Prashant Maheshwari

Results 5 comments of Prashant Maheshwari
trafficstars

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

I am facing similar issue

add_constant incompatible function arguments

I first converted my model into .onnx format and then simplified it using this repo [https://github.com/daquexian/onnx-simplifier](https://github.com/daquexian/onnx-simplifier) and then to .trt using this [repo](https://github.com/onnx/onnx-tensorrt). I did not find a way or...

Sampling a new data point using TFP distribution trained model

@MokkeMeguru thank you for such a detailed response and suggestions. Yes, by data point I meant sampling an image. I followed this tutorial [https://github.com/MokkeMeguru/glow-realnvp-tutorial/blob/master/tips/glow_mnist_en.ipynb](https://github.com/MokkeMeguru/glow-realnvp-tutorial/blob/master/tips/glow_mnist_en.ipynb ) and after training, I wanted...

Sampling a new data point using TFP distribution trained model

@MokkeMeguru I understand the working of the sample function. Thank you for pointing out the possible difference in the inverse and forward implementation of tensorflow. > I think you want...

Sampling a new data point using TFP distribution trained model

No, I was involved in a project and we thought if we could generate some results without heavily altering the implementation. So I asked if it is at all possible....