Я тренирую модель Tensorflow с LSTM для профилактического обслуживания. Для каждого экземпляра я создаю матрицу (50,4), где 50 - длина последовательности гистотрии, а 4 - количество признаков для каждой записи, поэтому для обучения модели я использую, например, (55048, 50, 4) тензор и а (55048, 1) в качестве метки. Когда я тренируюсь на Jupyter на моем компьютере, это работает (очень медленно, но работает), но на Colab я получаю эту ошибку:
Training data shape is (55048, 50, 4)
Labels shape is (55048, 1)
WARNING:tensorflow:Layer lstm will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
lstm (LSTM) (None, 50, 100) 42000
_________________________________________________________________
dense (Dense) (None, 50, 1) 101
=================================================================
Total params: 42,101
Trainable params: 42,101
Non-trainable params: 0
_________________________________________________________________
Epoch 1/50
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/resource_variable_ops.py:1817: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
ValueError: in user code:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:571 train_function *
outputs = self.distribute_strategy.run(
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:951 run **
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica
return fn(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:543 train_step **
self.compiled_metrics.update_state(y, y_pred, sample_weight)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:406 update_state
metric_obj.update_state(y_t, y_p)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/metrics_utils.py:90 decorated
update_op = update_state_fn(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/metrics.py:2083 update_state
label_weights=label_weights)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/metrics_utils.py:351 update_confusion_matrix_variables
y_pred.shape.assert_is_compatible_with(y_true.shape)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor_shape.py:1117 assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (None, 50) and (None, 1) are incompatible
Я делюсь с вами некоторыми фрагментами кода. Я знаю, что это довольно долго:
def build_lstm(train_data, train_labels, structure=(100,), epochs=50, activation_fun="relu", dropout_rate=0.1,
loss_function="binary_crossentropy", optimizer="adagrad", val_split=0.2, seq_length=50):
#n_features = len(train_data.columns)
print("Train data is\n",train_data)
acceptable_ids = [idx for idx in train_data['id'].unique() if train_data[train_data['id']==idx].shape[0]>seq_length]
seq_gen = [list(gen_sequence(train_data[train_data['id']==idx], seq_length)) for idx in acceptable_ids]
print("Seq gen is\n")
print(np.array(seq_gen).shape)
seq_array = np.concatenate(seq_gen,0).astype(np.float32)
print("Training data shape is", seq_array.shape)
#train_labels = np.asarray(train_labels).astype('float32').reshape((-1,1))
label_gen = [gen_labels(train_labels[train_labels['id']==idx], seq_length) for idx in acceptable_ids]
label_array = np.concatenate(label_gen).astype(np.float32)
print("Labels shape is", label_array.shape)
first_layer=True
model = tf.keras.Sequential()
for layer_nodes in structure:
if first_layer:
model.add(LSTM(layer_nodes, activation=activation_fun, input_shape=(seq_length,train_data.shape[1]-1),
dropout=dropout_rate, return_sequences=True))
first_layer=False
else:
model.add(LSTM(layer_nodes, activation=activation_fun,
dropout=dropout_rate, return_sequences=False))
model.add(Dense(1, activation='sigmoid'))
model.summary()
model.compile(loss=loss_function,
optimizer=optimizer,
metrics=['AUC','accuracy'])
history = model.fit(seq_array,label_array, epochs=epochs, shuffle=True, validation_split=val_split, callbacks=[earlystop_callback])
return model
def gen_sequence(id_df, seq_length):
""" Only sequences that meet the window-length are considered, no padding is used. This means for testing
we need to drop those which are below the window-length. An alternative would be to pad sequences so that
we can use shorter ones """
# for one id I put all the rows in a single matrix
data_matrix = id_df.drop("id",1).values
num_elements = data_matrix.shape[0]
# Iterate over two lists in parallel.
# For example id1 have 192 rows and sequence_length is equal to 50
# so zip iterate over two following list of numbers (0,112),(50,192)
# 0 50 -> from row 0 to row 50
# 1 51 -> from row 1 to row 51
# 2 52 -> from row 2 to row 52
# ...
# 111 191 -> from row 111 to 191
for start, stop in zip(range(0, num_elements-seq_length), range(seq_length, num_elements)):
#print(data_matrix[start:stop, :],"\n")
yield data_matrix[start:stop, :]
def gen_labels(id_df, seq_length):
data_array = id_df.drop("id",1).values
num_elements = data_array.shape[0]
return data_array[seq_length:num_elements, :]
...
for comb_hyp in hyp_combinations:
for id_validation in training_folds_2:
print(id_validation)
## SEPARATE TRAINING SET AND VALIDATION SET
X_val = X[X.id.isin(id_validation)].copy()
X_train = X[~X.id.isin(id_validation)].copy()
y_val = y[y.id.isin(id_validation)].copy()
y_train = y[~y.id.isin(id_validation)].copy()
## TRAIN THE CLASSIFIER
clf = build_lstm(train_data=X_train, train_labels=y_train, structure=comb_hyp[2], epochs=EPOCHS, activation_fun=comb_hyp[0], optimizer=SOLVER, seq_length=SEQ_LENGTH)
...
Почему это работает в Jupyter, а не в Colab? Спасибо за ваше внимание.