|
import numpy as np |
|
import cv2 |
|
import albumentations as A |
|
from utils import * |
|
import random |
|
from albumentations.pytorch import ToTensorV2 |
|
from yolov3 import YOLOV3_PL |
|
from pytorch_grad_cam.utils.image import show_cam_on_image |
|
from utils import YoloCAM, cells_to_bboxes, non_max_suppression |
|
from model import YOLOv3 |
|
|
|
def inference(image: np.ndarray, iou_thresh: float = 0.5, thresh: float = 0.5,show_cam: bool = False, transparency: float = 0.5): |
|
model = YOLOV3_PL() |
|
model.load_state_dict(torch.load("model.pth", map_location=torch.device('cpu')), strict=False) |
|
|
|
|
|
scaled_anchors = config.SCALED_ANCHORS |
|
|
|
backbone = model |
|
target_layer_list = list(backbone.children())[-2] |
|
|
|
cam = YoloCAM(model=model, target_layers = target_layer_list, use_cuda=False) |
|
transforms = A.Compose( |
|
[ |
|
A.LongestMaxSize(max_size=config.IMAGE_SIZE), |
|
A.PadIfNeeded( |
|
min_height=config.IMAGE_SIZE, min_width=config.IMAGE_SIZE, border_mode=cv2.BORDER_CONSTANT |
|
), |
|
A.Normalize(mean=[0, 0, 0], std=[1, 1, 1], max_pixel_value=255,), |
|
ToTensorV2(), |
|
], |
|
) |
|
with torch.no_grad(): |
|
transformed_image = transforms(image=image)["image"].unsqueeze(0) |
|
output = model(transformed_image) |
|
|
|
bboxes = [[] for _ in range(1)] |
|
for i in range(3): |
|
batch_size, A1, S, _, _ = output[i].shape |
|
anchor = scaled_anchors[i].to('cpu') |
|
boxes_scale_i = cells_to_bboxes( |
|
output[i].to('cpu'), anchor, S=S, is_preds=True |
|
) |
|
for idx, (box) in enumerate(boxes_scale_i): |
|
bboxes[idx] += box |
|
|
|
nms_boxes = non_max_suppression( |
|
bboxes[0], iou_threshold=iou_thresh, threshold=thresh, box_format="midpoint", |
|
) |
|
plot_img = draw_predictions(image, nms_boxes, class_labels=config.PASCAL_CLASSES) |
|
if not show_cam: |
|
return [plot_img] |
|
|
|
grayscale_cam = cam(transformed_image, scaled_anchors)[0, :, :] |
|
img = cv2.resize(image, (416, 416)) |
|
img = np.float32(img) / 255 |
|
cam_image = show_cam_on_image(img, grayscale_cam, use_rgb=True, image_weight=transparency) |
|
return [plot_img, cam_image] |
|
|
|
|
|
|
|
|
|
def draw_predictions(image: np.ndarray, boxes: list[list], class_labels: list[str]) -> np.ndarray: |
|
"""Plots predicted bounding boxes on the image""" |
|
|
|
colors = [[random.randint(0, 255) for _ in range(3)] for name in class_labels] |
|
|
|
im = np.array(image) |
|
height, width, _ = im.shape |
|
bbox_thick = int((height + width) /500) |
|
|
|
|
|
for box in boxes: |
|
assert len(box) == 6, "box should contain class pred, confidence, x, y, width, height" |
|
class_pred = box[0] |
|
conf = box[1] |
|
box = box[2:] |
|
upper_left_x = box[0] - box[2] / 2 |
|
upper_left_y = box[1] - box[3] / 2 |
|
|
|
x1 = int(upper_left_x * width) |
|
y1 = int(upper_left_y * height) |
|
|
|
x2 = x1 + int(box[2] * width) |
|
y2 = y1 + int(box[3] * height) |
|
|
|
cv2.rectangle( |
|
image, |
|
(x1, y1), (x2, y2), |
|
color=colors[int(class_pred)], |
|
thickness=bbox_thick |
|
) |
|
text = f"{class_labels[int(class_pred)]}: {conf:.2f}" |
|
t_size = cv2.getTextSize(text, 0, 0.7, thickness=bbox_thick // 2)[0] |
|
c3 = (x1 + t_size[0], y1 - t_size[1] - 3) |
|
|
|
cv2.rectangle(image, (x1, y1), c3, colors[int(class_pred)], -1) |
|
cv2.putText( |
|
image, |
|
text, |
|
(x1, y1 - 2), |
|
cv2.FONT_HERSHEY_SIMPLEX, |
|
0.7, |
|
(0, 0, 0), |
|
bbox_thick // 2, |
|
lineType=cv2.LINE_AA, |
|
) |
|
|
|
return image |
