Silvan Laube
Silvan Laube
The classic one is a person / employee that has a supervisor which is also a person / employee. In my case I need to reference to a "parent" or...
> I've found a workaround: > > In mongoose, you have an `add` method on models that allows you to concatenate model definitions (https://mongoosejs.com/docs/api/schema.html#schema_Schema-add). > > I split my model...
I found other ways to convert. That does not fix the issue of course, but as you said the link is no longer valid. You could try to download the...
I have a similar error, trying to convert openpose COCO model. To obtain it use getModels script: https://github.com/CMU-Perceptual-Computing-Lab/openpose/tree/master/models The convertsion to CoreML works fine, but from CoreML to onnx breaks:...
Trying to convert the body_25 model, I get a different error: ```Traceback (most recent call last): File "", line 1, in File "/usr/local/lib/python3.5/dist-packages/onnxmltools/convert/main.py", line 19, in convert_coreml custom_conversion_functions, custom_shape_calculators) File...
btw: the openVINO model optimizer also had trouble with the same model. A workaround seems to be to define a fix input size (in the model its 1x1 px as...
by the way, the dynamic input size causes problems in my case. I had to fix them similar to what is [described here](https://github.com/onnx/onnx/issues/654#issuecomment-410538671): ```python onnx_model.graph.input[0].type.tensor_type.shape.dim[2].dim_param = 128 # height onnx_model.graph.input[0].type.tensor_type.shape.dim[3].dim_param...
@hperrin I would be much interested in your findings using WASM compared to asm.js and whether performance improved further with the newest libx264 as well Did you do any such...
I would be interested in getting more than one candidates too any progress on that? :) Edit: Well in my case actually it is more like I have one exact...
Hmm yes, question is a bit (if it is to be done nicely for a PR, not a quick&dirty solution just for my own use case) what should the API...