tvm-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From ds-jnorwood <notificati...@github.com>
Subject Re: [dmlc/tvm] [RFC][Quantization] Support quantized models from TensorflowLite (#2351)
Date Wed, 29 May 2019 07:19:24 GMT
> From my experience, we needn't q_relu. But we need q_add / q_concate and so on. I suggest
we use MobilenetV2 quant model for example, 

Yes, I believe the MobilenetV2 relu_6 is effectively fused in by the downscale saturation.
 You might need it if you want to support their way of training, though.

Yes Mobilenet has the q_add, but I suggest the Inceptionv3  for q_concatenate, since it also
has concat nodes feeding into concat nodes, and tflite also has to rescale inside the concat
operations.  

Also, I believe the q_add required rescale... but in both q_concat and q_add you can recalculate
the prior op downscale multipliers so you can eliminate the extra rescales. 

Also, depending on your allocation capabilities, you can get rid of all concats.

-- 
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/issues/2351#issuecomment-496816409
Mime
  • Unnamed multipart/alternative (inline, 7-Bit, 0 bytes)
View raw message