[PyTorch] output with shape [1, 28, 28] doesn’t match the broadcast shape [3, 28, 28]

會產生這一個錯誤，原因是圖片的格式造成，是彩色還是灰階（黑白）圖片。

Let me clarify, if the img has three channels, you should have three number for mean, for example, img is RGB, mean is [0.5, 0.5, 0.5], the normalize result is R * 0.5, G * 0.5, B * 0.5. If img is grey type that only one channel, so mean should be [0.5], the normalize result is R * 0.5

資料來源：
https://github.com/yunjey/pytorch-tutorial/issues/161

解法很多，需要配合程式變成彩色，或修改程式的流程。如果是在python 裡使用 PIL 讀取圖片，轉換方式如下：

img = Image.open(GIF_FILENAME)
rgbimg = Image.new("RGBA", img.size)
rgbimg.paste(img)
rgbimg.save('foo.jpg')