1

I am solving a Multiview Classification problem using VGG16 pretrained model. In my case, I have 4 views that are my inputs and they are of size (64,64,3). But VGG16 uses input size of (224,224,3).

Now for solving the problem, I am supposed to create my own data loader instead of using quick built-in methods like keras load_img() or openCV imread(). So I am doing all this with plain numpy arrays.

I am trying to resize the shape of my input from 64x64 to 224X224. But I am unable to do it, it keeps throwing one error or another. This is my code for data loader:

def data_loader(dataframe, classDict, basePath, batch_size=16): 

  while True:

    x_batch = np.zeros((batch_size, 4, 64, 64, 3))    #Create a zeros array for images
    y_batch = np.zeros((batch_size, 20))              #Create a zeros array for classes
    
    for i in range(0, batch_size):
      rndNumber = np.random.randint(len(dataframe))        
      *images, class_id = dataframe.iloc[rndNumber]
                              
      for j in range(4):
        x_batch[i,j] = plt.imread(os.path.join(basePath, images[j])) / 255.     
        # x_batch[i,j] = x_batch[i,j].resize(1, 224, 224, 3)   #<--- Try(1)
        
      class_id = classDict[class_id]
      y_batch[i, class_id] = 1.0                             
    
    # yield {'image1': np.resize(x_batch[:, 0],(batch_size, 224, 224, 3)), #<--- Try(2)
    #       'image2': np.resize(x_batch[:, 1],(1, 224, 224, 3)), 
    #       'image3': np.resize(x_batch[:, 2],(1, 224, 224, 3)), 
    #       'image4': np.resize(x_batch[:, 3],(1, 224, 224, 3)) }, {'class_out': y_batch}                   #'yield' is a keyword that is used like return, except the function will return a generator"

    yield {'image1': x_batch[:, 0], 
          'image2': x_batch[:, 1], 
          'image3': x_batch[:, 2], 
          'image4': x_batch[:, 3], }, {'class_out': y_batch}

## Testing the data loader
example, lbl= next(data_loader(df_train, classDictTrain, basePath))
print(example['image1'].shape)  #example['image1'][0].shape
print(lbl['class_out'].shape)

I have made several attempts to resizing the images. I am listing them below with error messages I am receiving with each TRY:

  • Try(1) : Using x_batch[i,j] = x_batch[i,j].resize(1, 224, 224, 3) >> Error: ValueError: cannot resize this array: it does not own its data

  • Try(2) : Using yield {'image1': np.resize(x_batch[:, 0],(batch_size, 224, 224, 3)), ....... } >> The output shape is (16, 224, 224, 3) which seems fine but when I plot this, the resultant is an image like this enter image description here

where I need original image just bigger in size like this enter image description here

Please tell me what am I doing wrong and how can I fix it?

stackersTech101
  • 57
  • 8

1 Answers1

1

If I understand your problem correctly, you have an image which is 64x64, and you want to upscale it to a resolution of 224x224. Notice that the latter resolution contains many more pixels and you cannot simply force a reshape, because the original image has way less pixel.

You have to upsample the image, generating the missing pixels. A tool you can try is PIL Resize function which can be used with different resampling filters.

As far as I know, numpy does not easily support upscaling filters. Check out this post to understand how to convert a PIL image to a numpy array and you are ready to go.

Federico Di Cesare
  • 98
  • 7
  • Yes I have been able to convert it to numpy array.. however, I still cannot understand how to reshape my image. The resampling PIL is suggesting is not what I need. Can you guide me more on how can I now change the shape of array? – stackersTech101 Aug 23 '22 at 14:53
  • 1
    I think you can open the image with PIL, resize it with the function Image.resize, then convert it to a numpy array as suggested in the linked post. – Federico Di Cesare Aug 23 '22 at 16:12
  • Okay thankyou this worked for me. And If you find this question helpful for the community please upvote it as well – stackersTech101 Aug 23 '22 at 16:53