116 lines
3.8 KiB
Python
Executable File
116 lines
3.8 KiB
Python
Executable File
import os
|
|
import torch
|
|
import torch.nn as nn
|
|
from copy import deepcopy
|
|
|
|
from ultralytics import RTDETR
|
|
|
|
|
|
class DeepStreamOutput(nn.Module):
|
|
def __init__(self, img_size):
|
|
super().__init__()
|
|
self.img_size = img_size
|
|
|
|
def forward(self, x):
|
|
boxes = x[:, :, :4]
|
|
convert_matrix = torch.tensor(
|
|
[[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]], dtype=boxes.dtype, device=boxes.device
|
|
)
|
|
boxes @= convert_matrix
|
|
boxes *= torch.as_tensor([[*self.img_size]]).flip(1).tile([1, 2]).unsqueeze(1)
|
|
scores, labels = torch.max(x[:, :, 4:], dim=-1, keepdim=True)
|
|
return torch.cat([boxes, scores, labels.to(boxes.dtype)], dim=-1)
|
|
|
|
|
|
def rtdetr_ultralytics_export(weights, device):
|
|
model = RTDETR(weights)
|
|
model = deepcopy(model.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 RT-DETR Ultralytics model')
|
|
|
|
device = torch.device('cpu')
|
|
model = rtdetr_ultralytics_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')
|
|
|
|
img_size = args.size * 2 if len(args.size) == 1 else args.size
|
|
|
|
model = nn.Sequential(model, DeepStreamOutput(img_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 is not available for this model')
|
|
|
|
print(f'Done: {onnx_output_file}\n')
|
|
|
|
|
|
def parse_args():
|
|
import argparse
|
|
parser = argparse.ArgumentParser(description='DeepStream RT-DETR Ultralytics 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)
|