Does quantization support custom model,like object detection model？ about distiller

[HKLee2040]

You may refer to this issue
#62

[guyjacob]

Thank you @HKLee2040 for the pointer.

@InvictusY, just to clarify: The error you're seeing is not related to quantization. You're just trying to run our image classification example on a model that's not supported. Only the models listed in the error you're seeing are supported. And, as noted, it's an image classification sample, not object detection. So it likely won't work as is for what you're trying to run, in terms of loading the data/labels, optimizer setup, etc.

Assuming you have already have a script that runs the model you're interested in, please refer to the issue @HKLee2040 for some discussion on how you could integrate Distiller into that script.

[Coulson1026]

I have a object detection model, like mobilenet+ssd, and I use compress_classifier.py, I just want to quantize to 8 bits. I use command
python compress_classifier.py -a mobilenet_v1_ssd_lite_voc ../data.cifar10 --resume ../../data/models/mobilenet_v1_ssd_lite_voc_72.7.pth --quantize-eval
But, there is a error,

compress_classifier.py: error: argument --arch/-a: invalid choice: 'mobilenet_v1_ssd_lite_voc' (choose from 'alexnet', 'alexnet_bn', 'densenet121', 'densenet161', 'desenet169', 'densenet201', 'inception_v3', 'mobilenet', 'mobilenet_025', 'mobilenet_050', 'mobilenet_075', 'preact_resnet101', 'preact_resnet110_cifar', 'preact_resnet10_cifar_conv_ds', 'preact_resnet152', 'preact_resnet18', 'preact_resnet20_cifar', 'preact_resnet20_cifar_conv_ds', 'preact_resnet32_cifar', 'preact_resnet32_cifar_cov_ds', 'preact_resnet34', 'preact_resnet44_cifar', 'preact_resnet44_cifar_conv_ds', 'preact_resnet50', 'preact_resnet56_cifar', 'preact_resnet56_cifar_conv_ds', 'resnt101', 'resnet101_earlyexit', 'resnet110_cifar_earlyexit', 'resnet1202_cifar_earlyexit', 'resnet152', 'resnet152_earlyexit', 'resnet18', 'resnet18_earlyexit', 'resnet0_cifar', 'resnet20_cifar_earlyexit', 'resnet32_cifar', 'resnet32_cifar_earlyexit', 'resnet34', 'resnet34_earlyexit', 'resnet44_cifar', 'resnet44_cifar_earlyexit', 'rsnet50', 'resnet50_earlyexit', 'resnet56_cifar', 'resnet56_cifar_earlyexit', 'simplenet_cifar', 'squeezenet1_0', 'squeezenet1_1', 'vgg11', 'vgg11_bn', 'vgg11_bn_cifar, 'vgg11_cifar', 'vgg13', 'vgg13_bn', 'vgg13_bn_cifar', 'vgg13_cifar', 'vgg16', 'vgg16_bn', 'vgg16_bn_cifar', 'vgg16_cifar', 'vgg19', 'vgg19_bn', 'vgg19_bn_cifar', 'vg19_cifar')
Could you tell me how to do it? Thank you~

Excuse me, have you solved this problem? I have the same problem now

[nzmora]

Hi @Coulson1026,

We have not added a sample showing object-detection.

Thanks
Neta