python - ValueError: invalid literal for float() Keras -

i'm building simple neural network using keras.

each element of training data has 100 dimensions, , i'm reading labels of elements text file.

f = open('malee', "rt") labelstrain = [line.rstrip() line in f.readlines()] f.close() 

the labels strings have structure: number_text

to fit model on training data:

model.fit(train, labelstrain, epochs= 20000, batch_size= 1350) 

and following error:

file "dnn.py", line 112, in <module>     model.fit(train, labelstrain, epochs=20000, batch_size=1350)   file "/users/renzo/pyenvironments/tensorkeras/lib/python2.7/site-packages/keras/models.py", line 867, in fit     initial_epoch=initial_epoch)   file "/users/renzo/pyenvironments/tensorkeras/lib/python2.7/site-packages/keras/engine/training.py", line 1598, in fit     validation_steps=validation_steps)   file "/users/renzo/pyenvironments/tensorkeras/lib/python2.7/site-packages/keras/engine/training.py", line 1183, in _fit_loop     outs = f(ins_batch)   file "/users/renzo/pyenvironments/tensorkeras/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 2273, in __call__     **self.session_kwargs)   file "/users/renzo/pyenvironments/tensorkeras/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 889, in run     run_metadata_ptr)   file "/users/renzo/pyenvironments/tensorkeras/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1087, in _run     np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)   file "/users/renzo/pyenvironments/tensorkeras/lib/python2.7/site-packages/numpy/core/numeric.py", line 531, in asarray     return array(a, dtype, copy=false, order=order) valueerror: invalid literal float(): 225_sokode 

the label element 279 list of 378 labels.

first of all, pick unique name each of classes. because don't number in class labels (if not same each class, use str.split() keep text). should encode string labels. example, see this post one-hot encoding of labels.