Implementthe classic Alexnet for image categorization of CIFAR-10 dataset with Tensorflow

###this is the Alexnet network working in cifar-10 dataset

Best accurancy what I receive was 81.12% on test data set.

By default network will be run 60 epoch (60 times on all training data set).
_BATCH_SIZE =128

python3 train.py

### Run network on test data set
```sh
python3 predict.py

###result files some result files are saved in the file named checkpoint_dir