Resnet50 not working

[xalteropsx]

Resnet50 not working on gpu only working on cpu is it common or i have only the problem

import numpy as np
import ncnn
import torch

def test_inference():
    torch.manual_seed(0)
    in0 = torch.rand(1, 3, 224, 224, dtype=torch.float)
    out = []

    with ncnn.Net() as net:
        net.load_param("resnet50.ncnn.param")
        net.load_model("resnet50.ncnn.bin")
        # net.opt.use_vulkan_compute = True

        with net.create_extractor() as ex:
            ex.input("in0", ncnn.Mat(in0.squeeze(0).numpy()).clone())

            _, out0 = ex.extract("out0")
            out.append(torch.from_numpy(np.array(out0)).unsqueeze(0))
            _, out1 = ex.extract("out1")
            out.append(torch.from_numpy(np.array(out1)).unsqueeze(0))
            _, out2 = ex.extract("out2")
            out.append(torch.from_numpy(np.array(out2)).unsqueeze(0))

        return out

if __name__ == "__main__":
    print(test_inference())

[xalteropsx]

@Baiyuetribe morning bro >.< was pretty stuck to understand

net.opt.use_vulkan_compute = True why this line causing it crash without any warning or error is it common or just i have the problem ?

this is the model i used detection_Resnet50_Final.pth from xinntao facexlib

below ncnn model
https://drive.google.com/drive/folders/1F_qcV1qAm_QcNMFlh6WJ9QxRbeLCuXw0?usp=sharing