Error when checking input: expected dense_1_input to have shape (70,) but got array with shape (1,)

Question

I try to use an already trained neuronal network but always stumble upon this error. My input layer has a size of 70 numeric elements and as such the input data xData out of "last.cvs" come with same size:

[0.36 0.44 0.7  0.82 0.72 0.06 0.08 0.32 0.84 0.62 0.08 0.42 0.12 0.08
 0.6  0.48 0.52 0.08 0.28 0.2  0.18 0.4  0.68 0.98 0.32 0.06 0.2  0.04
 0.76 0.62 0.48 0.8  0.38 0.2  0.14 0.5  0.06 0.64 0.2  0.86 0.06 0.02
 0.98 0.7  0.12 0.78 0.24 0.18 0.08 0.04 0.18 0.72 0.94 0.46 0.18 0.04
 0.48 0.7  0.56 0.96 0.5  0.16 0.08 0.12 0.9  0.94 0.76 0.58 0.04 0.06]

My program itself looks like this:

import keras
from keras.models import load_model
from numpy import loadtxt, savetxt, reshape
import datetime as dt
import numpy as np
import os

xData= loadtxt('../input/last.csv')
print(xData)

model = load_model("model.dat")
prediction=model.predict(np.array(xData))
print(prediction);

So...any idea why it thinks the input size is 1 and not 70?

Thibault Bacqueyrisses · Accepted Answer · 2019-06-06 16:58:59Z

1

In keras the first dimension of a Tensor fed into a model must be the batch size : (batch_size, dim), so here your model understand that your are feeding 70 elements of size one.

Try to take your input vector and expand its dim, like that :

xData = np.expand_dims(xData, 0)

And then feed it into your network

answered Jun 6, 2019 at 16:58

Thibault Bacqueyrisses

2,3511 gold badge9 silver badges18 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Error when checking input: expected dense_1_input to have shape (70,) but got array with shape (1,)

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related