Not getting Proper Accurcacy for cifar10 dadatset with mobilenetv2 on CPU

Question

I have tried to train mobilenetV2 with cifar10 dataset as mentioned in https://github.com/tensorflow/models/tree/master/research/slim only change was I did it on CPU but i ended getting only 63% accuracy but the stated accuracy is 94%

DATASET_DIR=/tmp/cifar10
TRAIN_DIR=/tmp/train_logs
python train_image_classifier.py \
--train_dir=${TRAIN_DIR} \
--dataset_name=cifar10 \
--dataset_split_name=train \
--dataset_dir=${DATASET_DIR} \
--model_name=mobilenet_v2 \
--clone_cpu=True

Answer 1

Out of curiosity, which stated accuracy you are referring to?

All these networks to train well without changing on Cifar10 require upsampling Cifar10 to 224x224 (or similar) resolution. There should be a flag for that in train_image_classifier.

Answer 2

Tq @Mark Sandler The hack they did was correct I got about 93% Accuracy by Changing the strides of first 3 layers to 1 among total of 5 layers with Stride 2enter image description here

The File Link is : https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet_v2.py