Can't make a binary classifier (chap 10)

Hi everyone,

I don't know if it's very appropriate but it has been 2 days that I'm blocked so I try.
I follow the model of the FNN for MNIST (chapter 10) and try to adapt it to my problem which is a binary classification. I used SpaCy before so I get my tensors as ndarray with the same dtype.

2 days ago , I got problem with dtype of my tensor Y , I asked stackoverflow here [https://stackoverflow.com/questions/57077979/binary-classification-xentropy-mismatch-invalid-argument-received-a-label-v](url)
but didn't get any response so I have find myself a "solution" by casting the tensor Y with tf.tofloat(y).
Now, I got that error at the end :

````java
InvalidArgumentError Traceback (most recent call last)
~\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, *args)
1333 try:
-> 1334 return fn(*args)
1335 except errors.OpError as e:

~\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\client\session.py in _run_fn(feed_dict, fetch_list, target_list, options, run_metadata)
1318 return self._call_tf_sessionrun(
-> 1319 options, feed_dict, fetch_list, target_list, run_metadata)
1320

~\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\client\session.py in _call_tf_sessionrun(self, options, feed_dict, fetch_list, target_list, run_metadata)
1406 self._session, options, feed_dict, fetch_list, target_list,
-> 1407 run_metadata)
1408

InvalidArgumentError: targets[0] is out of range
[[{{node in_top_k_2/InTopKV2}}]]
````

**targets** is the second argument of the function : **tf.nn.in_top_k(logits,y,1)**

Here's my **full code** if someone could help me and tell me where is my error and what have I done wrong
````python
import tensorflow as tf
n_inputs = 28
n_hidden1 = 15
n_hidden2 = 5
n_outputs = 1
reset_graph()
X = tf.placeholder(tf.float32, shape=(None, n_inputs), name="X") # variable a qui on assignera values par feed_dict
y = tf.placeholder(tf.int32, shape=(None), name="y") #None => any

def neuron_layer(X, n_neurons, name, activation=None):
with tf.name_scope(name):
n_inputs = int(X.shape[1])
stddev = 2 / np.sqrt(n_inputs)
init = tf.truncated_normal((n_inputs, n_neurons), stddev=stddev) #matrice n_inputs x n_neurons values proche de 0
W = tf.Variable(init,name="kernel") #weights random
b = tf.Variable(tf.zeros([n_neurons]), name="bias")
Z = tf.matmul(X, W) + b
tf.cast(Z,tf.int32)
if activation is not None:
return activation(Z)
else:
return Z

hidden1 = neuron_layer(X, n_hidden1, name="hidden1",
activation=tf.nn.relu)
hidden2 = neuron_layer(hidden1, n_hidden2, name="hidden2",
activation=tf.nn.relu)
logits = neuron_layer(hidden2, n_outputs, name="outputs")

xentropy = tf.keras.backend.binary_crossentropy(tf.to_float(y),logits)
loss = tf.reduce_mean(xentropy)
learning_rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(learning_rate)
training_op = optimizer.minimize(loss)
correct = tf.nn.in_top_k(logits,y, 1)
accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))

init = tf.global_variables_initializer()
saver = tf.train.Saver()
n_epochs = 40
batch_size = 50

def shuffle_batch(X, y, batch_size):
rnd_idx = np.random.permutation(len(X))
n_batches = len(X) // batch_size
for batch_idx in np.array_split(rnd_idx, n_batches):
X_batch, y_batch = X[batch_idx], y[batch_idx]
yield X_batch, y_batch

#until here, no errors ...
with tf.Session() as sess:
init.run()
for epoch in range(n_epochs):
for X_batch, y_batch in shuffle_batch(X_train, Y_train, batch_size):
sess.run(training_op, feed_dict={X: X_batch, y: y_batch})
acc_batch = accuracy.eval(feed_dict={X: X_batch, y: y_batch})
acc_val = accuracy.eval(feed_dict={X: X_valid, y: y_valid})
print(epoch, "Batch accuracy:", acc_batch, "Val accuracy:", acc_val)

save_path = saver.save(sess, "./my_model_final.ckpt")
````
I really need some help .. thanks !