    888         else:
--> 889             result = self.forward(*input, **kwargs)
    890         for hook in itertools.chain(
    891                 _global_forward_hooks.values(),
<ipython-input-16-75a1255e5fcd> in forward(self, image, target)
     11             image = F.hflip(image)
     12             if target is not None:
---> 13                 width, _ = F.get_image_size(image)
     14                 target["boxes"][:, [0, 2]] = width - target["boxes"][:, [2, 0]]
     15                 if "masks" in target:
AttributeError: module 'torchvision.transforms.functional' has no attribute 'get_image_size'
          
The reason why you get issues is because you are trying to use code from the latest development branch with an old stable version of TorchVision. When you mix code from different versions you can get issues. As I explained earlier, the PR #4321 which renamed the private method F._get_image_size() to F.get_image_size() was merged yesterday and thus this change is only available to the latest nightly version or if you install TorchVision from source.
You are currently trying to call a method that does not exist on the TorchVision version you are using. A quick workaround is to replace get_image_size with _get_image_size in your code but you are still at risk because you mix code from different versions. If you want to stick to the latest stable version (0.10.0) you should be using the reference scripts from that version.
I believe this answers your question and thus I'll close the ticket. If you have further concerns feel free to reopen it.
      
Private function _get_image_size was changed to public in torchvision v0.11.
The use of torchvision v0.11 and above will result in the following error:
pytorch/vision#4328