keras model prediction is not suitable, what does that mean?… here is a solution to the problem.

## keras model prediction is not suitable, what does that mean?

I tensorflow 2.0 API See the following sample code

```
model = Sequential()
model.add(Embedding(1000, 64, input_length=10))
# the model will take as input an integer matrix of size (batch,
# input_length).
# the largest integer (i.e. word index) in the input should be no larger
# than 999 (vocabulary size).
# now model.output_shape == (None, 10, 64), where None is the batch
# dimension.
input_array = np.random.randint(1000, size=(32, 10))
model.compile('rmsprop', 'mse')
output_array = model.predict(input_array)
assert output_array.shape == (32, 10, 64)
```

I’ve been using the keras API for a few days now and compiling, fitting and then predicting is my way.

What does the above example mean without fitting steps?

### Solution

Represents the use of initialization parameters in models without `fit().`

This example is just to illustrate the return shape of `the Embedding layer`

.