From 81492d79eaec239674c8ec882ecd89466a26e4b0 Mon Sep 17 00:00:00 2001 From: Gal Novik <gal.novik@intel.com> Date: Wed, 26 Dec 2018 17:30:51 +0200 Subject: [PATCH] Update README.md Minor command line fix in the post training example --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index a767009..77ed092 100755 --- a/README.md +++ b/README.md @@ -285,7 +285,7 @@ $ python3 compress_classifier.py --resume=../ssl/checkpoints/checkpoint_trained_ This example performs 8-bit quantization of ResNet20 for CIFAR10. We've included in the git repository the checkpoint of a ResNet20 model that we've trained with 32-bit floats, so we'll take this model and quantize it: ``` -$ python3 compress_classifier.py -a resnet20_cifar ../../../data.cifar10 --resume ../examples/ssl/checkpoints/checkpoint_trained_dense.pth.tar --quantize-eval --evaluate +$ python3 compress_classifier.py -a resnet20_cifar ../../../data.cifar10 --resume ../ssl/checkpoints/checkpoint_trained_dense.pth.tar --quantize-eval --evaluate ``` The command-line above will save a checkpoint named `quantized_checkpoint.pth.tar` containing the quantized model parameters. See more examples [here](https://github.com/NervanaSystems/distiller/blob/master/examples/quantization/post_training_quant.md). -- GitLab