# Error in PYNQ-DPU loading "xmodel" **URL:** \ **Category:** Support\ **Created:** [February 9, 2021, 5:33pm UTC](https://discuss.pynq.io/t/error-in-pynq-dpu-loading-xmodel/2312 "2021-02-09T17:33:23Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![Lucas\_Leiva](https://sea1.discourse-cdn.com/flex019/user_avatar/discuss.pynq.io/lucas_leiva/32/1773_2.png) [@Lucas\_Leiva](https://discuss.pynq.io/u/Lucas_Leiva)\ **Post date:** [February 9, 2021, 5:33pm UTC](https://discuss.pynq.io/t/error-in-pynq-dpu-loading-xmodel/2312/1 "2021-02-09T17:33:23Z")
Hi, I´m trying to upload the model compiled from train\_mnist\_classifier example. I am using PYNQ 2.6 , Vivado 2020.1 and PYNQ-DPU 1.2. When I compile the model, I get a “.xmodel” file instead of “.elf”. Then, I uploaded the model and the “dpu.bit” files to the board, but when I try to run this code in Jupyter Notebook: from pynq\_dpu import DpuOverlay overlay = DpuOverlay(“…/mymodel/dpu.bit”) overlay.load\_model(“…/mymodel/mnist\_classifier.xmodel”) appears this error: RuntimeError Traceback (most recent call last) in () 1 from pynq\_dpu import DpuOverlay 2 overlay = DpuOverlay(“…/mymodel/dpu.bit”) ----\> 3 overlay.load\_model(“…/mymodel/mnist\_classifier\_org.xmodel”) /usr/local/lib/python3.6/dist-packages/pynq\_dpu/dpu.py in load\_model(self, model) 211 212 if not model.endswith(“.elf”): → 213 raise RuntimeError(“Currently only elf files can be loaded.”) 214 else: 215 if self.runtime == ‘dnndk’: RuntimeError: Currently only elf files can be loaded. Any suggestions? Regards ---
**Author:** ![rock](https://sea1.discourse-cdn.com/flex019/user_avatar/discuss.pynq.io/rock/32/32_2.png) [@rock](https://discuss.pynq.io/u/rock)\ **Post date:** [February 18, 2021, 3:19pm UTC](https://discuss.pynq.io/t/error-in-pynq-dpu-loading-xmodel/2312/2 "2021-02-18T15:19:25Z")
xmodel is for Vitis AI 1.3. Check the README here: " For the GPU accelerated docker image: ./docker\_run.sh xilinx/vitis-ai:1.2.82 From version 1.3 .xmodel files are generated instead of .elf " > **[DPU-PYNQ/host at master · Xilinx/DPU-PYNQ](https://github.com/Xilinx/DPU-PYNQ/tree/master/host)** > > master/host ---
**Author:** ![Gerardo\_V](https://sea1.discourse-cdn.com/flex019/user_avatar/discuss.pynq.io/gerardo_v/32/1868_2.png) [@Gerardo\_V](https://discuss.pynq.io/u/Gerardo_V)\ **Post date:** [March 16, 2021, 3:22pm UTC](https://discuss.pynq.io/t/error-in-pynq-dpu-loading-xmodel/2312/3 "2021-03-16T15:22:01Z")
Is there any plan to support this soon? If not, is there a possible way of creating the .elf file based on vitis ai 1.3? ---
**Author:** ![rock](https://sea1.discourse-cdn.com/flex019/user_avatar/discuss.pynq.io/rock/32/32_2.png) [@rock](https://discuss.pynq.io/u/rock)\ **Post date:** [March 16, 2021, 9:58pm UTC](https://discuss.pynq.io/t/error-in-pynq-dpu-loading-xmodel/2312/4 "2021-03-16T21:58:31Z")
It is already supported in DPU-PYNQ v1.3.0 ---
**Author:** ![Gerardo\_V](https://sea1.discourse-cdn.com/flex019/user_avatar/discuss.pynq.io/gerardo_v/32/1868_2.png) [@Gerardo\_V](https://discuss.pynq.io/u/Gerardo_V)\ **Post date:** [March 17, 2021, 12:33am UTC](https://discuss.pynq.io/t/error-in-pynq-dpu-loading-xmodel/2312/5 "2021-03-17T00:33:03Z")
So s you mean I can natively generate the .elf file even for vitis ai 1.3 while using DPU PYNQ repo? what about the .xmodel files, are they supported by PYQN ? As far as I know PYNQ 2.6 doesn’t support .xmodel file (I just update the dpu-pynq version of my ultra96v2) and I’m still not able to load them, because is not an elf file. ---
**Author:** ![Gerardo\_V](https://sea1.discourse-cdn.com/flex019/user_avatar/discuss.pynq.io/gerardo_v/32/1868_2.png) [@Gerardo\_V](https://discuss.pynq.io/u/Gerardo_V)\ **Post date:** [March 17, 2021, 2:53pm UTC](https://discuss.pynq.io/t/error-in-pynq-dpu-loading-xmodel/2312/6 "2021-03-17T14:53:01Z")
Sorry for the confusion, just for documenting, after upgrading my pynq version I had to update pynq-dpu to its latest version, after that I was able to load .xmodel files.