wangxudong

how is it now

I had the same issue with xavier on yolov3/4/5. ENV: Xlib: extension "NV-GLX" missing on display "localhost:11.0". Xlib: extension "NV-GLX" missing on display "localhost:11.0". Xlib: extension "NV-GLX" missing on display...

the same issue, pls make a reply.

output bbox: [[ 0.636135 0.27017403 0.9825909 1.1217589 ] [ 0.637047 0.40575445 0.67029864 0.49792147] [ 0.755039 0.28670368 0.9688152 0.9758347 ] [ 0.8456569 0.6002558 0.8926159 0.7711937 ] [ 0.83193415 0.5609849 0.90308326 0.8282661...

> Hi @wangxudong-cq, Have you checked whether the weights are stored in `model.graph.initializer`? Do you bump into any issue because they are not in the graph's input? Maybe I'm not...

> Thank you for the clarification. Actually only models whose IR_VERSION < 4 requires graph.initializer be included in graph.input. For models whose IR_VERSION >=4 (like these two models), their initializer...

``` for node in graph.node: for attr in node.attribute: # Ref attrs refer to other attrs, so we don't need to do anything if attr.ref_attr_name != "": continue if attr.type...

When the preprocessing of the inception model is the same as resnet, the inference result is wrong inception v1:  resnresnet18-v1:  how to solve?

any update,i have the same issue: ``` OnnxEmitter has not supported operator [ConvTranspose]. upscore2 OnnxEmitter has not supported operator [Crop]. score_pool4c OnnxEmitter has not supported operator [ConvTranspose]. upscore_pool4 OnnxEmitter has...

same issue, Can not install the latest version