YoloX implementation #39
Description
Hi,
this is a great library.
I need to implement inference for YoloX model but I'm having some trouble.
This is python script that I use:
import os
import cv2
import numpy as np
import onnxruntime
import os
import cv2
import numpy as np
import onnxruntime
# Constants
INPUT_SHAPE = (640, 640) # Adjust this if needed
NMS_THRESHOLD = 0.45
SCORE_THRESHOLD = 0.4
# Replace COCO_CLASSES with your class names
CLASS_NAMES = []
_COLORS = np.array(
[
0.000, 0.447, 0.741,
0.850, 0.325, 0.098,
0.929, 0.694, 0.125,
0.494, 0.184, 0.556,
0.466, 0.674, 0.188,
0.301, 0.745, 0.933,
0.635, 0.078, 0.184,
0.300, 0.300, 0.300,
0.600, 0.600, 0.600,
1.000, 0.000, 0.000,
1.000, 0.500, 0.000,
0.749, 0.749, 0.000,
0.000, 1.000, 0.000,
0.000, 0.000, 1.000,
0.667, 0.000, 1.000,
0.333, 0.333, 0.000,
0.333, 0.667, 0.000,
0.333, 1.000, 0.000,
0.667, 0.333, 0.000,
0.667, 0.667, 0.000,
0.667, 1.000, 0.000,
1.000, 0.333, 0.000,
1.000, 0.667, 0.000,
1.000, 1.000, 0.000,
0.000, 0.333, 0.500,
0.000, 0.667, 0.500,
0.000, 1.000, 0.500,
0.333, 0.000, 0.500,
0.333, 0.333, 0.500,
0.333, 0.667, 0.500,
0.333, 1.000, 0.500,
0.667, 0.000, 0.500,
0.667, 0.333, 0.500,
0.667, 0.667, 0.500,
0.667, 1.000, 0.500,
1.000, 0.000, 0.500,
1.000, 0.333, 0.500,
1.000, 0.667, 0.500,
1.000, 1.000, 0.500,
0.000, 0.333, 1.000,
0.000, 0.667, 1.000,
0.000, 1.000, 1.000,
0.333, 0.000, 1.000,
0.333, 0.333, 1.000,
0.333, 0.667, 1.000,
0.333, 1.000, 1.000,
0.667, 0.000, 1.000,
0.667, 0.333, 1.000,
0.667, 0.667, 1.000,
0.667, 1.000, 1.000,
1.000, 0.000, 1.000,
1.000, 0.333, 1.000,
1.000, 0.667, 1.000,
0.333, 0.000, 0.000,
0.500, 0.000, 0.000,
0.667, 0.000, 0.000,
0.833, 0.000, 0.000,
1.000, 0.000, 0.000,
0.000, 0.167, 0.000,
0.000, 0.333, 0.000,
0.000, 0.500, 0.000,
0.000, 0.667, 0.000,
0.000, 0.833, 0.000,
0.000, 1.000, 0.000,
0.000, 0.000, 0.167,
0.000, 0.000, 0.333,
0.000, 0.000, 0.500,
0.000, 0.000, 0.667,
0.000, 0.000, 0.833,
0.000, 0.000, 1.000,
0.000, 0.000, 0.000,
0.143, 0.143, 0.143,
0.286, 0.286, 0.286,
0.429, 0.429, 0.429,
0.571, 0.571, 0.571,
0.714, 0.714, 0.714,
0.857, 0.857, 0.857,
0.000, 0.447, 0.741,
0.314, 0.717, 0.741,
0.50, 0.5, 0
]
).astype(np.float32).reshape(-1, 3)
def preprocess(img, input_size, swap=(2, 0, 1)):
if len(img.shape) == 3:
padded_img = np.ones((input_size[0], input_size[1], 3), dtype=np.uint8) * 114
else:
padded_img = np.ones(input_size, dtype=np.uint8) * 114
r = min(input_size[0] / img.shape[0], input_size[1] / img.shape[1])
resized_img = cv2.resize(
img,
(int(img.shape[1] * r), int(img.shape[0] * r)),
interpolation=cv2.INTER_LINEAR,
).astype(np.uint8)
padded_img[: int(img.shape[0] * r), : int(img.shape[1] * r)] = resized_img
padded_img = padded_img.transpose(swap)
padded_img = np.ascontiguousarray(padded_img, dtype=np.float32)
return padded_img, r
def demo_postprocess(outputs, img_size, p6=False):
grids = []
expanded_strides = []
strides = [8, 16, 32] if not p6 else [8, 16, 32, 64]
hsizes = [img_size[0] // stride for stride in strides]
wsizes = [img_size[1] // stride for stride in strides]
for hsize, wsize, stride in zip(hsizes, wsizes, strides):
xv, yv = np.meshgrid(np.arange(wsize), np.arange(hsize))
grid = np.stack((xv, yv), 2).reshape(1, -1, 2)
grids.append(grid)
shape = grid.shape[:2]
expanded_strides.append(np.full((*shape, 1), stride))
grids = np.concatenate(grids, 1)
expanded_strides = np.concatenate(expanded_strides, 1)
outputs[..., :2] = (outputs[..., :2] + grids) * expanded_strides
outputs[..., 2:4] = np.exp(outputs[..., 2:4]) * expanded_strides
return outputs
def nms(boxes, scores, nms_thr):
x1 = boxes[:, 0]
y1 = boxes[:, 1]
x2 = boxes[:, 2]
y2 = boxes[:, 3]
areas = (x2 - x1 + 1) * (y2 - y1 + 1)
order = scores.argsort()[::-1]
keep = []
while order.size > 0:
i = order[0]
keep.append(i)
xx1 = np.maximum(x1[i], x1[order[1:]])
yy1 = np.maximum(y1[i], y1[order[1:]])
xx2 = np.minimum(x2[i], x2[order[1:]])
yy2 = np.minimum(y2[i], y2[order[1:]])
w = np.maximum(0.0, xx2 - xx1 + 1)
h = np.maximum(0.0, yy2 - yy1 + 1)
inter = w * h
ovr = inter / (areas[i] + areas[order[1:]] - inter)
inds = np.where(ovr <= nms_thr)[0]
order = order[inds + 1]
return keep
def multiclass_nms(boxes, scores, nms_thr, score_thr, class_agnostic=True):
if class_agnostic:
return multiclass_nms_class_agnostic(boxes, scores, nms_thr, score_thr)
# else:
# return multiclass_nms_class_aware(boxes, scores, nms_thr, score_thr)
def multiclass_nms_class_agnostic(boxes, scores, nms_thr, score_thr):
cls_inds = scores.argmax(1)
cls_scores = scores[np.arange(len(cls_inds)), cls_inds]
valid_score_mask = cls_scores > score_thr
if valid_score_mask.sum() == 0:
return None
valid_scores = cls_scores[valid_score_mask]
valid_boxes = boxes[valid_score_mask]
valid_cls_inds = cls_inds[valid_score_mask]
keep = nms(valid_boxes, valid_scores, nms_thr)
if keep:
return np.concatenate(
[valid_boxes[keep], valid_scores[keep, None], valid_cls_inds[keep, None]], 1
)
return None
def vis(img, boxes, scores, cls_ids, conf=0.5, class_names=None):
for i in range(len(boxes)):
box = boxes[i]
cls_id = int(cls_ids[i])
score = scores[i]
if score < conf:
continue
x0 = int(box[0])
y0 = int(box[1])
x1 = int(box[2])
y1 = int(box[3])
color = (_COLORS[cls_id] * 255).astype(np.uint8).tolist()
text = '{}:{:.1f}%'.format(class_names[cls_id], score * 100)
txt_color = (0, 0, 0) if np.mean(_COLORS[cls_id]) > 0.5 else (255, 255, 255)
font = cv2.FONT_HERSHEY_SIMPLEX
txt_size = cv2.getTextSize(text, font, 0.4, 1)[0]
cv2.rectangle(img, (x0, y0), (x1, y1), color, 2)
txt_bk_color = (_COLORS[cls_id] * 255 * 0.7).astype(np.uint8).tolist()
cv2.rectangle(
img,
(x0, y0 + 1),
(x0 + txt_size[0] + 1, y0 + int(1.5 * txt_size[1])),
txt_bk_color,
-1
)
cv2.putText(img, text, (x0, y0 + txt_size[1]), font, 0.4, txt_color, thickness=1)
return img
def mkdir(path):
if not os.path.exists(path):
os.makedirs(path)
def process_images(input_dir, output_dir, model_path):
mkdir(output_dir)
session = onnxruntime.InferenceSession(model_path)
for img_file in os.listdir(input_dir):
if img_file.lower().endswith(('.jpg', '.png', '.jpeg')):
img_path = os.path.join(input_dir, img_file)
origin_img = cv2.imread(img_path)
img, ratio = preprocess(origin_img, INPUT_SHAPE)
ort_inputs = {session.get_inputs()[0].name: img[None, :, :, :]}
output = session.run(None, ort_inputs)
predictions = demo_postprocess(output[0], INPUT_SHAPE)[0]
boxes = predictions[:, :4]
scores = predictions[:, 4:5] * predictions[:, 5:]
boxes_xyxy = np.ones_like(boxes)
boxes_xyxy[:, 0] = boxes[:, 0] - boxes[:, 2] / 2.
boxes_xyxy[:, 1] = boxes[:, 1] - boxes[:, 3] / 2.
boxes_xyxy[:, 2] = boxes[:, 0] + boxes[:, 2] / 2.
boxes_xyxy[:, 3] = boxes[:, 1] + boxes[:, 3] / 2.
boxes_xyxy /= ratio
dets = multiclass_nms(boxes_xyxy, scores, nms_thr=NMS_THRESHOLD, score_thr=SCORE_THRESHOLD)
if dets is not None:
final_boxes, final_scores, final_cls_inds = dets[:, :4], dets[:, 4], dets[:, 5]
origin_img = vis(origin_img, final_boxes, final_scores, final_cls_inds,
conf=SCORE_THRESHOLD, class_names=CLASS_NAMES)
output_path = os.path.join(output_dir, img_file)
cv2.imwrite(output_path, origin_img)
print(f"Saved result to {output_path}")
if __name__ == "__main__":
input_dir = './new-dataset/temp'
output_dir = './new-dataset/temp/output_folder_latest14'
model_path = "./model/model_yolox.onnx"
process_images(input_dir, output_dir, model_path)
I don't know how to convert in C#.
Any help?