Do we need to normalize single image before running predict function on it?

#1

Just completed the first lesson and went through the forum to figure out how to call predict on a single image.

After reading through a few different forum posts, my takeaway is that I need to run the following code:

learn.load('stage-1');
img = open_image('sample-image.jpg')
learn.predict(img)

Do I need to “normalize” the sample-image.jpg and also resize it to 224?

Other people have run this code without normalizing but resizing. I am confused because I think since the model was trained on normalized images, the new test image should also be normalized.

Thanks for the help.

1 Like

(Yann) #2

I’m also interested in this. I’m seeing a lot of people especially in Keras/TensorFlow/Pytorch projects doing some data augmentation or pre-processing stuff before sending images to their pre-trained model in production. FastAI does that automatically when using load_learner and predict?

I tried different approaches, resize manually to 224 (same size as my training set), different resize_method, but I struggle to find the good approach, results differ a lot. I couldn’t find a way to normalize (if necessary) my single image to imagenet_stats before submitting it to my model.

0 Likes

#3

Also interested, tungsten’s hypothesis seems to make sense.

0 Likes

(Natalija Lace) #4

Not sure about normalization (curious to know too) but in my experiments I found that you do need to resize image you use for prediction, so it is the same size as your training/validation set.

0 Likes

(Stefano Giomo) #5

TL; DR: You don’t need to normalize your input because fast.ai do it for you.

When you call Databunch.normalize(norm_params)

    def normalize(self, stats:Collection[Tensor]=None, do_x:bool=True, do_y:bool=False)->None:
        "Add normalize transform using `stats` (defaults to `DataBunch.batch_stats`)"
        if getattr(self,'norm',False): raise Exception('Can not call normalize twice')
        if stats is None: self.stats = self.batch_stats()
        else:             self.stats = stats
        self.norm,self.denorm = normalize_funcs(*self.stats, do_x=do_x, do_y=do_y)
        self.add_tfm(self.norm)
        return self

This row self.add_tfm(self.norm), add the normalization transform.
So nay time you get an image from the batch it’s normalized.

If you try to use your model (remember that under the hood is a standard pytorch model) without fast.ai, you need to normalize your input manually (and probably reshape it to"size").

NOTE ON TFMS ORDER: the order of transforms is determined by the ‘order’ property, not only the order of original array - ie: resize is always the last one.

0 Likes

How change layers pre-trained model wihout using Learner
(Yann) #6

What kind of resize_methods are you using? crop, pad, squish? Squish seems to give good results to me, but I’m not sure if it’s the correct way to do.

img = img.apply_tfms(tfms=get_transforms()[1], size=224, resize_method=3)
0 Likes

(Natalija Lace) #7

Since I am dealing with spectrogram images (visual representation of sound) I cannot do any transforms that could distort time/frequency representation (like squish). So I do it old fashion way, just resizing images outside the model, while keeping the proportion of my original image size. I also deal with rectangular images, so when I resize I try to keep the 1.36 proportion.

I think you can also resize proportionally with tfms but I do not know how, so I just resize images outside of the model, basically preparing them for the test set.

If someone knows easy resize tfms transform that basically makes image smaller while keeping proportions, I would love to learn it too.

0 Likes