Spaces:
Runtime error
Runtime error
File size: 2,352 Bytes
3533c69 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 |
import cv2
import numpy as np
import torch
from torchvision.transforms import Compose, Normalize, ToTensor
def preprocess_image(img: np.ndarray, mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]) -> torch.Tensor:
preprocessing = Compose([
ToTensor(),
Normalize(mean=mean, std=std)
])
return preprocessing(img.copy()).unsqueeze(0)
def deprocess_image(img):
""" see https://github.com/jacobgil/keras-grad-cam/blob/master/grad-cam.py#L65 """
img = img - np.mean(img)
img = img / (np.std(img) + 1e-5)
img = img * 0.1
img = img + 0.5
img = np.clip(img, 0, 1)
return np.uint8(img * 255)
def show_cam_on_image(img: np.ndarray,
mask: np.ndarray,
use_rgb: bool = False,
colormap: int = cv2.COLORMAP_JET) -> np.ndarray:
""" This function overlays the cam mask on the image as an heatmap.
By default the heatmap is in BGR format.
:param img: The base image in RGB or BGR format.
:param mask: The cam mask.
:param use_rgb: Whether to use an RGB or BGR heatmap, this should be set to True if 'img' is in RGB format.
:param colormap: The OpenCV colormap to be used.
:returns: The default image with the cam overlay.
"""
heatmap = cv2.applyColorMap(np.uint8(255 * mask), colormap)
if use_rgb:
heatmap = cv2.cvtColor(heatmap, cv2.COLOR_BGR2RGB)
heatmap = np.float32(heatmap) / 255
if np.max(img) > 1:
raise Exception(
"The input image should np.float32 in the range [0, 1]")
cam = heatmap + img
cam = cam / np.max(cam)
return np.uint8(255 * cam)
def scale_cam_image(cam, target_size=None):
result = []
for img in cam:
img = img - np.min(img)
img = img / (1e-7 + np.max(img))
if target_size is not None:
img = cv2.resize(img, target_size)
result.append(img)
result = np.float32(result)
return result
def scale_accross_batch_and_channels(tensor, target_size):
batch_size, channel_size = tensor.shape[:2]
reshaped_tensor = tensor.reshape(
batch_size * channel_size, *tensor.shape[2:])
result = scale_cam_image(reshaped_tensor, target_size)
result = result.reshape(
batch_size,
channel_size,
target_size[1],
target_size[0])
return result
|