CalibTIP

CalibTIP copied to clipboard

Quantized model accuracy

1

Good afternoon, I found your paper very interesting and wanted to try out your code. I have a several questions I would be grateful if you could answer: 1) In...

KamikaziZen

Shows invalid checkpoint error

2

Hello. I was trying to running the code as per instructed but got this error while running the code. Is there anything I am missing to add during the run?...

hnahi

when i use advanced_pipeline.sh, and i achieve bugs at line 3 "sh scripts/integer-programing.sh resnet resnet50 4 4 8 8 50 loss True", which is 'No such file or directory: 'results/resnet50_w8a8.adaquant/IP_resnet50_loss.txt'....

Dayrker

sequential adaquant updating only one batch with quantized input?

2

https://github.com/itayhubara/CalibTIP/blob/69077c92611b079234706784c344e8c9156f3283/main.py#L481 [0] index into the first batch. isn't sequential adaquant supposed to update the input cache of all batches to the quantized values?

hy-chen

How gradients are computed

1

Hello and thank you for an interesting paper! I have a question concerning the optimization of the quantization step size. In section D.1 of the paper, you mentioned the usage...

AndreevP

MSE loss calculation in adaquant optimize layer seems off for ResNet

1

This implies to calculate MSE between relu(conv_out) for conv1 and conv2 layers https://github.com/itayhubara/CalibTIP/blob/69077c92611b079234706784c344e8c9156f3283/utils/adaquant.py#L124 But in ResNet architecture, conv2 is not followed by a direct Relu. Instead it follows by a...

hy-chen

Calibration dataset

1

What data are you use in /media/drive/Datasets/imagenet/calib?

AlZuev

Hi! Thanks for your work! In Table 2, you showed the results of w4a4 configuration for ResNet models. But you omitted the result of MobileNet-V2 at that table. From figure...

tojiboyevf