122 lines
3.9 KiB
Python
122 lines
3.9 KiB
Python
import os
|
|
import onnx
|
|
import torch
|
|
import torch.nn as nn
|
|
|
|
import yolov6.utils.general as _m
|
|
from yolov6.layers.common import SiLU
|
|
from gold_yolo.switch_tool import switch_to_deploy
|
|
from yolov6.utils.checkpoint import load_checkpoint
|
|
|
|
|
|
def _dist2bbox(distance, anchor_points, box_format='xyxy'):
|
|
lt, rb = torch.split(distance, 2, -1)
|
|
x1y1 = anchor_points - lt
|
|
x2y2 = anchor_points + rb
|
|
bbox = torch.cat([x1y1, x2y2], -1)
|
|
return bbox
|
|
|
|
_m.dist2bbox.__code__ = _dist2bbox.__code__
|
|
|
|
|
|
class DeepStreamOutput(nn.Module):
|
|
def __init__(self):
|
|
super().__init__()
|
|
|
|
def forward(self, x):
|
|
boxes = x[:, :, :4]
|
|
objectness = x[:, :, 4:5]
|
|
scores, labels = torch.max(x[:, :, 5:], dim=-1, keepdim=True)
|
|
scores *= objectness
|
|
return torch.cat([boxes, scores, labels.to(boxes.dtype)], dim=-1)
|
|
|
|
|
|
def gold_yolo_export(weights, device, inplace=True, fuse=True):
|
|
model = load_checkpoint(weights, map_location=device, inplace=inplace, fuse=fuse)
|
|
model = switch_to_deploy(model)
|
|
for layer in model.modules():
|
|
t = type(layer)
|
|
if t.__name__ == 'RepVGGBlock':
|
|
layer.switch_to_deploy()
|
|
model.eval()
|
|
for k, m in model.named_modules():
|
|
if m.__class__.__name__ == 'Conv':
|
|
if isinstance(m.act, nn.SiLU):
|
|
m.act = SiLU()
|
|
elif m.__class__.__name__ == 'Detect':
|
|
m.inplace = False
|
|
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 Gold-YOLO model')
|
|
|
|
device = torch.device('cpu')
|
|
model = gold_yolo_export(args.weights, device)
|
|
|
|
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 Gold-YOLO 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=13, 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)
|