Erwan BERNARD

Results 14 comments of Erwan BERNARD

The Pypi repository is no longer this version of tensorboard : https://github.com/dmlc/tensorboard/issues/50

have you also use onnxconverter-common from source ?

hyperparameter change in function of multi-gpu or not, batch size etc ... If you want to achieve the best MAP on different configuration, you need to adjust them.

@niufuren @315386775 ndarray api make some computation asynchronously. https://github.com/apache/incubator-mxnet/issues/6974 so if you want to time ndarray computation, you need to be sure computation are finished. You can either call asnumpy()...

I don't test it, but it seem `evaluate` use batch and `demo` don't.

What graphic card did you have ? Is there enough memory ?

I don't think mxnet-ssd is compatible with python3. Your error come from behavior difference in import between python3 and python2. For a python3 import you need to change this relative...

something like that should work : ``` train.py --network mobilenet --data-shape 224 --pretrained your_pretrained_model_prefix --epoch XXX --prefix output_model_prefix ``` you need to take care if your mobilenet is exactly the...

Is there any update on this issue ?

I'm not really sure it's exactly the same issue, I got a simillar error with this example using `USE_XSIMD` # pythran export mysum(int[]) # failed # pythran export mysum(int8[]) #...