img should be PIL Image. Got <class 'torch.Tensor'>

Just add transforms.ToPILImage() to convert into pil image and then it will work, example:

transform = transforms.Compose([
    transforms.ToPILImage(),
    transforms.Resize(255),
    transforms.CenterCrop(224),
    transforms.ToTensor(),
    transforms.RandomHorizontalFlip(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

transforms.RandomHorizontalFlip() works on PIL.Images, not torch.Tensor. In your code above, you are applying transforms.ToTensor() prior to transforms.RandomHorizontalFlip(), which results in tensor.

But, as per the official pytorch documentation here,

transforms.RandomHorizontalFlip() horizontally flip the given PIL Image randomly with a given probability.

So, just change the order of your transformation in above code, like below:

train_transforms = transforms.Compose([transforms.Resize(255), 
                                       transforms.CenterCrop(224),  
                                       transforms.RandomHorizontalFlip(),
                                       transforms.ToTensor(), 
                                       transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])