Type mismatch in ch4/fcnet_classification_tf.py

```
Traceback (most recent call last):
File "fcnet_classification_tf.py", line 17, in
y_zeros = np.zeros((N/2,))
TypeError: 'float' object cannot be interpreted as an integer
```
and in other lines. To correct, `sed -i 's|N/2|N//2|g' ch4/fcnet_classification_tf.py`.

Start with ch4/fcnet_classification_tf.py and the traceback at line 17, then inspect the other N/2 occurrences mentioned in the issue. Run the script after the correction and confirm it no longer raises the reported integer-type error.

Written by the indexing model from the issue text.