Training with Grey images dataset

[Genius-farmer]

These are the steps that I have followed so far for my grey scale dataset.

Step 1

> class DetectorConfig(Config):
>     """Configuration for training pneumonia detection on the RSNA pneumonia dataset.
>     Overrides values in the base Config class https://github.com/matterport/Mask_RCNN/blob/master/mrcnn/config.py.
>     """
>     IMAGE_CHANNEL_COUNT = 1
>     MEAN_PIXEL = [123.7] # this value is the one that I chose

Step 2

> def load_image(self, image_id):
>         # Load image
>         image = skimage.io.imread(self.image_info[image_id]['path'])
>         # Convert to grayscale for consistency.
>         if image.ndim != 1:
>             image = skimage.color.gray2rgb(image) #Instead of rgb2gray(image)
> 
>         # Extending the size of the image to be (h,w,1)
>         image = image[..., np.newaxis]
>         return image```

Alternate Step 2

>     def load_image(self, image_id):
>         """Load the specified image and return a [H,W,3] Numpy array.
>         """
>         # Load image
>         image = skimage.io.imread(self.image_info[image_id]['path'])         
>         image = image[..., np.newaxis] # Extending the size of the image to be (h,w,1)
>         return image

Step 3

> model.load_weights(COCO_MODEL_PATH, by_name=True,
>                         exclude=["mrcnn_class_logits", "mrcnn_bbox_fc", 
>                                  "mrcnn_bbox", "mrcnn_mask", "conv1"])

Step 4

>  layer_regex = {
>             # all layers but the backbone
>             "heads": r"(conv1\_.*)|(mrcnn\_.*)|(rpn\_.*)|(fpn\_.*)",
> 

> def load_image(self, image_id):
>      image = image[..., np.newaxis]

Step 5

> def resize_image(image, min_dim=None, max_dim=None, min_scale=None, mode="square"):
> padding = [(top_pad, bottom_pad), (left_pad, right_pad)]
> image = np.pad(image, padding, mode='constant', constant_values=0)
> 

Step 6

> > if len(image.shape) != 3 or image.shape[2] != 3:
>         image = np.squeeze(image, axis = -1)
>         image = np.stack((image,) * 3, -1)

When I run this code, I faced this issue from train(model)

ValueError: len(output_shape) cannot be smaller than the image dimensions

The issue is different if I used "rgb2gray(image)" instead at Step 2

ValueError: operands could not be broadcast together with remapped shapes [original->remapped]: (2,2) and requested shape (3,2)

Alternate step 2

ValueError: operands could not be broadcast together with remapped shapes [original->remapped]: (2,2) and requested shape (3,2)

Please provide some assistance.

[Genius-farmer]

Just did this on utils

>     def load_image(self, image_id):
>         """Load the specified image and return a [H,W,3] Numpy array.
>         # Load image
>         image = cv2.imread(self.image_info[image_id]['path'])         
>         image = image[..., np.newaxis] # Extending the size of the image to be (h,w,1)
>         return image

Result

ValueError: len(output_shape) cannot be smaller than the image dimensions

Dataset images are of all same dimensions.

[Genius-farmer]

~\AppData\Roaming\Python\Python36\site-packages\skimage\transform\_warps.py in resize(image, output_shape, order, mode, cval, clip, preserve_range, anti_aliasing, anti_aliasing_sigma)
     98         output_shape = output_shape + (image.shape[-1], )
     99     elif output_ndim < image.ndim - 1:
--> 100         raise ValueError("len(output_shape) cannot be smaller than the image "
    101                          "dimensions")
    102

ValueError: len(output_shape) cannot be smaller than the image dimensions

I had tried to trace and the error comes out from _warps.py file. Is there a need to edit this file?

[Arthod]

I receive same error as you did above How did you solve it? If you did

ValueError: operands could not be broadcast together with remapped shapes [original->remapped]: (3,2) and requested shape (2,2)

[elmahib]

Hi, I've followed all the steps but I still get an error at the beginning of my training (Error when checking input: expected input_image to have shape (None, None, 1) but got array with shape (404, 404, 3)) and I don't see why i get it.

[avinash-218]

Getting this same error

ValueError: len(output_shape) cannot be smaller than the image dimensions

Anyone solved this??