"transforms" helper function has no attribute ToTensor

InnovArul · June 13, 2022, 1:44pm

I think that the tutorial was written based on an old version (v0.8.2) of Torchvision source code.
You can see ToTensor() method in the file:

github.com

pytorch/vision/blob/v0.8.2/references/detection/transforms.py

import random
import torch

from torchvision.transforms import functional as F


def _flip_coco_person_keypoints(kps, width):
    flip_inds = [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
    flipped_data = kps[:, flip_inds]
    flipped_data[..., 0] = width - flipped_data[..., 0]
    # Maintain COCO convention that if visibility == 0, then x, y = 0
    inds = flipped_data[..., 2] == 0
    flipped_data[inds] = 0
    return flipped_data


class Compose(object):
    def __init__(self, transforms):
        self.transforms = transforms

This file has been truncated. show original

Further, if you look at the Google Colab file, you can notice that somewhere down the line, they checkout a specific Github tag (v0.8.2) before executing the code.

# Download TorchVision repo to use some files from
# references/detection
git clone https://github.com/pytorch/vision.git
cd vision
git checkout v0.8.2

cp references/detection/utils.py ../
cp references/detection/transforms.py ../
cp references/detection/coco_eval.py ../
cp references/detection/engine.py ../
cp references/detection/coco_utils.py ../