Deeplabv3

ONNX格式導出

model=tv.models.segmentation.deeplabv3_mobilenet_v3_large(pretrained=True)
dummy_input=torch.randn(1,3,320,320)
model.eval()
model(dummy_input)
im=torch.zeros(1,3,320,320).to("cpu")
torch.onnx.export(model,im,
"deeplabv3_mobilenet.onnx",
verbose=False,
opset_version=11,
training=torch.onnx.TrainingMode.EVAL,
do_constant_folding=True,
input_names=['input'],
output_names=['out','aux'],
dynamic_axes={'input':{0:'batch',2:'height',3:'width'}}
)

推理測試

transform = torchvision.transforms.Compose([
     torchvision.transforms.ToTensor(),
     torchvision.transforms.Normalize(mean=[0.485, 0.456, 0.406],
      std=[0.229, 0.224, 0.225])
 ])

transform=torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize(mean=[0.485,0.456,0.406],
std=[0.229,0.224,0.225])
])

sess_options=ort.SessionOptions()
#Belowisforoptimizingperformance
sess_options.intra_op_num_threads=24
#sess_options.execution_mode=ort.ExecutionMode.ORT_PARALLEL
sess_options.graph_optimization_level=ort.GraphOptimizationLevel.ORT_ENABLE_ALL
ort_session=ort.InferenceSession("deeplabv3_mobilenet.onnx",providers=['CUDAExecutionProvider'],sess_options=sess_options)
#src=cv.imread("D:/images/messi_player.jpg")
src=cv.imread("D:/images/master.jpg")
image=cv.cvtColor(src,cv.COLOR_BGR2RGB)
blob=transform(image)
c,h,w=blob.shape
input_x=blob.view(1,c,h,w)

defto_numpy(tensor):
returntensor.detach().cpu().numpy()iftensor.requires_gradelsetensor.cpu().numpy()

#computeONNXRuntimeoutputprediction
ort_inputs={ort_session.get_inputs()[0].name:to_numpy(input_x)}
ort_outs=ort_session.run(None,ort_inputs)
t1=ort_outs[0]
t2=ort_outs[1]
labels=np.argmax(np.squeeze(t1,0),axis=0)
print(labels.dtype,labels.shape)
red_map=np.zeros_like(labels).astype(np.uint8)
green_map=np.zeros_like(labels).astype(np.uint8)
blue_map=np.zeros_like(labels).astype(np.uint8)
forlabel_numinrange(0,len(label_color_map)):
index=labels==label_num
red_map[index]=np.array(label_color_map)[label_num,0]
green_map[index]=np.array(label_color_map)[label_num,1]
blue_map[index]=np.array(label_color_map)[label_num,2]
segmentation_map=np.stack([blue_map,green_map,red_map],axis=2)
cv.addWeighted(src,0.8,segmentation_map,0.2,0,src)
cv.imshow("deeplabv3",src)
cv.waitKey(0)
cv.destroyAllWindows()