nohup: ignoring input [W Context.cpp:69] Warning: torch.set_deterministic is in beta, and its design and functionality may change in the future. (function operator()) [04 07:01:36 :39] WRN migrate all stand-alone args into a single task [04 07:01:36 :159] set task task_0's 0th input model path as /root/axera/axera-quan-hjj/model/fasternet_size-256.onnx [04 07:01:36 :178] set task task_0's 0th output model path as /root/axera/axera-quan-hjj/joint/fasternet-handpose.joint [04 07:01:36 :297] set task task_0's pulsar_conf.output_dir as /root/axera/axera-quan-hjj /opt/venv/lib/python3.6/site-packages/torch/cuda/__init__.py:52: UserWarning: CUDA initialization: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx (Triggered internally at /pytorch/c10/cuda/CUDAFunctions.cpp:100.) return torch._C._cuda_getDeviceCount() > 0 [04 07:01:37 :17] planning task task_0 [04 07:01:37 :459] WRN affine_preprocess at QAT model compiling is deprecated, insert enforce_integers at front, please use scale_to_integers instead. [04 07:01:37 :340] ################## Running task task_0 ################## [04 07:01:37 :30] python3 /root/python_modules/super_pulsar/super_pulsar/toolchain_wrappers/wrapper_neuwizard.py --config /tmp/tmp5q69qwrl.prototxt [04 07:01:38 :36] DBG [neuwizard] [W Context.cpp:69] Warning: torch.set_deterministic is in beta, and its design and functionality may change in the future. (function operator()) [04 07:02:19 :36] DBG [neuwizard] /opt/venv/lib/python3.6/site-packages/torch/cuda/__init__.py:52: UserWarning: CUDA initialization: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx (Triggered internally at /pytorch/c10/cuda/CUDAFunctions.cpp:100.) [04 07:02:19 :36] DBG [neuwizard] return torch._C._cuda_getDeviceCount() > 0 [04 07:02:19 :36] DBG [neuwizard] ONNX Model Version 12 for "/root/axera/axera-quan-hjj/model/fasternet_size-256.onnx" [04 07:02:19 :36] DBG [neuwizard] Planning load step finished; elapsed time: 0.01s [04 07:02:19 :36] DBG [neuwizard] Planning transform step finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Planning transform step finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Planning transform step finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Planning transform step to "native" finished; elapsed time: 0.07s [04 07:02:19 :36] DBG [neuwizard] Planning transform step to "native_no_bn" finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Planning transform step to "pretransformed" finished; elapsed time: 0.60s [04 07:02:19 :36] DBG [neuwizard] Planning calibrate step finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Planning transform step to "transformed" finished; elapsed time: 32.91s [04 07:02:19 :36] DBG [neuwizard] Planning transform step to "posttransformed" finished; elapsed time: 4.36s [04 07:02:19 :36] DBG [neuwizard] Planning transform step to "magma" finished; elapsed time: 0.39s [04 07:02:19 :36] DBG [neuwizard] Planning transform step to "magma_validified" finished; elapsed time: 0.10s [04 07:02:19 :36] DBG [neuwizard] Planning transform step to "lava_with_rtv" finished; elapsed time: 1.84s [04 07:02:19 :36] DBG [neuwizard] Planning dump_joint_model step finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Planning evaluate step finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Planning ir_bit_macs step finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Planning ir_bit_float_params step finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Planning ir_bit_quantized_params step finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Loading model finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Transforming to "onnx_step_1" finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Transforming to "onnx_step_2" finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Transforming to "onnx" finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Transforming to "native" finished; elapsed time: 0.03s [04 07:02:19 :36] DBG [neuwizard] Transforming to "native_no_bn" finished; elapsed time: 0.00s [04 07:02:19 :36] DBG [neuwizard] Transforming to "pretransformed" finished; elapsed time: 0.15s [04 07:02:19 :36] DBG [neuwizard] Calibrating finished; elapsed time: 0.02s [04 07:02:19 :36] DBG [neuwizard] Traceback (most recent call last): [04 07:02:19 :36] DBG [neuwizard] File "", line 3, in  [04 07:02:19 :36] DBG [neuwizard] File "", line 98, in  [04 07:02:19 :36] DBG [neuwizard] File "", line 58, in convert [04 07:02:19 :36] DBG [neuwizard] File "", line 40, in run [04 07:02:19 :36] DBG [neuwizard] File "", line 47, in run [04 07:02:19 :36] DBG [neuwizard] File "", line 127, in calibrate [04 07:02:19 :36] DBG [neuwizard] File "", line 45, in __init__ [04 07:02:19 :36] DBG [neuwizard] File "/opt/venv/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1052, in load_state_dict [04 07:02:19 :36] DBG [neuwizard] self.__class__.__name__, "\n\t".join(error_msgs))) [04 07:02:19 :36] DBG [neuwizard] RuntimeError: Error(s) in loading state_dict for NeuwizardModule: [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_29.weight: copying a param with shape torch.Size([10, 10, 3, 3]) from checkpoint, the shape in current model is torch.Size([10, 20, 3, 3]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_27.weight: copying a param with shape torch.Size([80, 40, 1, 1]) from checkpoint, the shape in current model is torch.Size([80, 30, 1, 1]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_33.weight: copying a param with shape torch.Size([20, 20, 3, 3]) from checkpoint, the shape in current model is torch.Size([20, 40, 3, 3]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_31.weight: copying a param with shape torch.Size([160, 80, 1, 1]) from checkpoint, the shape in current model is torch.Size([160, 60, 1, 1]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_36.weight: copying a param with shape torch.Size([20, 20, 3, 3]) from checkpoint, the shape in current model is torch.Size([20, 40, 3, 3]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_34.weight: copying a param with shape torch.Size([160, 80, 1, 1]) from checkpoint, the shape in current model is torch.Size([160, 60, 1, 1]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_40.weight: copying a param with shape torch.Size([40, 40, 3, 3]) from checkpoint, the shape in current model is torch.Size([40, 80, 3, 3]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_38.weight: copying a param with shape torch.Size([320, 160, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 120, 1, 1]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_43.weight: copying a param with shape torch.Size([40, 40, 3, 3]) from checkpoint, the shape in current model is torch.Size([40, 80, 3, 3]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_41.weight: copying a param with shape torch.Size([320, 160, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 120, 1, 1]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_46.weight: copying a param with shape torch.Size([40, 40, 3, 3]) from checkpoint, the shape in current model is torch.Size([40, 80, 3, 3]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_44.weight: copying a param with shape torch.Size([320, 160, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 120, 1, 1]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_49.weight: copying a param with shape torch.Size([40, 40, 3, 3]) from checkpoint, the shape in current model is torch.Size([40, 80, 3, 3]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_47.weight: copying a param with shape torch.Size([320, 160, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 120, 1, 1]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_52.weight: copying a param with shape torch.Size([40, 40, 3, 3]) from checkpoint, the shape in current model is torch.Size([40, 80, 3, 3]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_50.weight: copying a param with shape torch.Size([320, 160, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 120, 1, 1]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_55.weight: copying a param with shape torch.Size([40, 40, 3, 3]) from checkpoint, the shape in current model is torch.Size([40, 80, 3, 3]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_53.weight: copying a param with shape torch.Size([320, 160, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 120, 1, 1]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_58.weight: copying a param with shape torch.Size([40, 40, 3, 3]) from checkpoint, the shape in current model is torch.Size([40, 80, 3, 3]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_56.weight: copying a param with shape torch.Size([320, 160, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 120, 1, 1]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_61.weight: copying a param with shape torch.Size([40, 40, 3, 3]) from checkpoint, the shape in current model is torch.Size([40, 80, 3, 3]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_59.weight: copying a param with shape torch.Size([320, 160, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 120, 1, 1]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_362:conv1.weight: copying a param with shape torch.Size([80, 0, 3, 3]) from checkpoint, the shape in current model is torch.Size([80, 80, 3, 3]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_63.weight: copying a param with shape torch.Size([640, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([640, 240, 1, 1]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_363:conv1.weight: copying a param with shape torch.Size([80, 0, 3, 3]) from checkpoint, the shape in current model is torch.Size([80, 80, 3, 3]). [04 07:02:19 :36] DBG [neuwizard] size mismatch for op_66.weight: copying a param with shape torch.Size([640, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([640, 240, 1, 1]). Traceback (most recent call last): File "/root/python_modules/super_pulsar/pulsar", line 27, in main() File "/root/python_modules/super_pulsar/pulsar", line 21, in main args.func(args) File "", line 410, in File "", line 343, in main_build File "", line 539, in run File "", line 43, in convert_cli RuntimeError: neuwizard failed