File size: 3,723 Bytes
2a4462d 0869998 7b271ac 3cf5303 e80b224 2a4462d 2e620cf 0869998 f0b653f 7b3d454 18ff9ad ba0213c 18ff9ad 2a4462d 7b271ac 165b257 2a4462d 5fd0532 2a4462d 5fd0532 2a4462d 5fd0532 2a4462d |
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 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 |
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() #YOLOv3(num_classes=20)
model.load_state_dict(torch.load("model.pth", map_location=torch.device('cpu')), strict=False)
# iou_thresh = 0.75
# thresh = 0.75
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)
# Create a Rectangle patch
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 |