Adjusting batch size

[WJ-8]

I meet the problem

tensorflow.python.framework.errors_impl.InternalError:  Blas GEMM launch failed : a.shape=(1451673, 100), b.shape=(100, 16), m=1451673, n=16, k=100
         [[node dense_1/MatMul (defined at /home/wj/anaconda3/envs/funded/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:1751) ]] [Op:__forward__internal_call_7111]

I have checked TensorFlow and Cuda, and I believe it is due to insufficient graphics memory