apq
apq copied to clipboard
[CVPR 2020] APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
I did multiple runs of search and usually after 800-1000 iterations there is no improvement. Is it a desired result? Given large search space I would expect the search to...
Hello, Can you please provide more details about how the data was collected to train the accuracy predictor? To be more specific, can you provide details about how the sampling...
How to train the mixed precision accuracy predictor(acc_quant.pt)? Do you have the code to generate the dataset of 5000 elements?
When running `search.py` with pre-trained weights provided in the README I am getting consistent accuracy results independently of the latency constraint (120ms yields similar results to 8ms). How could that...
Hi: Great work! Could you also provide more information on how did you get BitFusion latency and energy? I noticed that the BitFusion authors released a simulator (https://github.com/hsharma35/bitfusion). Did you...
Hello Could you provide "FP32 Model ACC Predictor", please? Thanks.
Could you please provide the code for training quantization aware accuracy predictor or creating dataset for quantization aware accuracy predictor?
I have doubts that the search code will produce a better architecture. I saved the architecture as a JSON file, but the testing accuracy is quite low, around 0.4. Has...