<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Error loading MixNet model in Intel® Distribution of OpenVINO™ Toolkit</title>
    <link>https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Error-loading-MixNet-model/m-p/1203990#M20416</link>
    <description>&lt;P&gt;Hello,&lt;/P&gt;
&lt;P&gt;when loading a MixNet model converted from ONNX using model converter, I get an error saying "Convolution initialization. Group splitted mode are used together with direct group specification" when model is loaded. Error is reproduced in 2020.3 and 2020.4 releases in Ubuntu Linux 18.04&lt;/P&gt;
&lt;P&gt;ONNX model is converted from a pretrained Pytorch model from&amp;nbsp;&lt;A href="https://github.com/rwightman/gen-efficientnet-pytorch" target="_blank"&gt;https://github.com/rwightman/gen-efficientnet-pytorch.&lt;/A&gt;&lt;/P&gt;
&lt;P&gt;and converted using:&lt;/P&gt;
&lt;P&gt;python mo_onnx.py --input_model=&amp;lt;ONNX_FILE&amp;gt; --output_dir=&amp;lt;OUTPUT_FOLDER&amp;gt;&lt;/P&gt;
&lt;P&gt;Find attached ONNX file and converted models&lt;/P&gt;
&lt;P&gt;Any help?&lt;/P&gt;
&lt;P&gt;Thanks,&lt;/P&gt;
&lt;P&gt;Ricard&lt;/P&gt;</description>
    <pubDate>Tue, 25 Aug 2020 16:07:24 GMT</pubDate>
    <dc:creator>RicardBorras</dc:creator>
    <dc:date>2020-08-25T16:07:24Z</dc:date>
    <item>
      <title>Error loading MixNet model</title>
      <link>https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Error-loading-MixNet-model/m-p/1203990#M20416</link>
      <description>&lt;P&gt;Hello,&lt;/P&gt;
&lt;P&gt;when loading a MixNet model converted from ONNX using model converter, I get an error saying "Convolution initialization. Group splitted mode are used together with direct group specification" when model is loaded. Error is reproduced in 2020.3 and 2020.4 releases in Ubuntu Linux 18.04&lt;/P&gt;
&lt;P&gt;ONNX model is converted from a pretrained Pytorch model from&amp;nbsp;&lt;A href="https://github.com/rwightman/gen-efficientnet-pytorch" target="_blank"&gt;https://github.com/rwightman/gen-efficientnet-pytorch.&lt;/A&gt;&lt;/P&gt;
&lt;P&gt;and converted using:&lt;/P&gt;
&lt;P&gt;python mo_onnx.py --input_model=&amp;lt;ONNX_FILE&amp;gt; --output_dir=&amp;lt;OUTPUT_FOLDER&amp;gt;&lt;/P&gt;
&lt;P&gt;Find attached ONNX file and converted models&lt;/P&gt;
&lt;P&gt;Any help?&lt;/P&gt;
&lt;P&gt;Thanks,&lt;/P&gt;
&lt;P&gt;Ricard&lt;/P&gt;</description>
      <pubDate>Tue, 25 Aug 2020 16:07:24 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Error-loading-MixNet-model/m-p/1203990#M20416</guid>
      <dc:creator>RicardBorras</dc:creator>
      <dc:date>2020-08-25T16:07:24Z</dc:date>
    </item>
    <item>
      <title>Re:Error loading MixNet model</title>
      <link>https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Error-loading-MixNet-model/m-p/1204696#M20437</link>
      <description>&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;Hi Ricard,&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;EfficientNet B0, EfficientNet B5 and EfficientNet B7 are available as public models in Open Model Zoo. For your case, I’ve validated EfficientNet B0 using OpenVINO 2020.4 in Ubuntu 18.04 LTS, and the model is working fine with Image Classification Python Sample. &lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;I suggest you try the following: &lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;I converted the PyTorch model to ONNX using the following command available from &lt;/SPAN&gt;&lt;A href="https://github.com/rwightman/gen-efficientnet-pytorch" rel="noopener noreferrer" target="_blank" style="font-size: 16px;"&gt;https://github.com/rwightman/gen-efficientnet-pytorch&lt;/A&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;python3 onnx_export.py --model efficientnet_b0 ./efficientnet-b0.onnx &lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;The Model Optimizer command that I used is as follows:&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;python3 /opt/intel/openvino/deployment_tools/model_optimizer/mo_onnx.py --input_model /home/username/Desktop/efficientnet-b0.onnx --reverse_input_channels --input_shape [1,3,224,224]&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;The Model Optimizer conversion parameters for efficientnet-b0-pytorch is available at &lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;A href="https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/efficientnet-b0-pytorch/model.yml#L64" rel="noopener noreferrer" target="_blank" style="font-size: 16px;"&gt;https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/efficientnet-b0-pytorch/model.yml#L64&lt;/A&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;Similarly, Model Optimizer conversion parameters for efficientnet-b5-pytorch and efficientnet-b7-pytorch are available at&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;A href="https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/efficientnet-b5-pytorch/model.yml#L70" rel="noopener noreferrer" target="_blank" style="font-size: 16px;"&gt;https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/efficientnet-b5-pytorch/model.yml#L70&lt;/A&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;&lt;A href="https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/efficientnet-b7-pytorch/model.yml#L69" rel="noopener noreferrer" target="_blank" style="font-size: 16px;"&gt;https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/efficientnet-b7-pytorch/model.yml#L69&lt;/A&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;Regards,&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;Munesh&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Thu, 27 Aug 2020 15:35:21 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Error-loading-MixNet-model/m-p/1204696#M20437</guid>
      <dc:creator>Munesh_Intel</dc:creator>
      <dc:date>2020-08-27T15:35:21Z</dc:date>
    </item>
    <item>
      <title>Re: Re:Error loading MixNet model</title>
      <link>https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Error-loading-MixNet-model/m-p/1205329#M20470</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;
&lt;P&gt;I haven't tryied EfficientNET models from this repo, I am trying to use MIXNET models (following same steps that you supplied for EfficientNET). Can you verify if your approach works for Mixnet models?&lt;/P&gt;
&lt;P&gt;thanks,&lt;/P&gt;
&lt;P&gt;Ricard&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Sun, 30 Aug 2020 15:55:36 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Error-loading-MixNet-model/m-p/1205329#M20470</guid>
      <dc:creator>RicardBorras</dc:creator>
      <dc:date>2020-08-30T15:55:36Z</dc:date>
    </item>
    <item>
      <title>Re:Error loading MixNet model</title>
      <link>https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Error-loading-MixNet-model/m-p/1206077#M20512</link>
      <description>&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;Hi Ricard,&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;I’ve validated your MixNet model, and am seeing the same errors as well. This is due to MixNet not being supported officially by OpenVINO.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;Details about supported PyTorch models are available at the following page:&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;A href="https://docs.openvinotoolkit.org/2020.4/openvino_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_ONNX.html#supported_pytorch_models_via_onnx_conversion" rel="noopener noreferrer" target="_blank" style="font-size: 16px;"&gt;https://docs.openvinotoolkit.org/2020.4/openvino_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_ONNX.html#supported_pytorch_models_via_onnx_conversion&lt;/A&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;Regards,&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;Munesh&lt;/SPAN&gt;&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Wed, 02 Sep 2020 11:17:59 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Error-loading-MixNet-model/m-p/1206077#M20512</guid>
      <dc:creator>Munesh_Intel</dc:creator>
      <dc:date>2020-09-02T11:17:59Z</dc:date>
    </item>
    <item>
      <title>Re:Error loading MixNet model</title>
      <link>https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Error-loading-MixNet-model/m-p/1208247#M20601</link>
      <description>&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;Hi Ricard,&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;This thread will no longer be monitored since we have provided a solution.&amp;nbsp;If you need any additional information from Intel, please submit a new question.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;Regards,&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN style="font-size: 16px;"&gt;Munesh&lt;/SPAN&gt;&lt;/P&gt;&lt;BR /&gt;</description>
      <pubDate>Thu, 10 Sep 2020 11:33:51 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Error-loading-MixNet-model/m-p/1208247#M20601</guid>
      <dc:creator>Munesh_Intel</dc:creator>
      <dc:date>2020-09-10T11:33:51Z</dc:date>
    </item>
  </channel>
</rss>

