Manu Mathew
Manu Mathew
Are you facing any issue with that clip being there?
I noticed that you said that there was an issue with that clip being there. (We are not facing that issue, but in our case it was dataLayer+BN+Clip because TIDL...
Hi @wuzhiyang2016, Which version of TIDL did you get these errors in?
Sorry, I couldn't understand. Please post the exact error that you are getting and describe the situation in further detail.
Hi wuzhiyang2016, Reading your comment carefully, I understood better. What you are saying is that the backward method of QuantizeDequantizeG is not called during back-propagation (loss.backward()). This is a good...
Hi, The backward of QuantizeDequantizeG has numerical gradient: https://en.wikipedia.org/wiki/Numerical_differentiation It's not the one from that paper. Also our recommended quantized_estimation_type is STE, in which case this gradient is not used...
Keeping this open as an FAQ item, so that others can also benefit.
2GB GPU memory is quite less. But you can try to use fp16 for training - that might help you to double the batch size. Try adding the following to...
Hi @wuzhiyang2016 Since this question is about TIDL, I suggest you to ask the question here: https://e2e.ti.com/support/processors/f/791/tags/TIDL
TIDL can import PyTorch(exported to ONNX), Tensorflow, TFLite and Caffe models. Object Detection: ============= Currently TIDL supports Single Shot Multi Box (SSD) Object detector. There are plans to add more...