leandron commented on PR #12042:
URL: https://github.com/apache/tvm/pull/12042#issuecomment-1307482657

   > Hello @leandron,
   > 
   > I'm working on similar lines & have a model with conv2d_transpose & all 
the other ops are already supported from your already merged commit. I've made 
the same changes you've done for conv2d_transpose from this patch, but the 
dequantize layer at the end is getting int64 input which isn't right. Am I 
missing something that needs to be changed?
   > 
   > Thanks in advance!
   
   In TFlite as of now, biases are set by default to be int64 when int16 
quantisation is used.
   
   I have [this 
model](https://github.com/ARM-software/ML-zoo/blob/48f458af1e9065d9aad2ad94d24b58d6e7c00817/models/keyword_spotting/ds_cnn_small/tflite_int16/ds_cnn_quantized.tflite)
 which was created using the [default int16 
flow](https://www.tensorflow.org/lite/performance/post_training_integer_quant_16x8),
 and can be used to check these internal data types with e.g. Netron


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to