144 lines
4.7 KiB
Python
144 lines
4.7 KiB
Python
import os
|
|
import sys
|
|
import onnx
|
|
import torch
|
|
import torch.nn as nn
|
|
from copy import deepcopy
|
|
|
|
import ultralytics.utils
|
|
import ultralytics.models.yolo
|
|
import ultralytics.utils.tal as _m
|
|
|
|
sys.modules['ultralytics.yolo'] = ultralytics.models.yolo
|
|
sys.modules['ultralytics.yolo.utils'] = ultralytics.utils
|
|
|
|
|
|
def _dist2bbox(distance, anchor_points, xywh=False, dim=-1):
|
|
lt, rb = distance.chunk(2, dim)
|
|
x1y1 = anchor_points - lt
|
|
x2y2 = anchor_points + rb
|
|
return torch.cat((x1y1, x2y2), dim)
|
|
|
|
|
|
_m.dist2bbox.__code__ = _dist2bbox.__code__
|
|
|
|
|
|
class DeepStreamOutput(nn.Module):
|
|
def __init__(self):
|
|
super().__init__()
|
|
|
|
def forward(self, x):
|
|
x = x.transpose(1, 2)
|
|
boxes = x[:, :, :4]
|
|
scores, labels = torch.max(x[:, :, 4:], dim=-1, keepdim=True)
|
|
return torch.cat([boxes, scores, labels.to(boxes.dtype)], dim=-1)
|
|
|
|
|
|
def yolov8_export(weights, device, inplace=True, fuse=True):
|
|
ckpt = torch.load(weights, map_location='cpu')
|
|
ckpt = (ckpt.get('ema') or ckpt['model']).to(device).float()
|
|
if not hasattr(ckpt, 'stride'):
|
|
ckpt.stride = torch.tensor([32.])
|
|
if hasattr(ckpt, 'names') and isinstance(ckpt.names, (list, tuple)):
|
|
ckpt.names = dict(enumerate(ckpt.names))
|
|
model = ckpt.fuse().eval() if fuse and hasattr(ckpt, 'fuse') else ckpt.eval()
|
|
for m in model.modules():
|
|
t = type(m)
|
|
if hasattr(m, 'inplace'):
|
|
m.inplace = inplace
|
|
elif t.__name__ == 'Upsample' and not hasattr(m, 'recompute_scale_factor'):
|
|
m.recompute_scale_factor = None
|
|
model = deepcopy(model).to(device)
|
|
for p in model.parameters():
|
|
p.requires_grad = False
|
|
model.eval()
|
|
model.float()
|
|
model = model.fuse()
|
|
for k, m in model.named_modules():
|
|
if m.__class__.__name__ in ('Detect', 'RTDETRDecoder'):
|
|
m.dynamic = False
|
|
m.export = True
|
|
m.format = 'onnx'
|
|
elif m.__class__.__name__ == 'C2f':
|
|
m.forward = m.forward_split
|
|
return model
|
|
|
|
|
|
def suppress_warnings():
|
|
import warnings
|
|
warnings.filterwarnings('ignore', category=torch.jit.TracerWarning)
|
|
warnings.filterwarnings('ignore', category=UserWarning)
|
|
warnings.filterwarnings('ignore', category=DeprecationWarning)
|
|
warnings.filterwarnings('ignore', category=FutureWarning)
|
|
warnings.filterwarnings('ignore', category=ResourceWarning)
|
|
|
|
|
|
def main(args):
|
|
suppress_warnings()
|
|
|
|
print(f'\nStarting: {args.weights}')
|
|
|
|
print('Opening YOLOv8 model')
|
|
|
|
device = torch.device('cpu')
|
|
model = yolov8_export(args.weights, device)
|
|
|
|
if len(model.names.keys()) > 0:
|
|
print('Creating labels.txt file')
|
|
with open('labels.txt', 'w', encoding='utf-8') as f:
|
|
for name in model.names.values():
|
|
f.write(f'{name}\n')
|
|
|
|
model = nn.Sequential(model, DeepStreamOutput())
|
|
|
|
img_size = args.size * 2 if len(args.size) == 1 else args.size
|
|
|
|
onnx_input_im = torch.zeros(args.batch, 3, *img_size).to(device)
|
|
onnx_output_file = f'{args.weights}.onnx'
|
|
|
|
dynamic_axes = {
|
|
'input': {
|
|
0: 'batch'
|
|
},
|
|
'output': {
|
|
0: 'batch'
|
|
}
|
|
}
|
|
|
|
print('Exporting the model to ONNX')
|
|
torch.onnx.export(
|
|
model, onnx_input_im, onnx_output_file, verbose=False, opset_version=args.opset, do_constant_folding=True,
|
|
input_names=['input'], output_names=['output'], dynamic_axes=dynamic_axes if args.dynamic else None
|
|
)
|
|
|
|
if args.simplify:
|
|
print('Simplifying the ONNX model')
|
|
import onnxslim
|
|
model_onnx = onnx.load(onnx_output_file)
|
|
model_onnx = onnxslim.slim(model_onnx)
|
|
onnx.save(model_onnx, onnx_output_file)
|
|
|
|
print(f'Done: {onnx_output_file}\n')
|
|
|
|
|
|
def parse_args():
|
|
import argparse
|
|
parser = argparse.ArgumentParser(description='DeepStream YOLOv8 conversion')
|
|
parser.add_argument('-w', '--weights', required=True, help='Input weights (.pt) file path (required)')
|
|
parser.add_argument('-s', '--size', nargs='+', type=int, default=[640], help='Inference size [H,W] (default [640])')
|
|
parser.add_argument('--opset', type=int, default=17, help='ONNX opset version')
|
|
parser.add_argument('--simplify', action='store_true', help='ONNX simplify model')
|
|
parser.add_argument('--dynamic', action='store_true', help='Dynamic batch-size')
|
|
parser.add_argument('--batch', type=int, default=1, help='Static batch-size')
|
|
args = parser.parse_args()
|
|
if not os.path.isfile(args.weights):
|
|
raise SystemExit('Invalid weights file')
|
|
if args.dynamic and args.batch > 1:
|
|
raise SystemExit('Cannot set dynamic batch-size and static batch-size at same time')
|
|
return args
|
|
|
|
|
|
if __name__ == '__main__':
|
|
args = parse_args()
|
|
main(args)
|