spacr.mediar

Module Contents

spacr.mediar.mediar_path[source]
spacr.mediar.init_file[source]
spacr.mediar.display_imgs_in_list(lists_of_imgs, cmaps=None)[source]

Displays images from multiple lists side by side. Each row will display one image from each list (lists_of_imgs[i][j] is the j-th image in the i-th list).

Parameters:
  • lists_of_imgs – A list of lists, where each inner list contains images.

  • cmaps – List of colormaps to use for each list (optional). If not provided, defaults to ‘gray’ for all lists.

spacr.mediar.get_weights(finetuned_weights=False)[source]
spacr.mediar.normalize_image(image, lower_percentile=0.0, upper_percentile=99.5)[source]

Normalize an image based on the 0.0 and 99.5 percentiles.

Parameters:
  • image – Input image (numpy array).

  • lower_percentile – Lower percentile (default is 0.0).

  • upper_percentile – Upper percentile (default is 99.5).

Returns:

Normalized image (numpy array).

class spacr.mediar.MEDIARPredictor(input_path=None, output_path=None, device=None, model='ensemble', roi_size=512, overlap=0.6, finetuned_weights=False, test=False, use_tta=False, normalize=True, quantiles=[0.0, 99.5])[source]
device = None[source]
test = False[source]
model = 'ensemble'[source]
normalize = True[source]
quantiles = [0.0, 99.5][source]
model1[source]
model2[source]
load_model(model_path, device)[source]
display_image_and_mask(img, mask)[source]
predict_batch(imgs)[source]

Predict masks for a batch of images.

Parameters:

imgs – List of input images as NumPy arrays (each in (H, W, C) format).

Returns:

List of predicted masks as NumPy arrays.

run_test()[source]

Run the model on test images if the test flag is True.

preprocess_image(img)[source]

Preprocess input image (numpy array) for compatibility with the model.