def __getitem__(self, idx: int) -> Dict[str, Any]:
image_path = self.file_names[idx]
image = load_rgb(image_path)
height, width = image.shape[:2]
# Resize
resizer = albu.Compose([albu.LongestMaxSize(max_size=768, p=1)], p=1)
image = resizer(image=image)["image"]
# pad
image, pads = pad(image, factor=768)
# apply augmentations
image = self.transform(image=image)["image"]
return {
"image_id": image_path.stem,
"features": tensor_from_rgb_image(image),
"pads": np.array(pads).T,
"height": height,
"width": width,
}
[albu.LongestMaxSize(max_size=MAX_SIZE), albu.Normalize(p=1)], p=1
)
st.title("Segment glomeruli")
# What about a TIFF image?
uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "png"])
if uploaded_file is not None:
original_image = np.array(Image.open(uploaded_file))
st.image(original_image, caption="Before", use_column_width=True)
st.write("")
st.write("Detecting glomeruli...")
original_height, original_width = original_image.shape[:2]
image = transform(image=original_image)["image"]
padded_image, pads = pad(image, factor=MAX_SIZE, border=cv2.BORDER_CONSTANT)
x = torch.unsqueeze(tensor_from_rgb_image(padded_image), 0)
with torch.no_grad():
prediction = model(x)[0][0]
mask = (prediction > 0).cpu().numpy().astype(np.uint8)
mask = unpad(mask, pads)
mask = cv2.resize(
mask, (original_width, original_height), interpolation=cv2.INTER_NEAREST
)
mask_3_channels = cv2.cvtColor(mask, cv2.COLOR_GRAY2RGB)
dst = cv2.addWeighted(
original_image, 1, (mask_3_channels * (0, 255, 0)).astype(np.uint8), 0.5, 0
)
def test_pad_grayscale(input_array, factor):
padded_array, pads = pad(input_array, factor)
unpadded_array = unpad(padded_array, pads)
assert np.array_equal(input_array, unpadded_array)
from iglovikov_helper_functions.utils.image_utils import load_rgb, pad, unpad
from iglovikov_helper_functions.dl.pytorch.utils import tensor_from_rgb_image
from midv500models.pre_trained_models import create_model
start = timeit.default_timer()
model = create_model('Unet_resnet34_2020-05-19')
model.eval()
image = load_rgb(sys.argv[1])
# im = Image.fromarray(image)
# im.save()
transform = albu.Compose([albu.Normalize(p=1)], p=1)
padded_image, pads = pad(image, factor=32, border=cv2.BORDER_CONSTANT)
x = transform(image=padded_image)['image']
x = torch.unsqueeze(tensor_from_rgb_image(x), 0)
with torch.no_grad():
prediction = model(x)[0][0]
mask = (prediction > 0).cpu().numpy().astype(np.uint8)
mask = unpad(mask, pads)
# im = Image.fromarray(mask)
# im.save()
dst = cv2.addWeighted(image, 1, (cv2.cvtColor(mask, cv2.COLOR_GRAY2RGB) *
(0, 255, 0)).astype(np.uint8), 0.5, 0)
# im = Image.fromarray(dst)
# im.save()