0
Ich habe ein einfaches Convolution1D Modell, dass ich erfolgreichKeras CNN vorhersagen Fehler
model = Sequential()
model.add(Embedding(input_dim=vocabsize, output_dim=32,
input_length=STR_MAX_LEN, dropout=0.2))
model.add(Dropout(0.2))
model.add(Convolution1D(64, 5, activation='relu', border_mode='same'))
model.add(Dropout(0.2))
model.add(MaxPooling1D())
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dropout(0.7))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss="binary_crossentropy", optimizer=Adam(), metrics=['accuracy'])
model.summary()
Modell Zusammenfassung wie unten
____________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
====================================================================================================
embedding_1 (Embedding) (None, 500, 32) 160000 embedding_input_1[0][0]
____________________________________________________________________________________________________
dropout_1 (Dropout) (None, 500, 32) 0 embedding_1[0][0]
____________________________________________________________________________________________________
convolution1d_1 (Convolution1D) (None, 500, 64) 10304 dropout_1[0][0]
____________________________________________________________________________________________________
dropout_2 (Dropout) (None, 500, 64) 0 convolution1d_1[0][0]
____________________________________________________________________________________________________
maxpooling1d_1 (MaxPooling1D) (None, 250, 64) 0 dropout_2[0][0]
____________________________________________________________________________________________________
flatten_1 (Flatten) (None, 16000) 0 maxpooling1d_1[0][0]
____________________________________________________________________________________________________
dense_1 (Dense) (None, 100) 1600100 flatten_1[0][0]
____________________________________________________________________________________________________
dropout_3 (Dropout) (None, 100) 0 dense_1[0][0]
____________________________________________________________________________________________________
dense_2 (Dense) (None, 1) 101 dropout_3[0][0]
====================================================================================================
Total params: 1770505
____________________________________________________________________________________________________
trainiert und ich habe einen Text, ich brauche auf der Vorhersage laufen.
text = "dont know what could have saved limp dispiriting yam but it definitely wasnt a lukewarm mushroom as murky and appealing as bong water"
textWordsArray = np.array(text.split())
textIdxArrayPadded =
sequence.pad_sequences(textWordsIdxArray,maxlen=STR_MAX_LEN, value=0)
textIdxArrayPadded
Struktur der Texteingabe
array([[ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 5363, 121, 48, 97,
25, 1891, 8849, 51645, 19831, 18, 9, 404, 15422, 3, 15610, 27479, 14,
7217, 2, 2273, 14, 36597, 1090]], dtype=int32)
Allerdings erhalte ich die unten Fehlermeldung, wenn ich die Vorhersage auszuführen.
Prädiktion = model.predict (textIdxArrayPadded, batch_size = 1, verbose = 1)
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-70-818365da75ca> in <module>()
----> 1 prediction = model.predict(textIdxArrayPadded, batch_size=1,verbose=1)
/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/models.pyc in predict(self, x, batch_size, verbose)
669 if self.model is None:
670 self.build()
--> 671 return self.model.predict(x, batch_size=batch_size, verbose=verbose)
672
673 def predict_on_batch(self, x):
/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/engine/training.pyc in predict(self, x, batch_size, verbose)
1177 f = self.predict_function
1178 return self._predict_loop(f, ins,
-> 1179 batch_size=batch_size, verbose=verbose)
1180
1181 def train_on_batch(self, x, y,
/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/engine/training.pyc in _predict_loop(self, f, ins, batch_size, verbose)
876 ins_batch = slice_X(ins, batch_ids)
877
--> 878 batch_outs = f(ins_batch)
879 if type(batch_outs) != list:
880 batch_outs = [batch_outs]
/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/backend/theano_backend.pyc in __call__(self, inputs)
715 def __call__(self, inputs):
716 assert type(inputs) in {list, tuple}
--> 717 return self.function(*inputs)
718
719
/home/ubuntu/anaconda2/lib/python2.7/site-packages/theano/compile/function_module.pyc in __call__(self, *args, **kwargs)
869 node=self.fn.nodes[self.fn.position_of_error],
870 thunk=thunk,
--> 871 storage_map=getattr(self.fn, 'storage_map', None))
872 else:
873 # old-style linkers raise their own exceptions
/home/ubuntu/anaconda2/lib/python2.7/site-packages/theano/gof/link.pyc in raise_with_op(node, thunk, exc_info, storage_map)
312 # extra long error message in that case.
313 pass
--> 314 reraise(exc_type, exc_value, exc_trace)
315
316
/home/ubuntu/anaconda2/lib/python2.7/site-packages/theano/compile/function_module.pyc in __call__(self, *args, **kwargs)
857 t0_fn = time.time()
858 try:
--> 859 outputs = self.fn()
860 except Exception:
861 if hasattr(self.fn, 'position_of_error'):
IndexError: One of the index value is out of bound. Error code: 65535.\n
Apply node that caused the error: GpuAdvancedSubtensor1(GpuElemwise{Composite{Switch(i0, (i1 * i2 * i3), i2)},no_inplace}.0, Elemwise{Cast{int64}}.0)
Toposort index: 38
Inputs types: [CudaNdarrayType(float32, matrix), TensorType(int64, vector)]
Inputs shapes: [(5000, 32), (500,)]
Inputs strides: [(32, 1), (8,)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[GpuReshape{3}(GpuAdvancedSubtensor1.0, MakeVector{dtype='int64'}.0)]]
HINT: Re-running with most Theano optimization disabled could give you a back-trace of when this node was created. This can be done with by setting the Theano flag 'optimizer=fast_compile'. If that does not work, Theano optimizations can be disabled with 'optimizer=None'.
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.
haben Sie irgendwelche Protokolle der Ausbildung? Etwas scheint mit dem Netzwerk aus sein .. Ihre Ausgabeklasse Dimension ist binär, aber die Reihenfolge, die Sie voraussagen, hat Werte von 0 - 51649 von dem, was ich sehen kann. Die Fehlermeldung tritt auf, wenn etwas make out of bound <65535 wird. –
Das bedeutet, Sie haben zu viele Klassen gegeben "Sigmoid" als Ausgabeschicht –
Dies wurde für mich in einem der anderen Foren gelöst, werde ich die Lösung hier veröffentlichen –