Tuning for int8 quantized config log too slow


Use tf.compat.v1.graph_util.extract_sub_graph
…100%, 0.02 MB, 1 KB/s, 16 seconds passed
[Task 1/23] Current/Best: 72.31/ 823.37 GFLOPS | Progress: (2000/2000) | 40238.38 s Done.
[Task 2/23] Current/Best: 5.33/1250.61 GFLOPS | Progress: (448/2000) | 13866.37 s

I want to tune resnet50 model for int8 quantized config log, but the tuning process is too slow.
Is it normal?


Your search space is a little too large, I’ve found that you can get excellent results after just 100 or 200 trials compared to your 2000.


Thanks,I will try it.


how to use int8 quantized? where is the tutorial? thanks


Could you give me a sample code for tuning int8 quantized config?
I had got a int8 quantized config, but performance has not improved, just like float32.
And the config log is lack of the first conv2d (‘conv2d’, (1, 3, 230, 230, ‘int8’), because I just got conv2d (‘conv2d’, (1, 3, 230, 230, ‘float32’) after tuning.


please refer to https://github.com/vinx13/tvm-cuda-int8-benchmark


tvm int8 quantize support arm?