AttributeError: 'TFSequenceClassifierOutput' object has no attribute 'argmax' - tensorflow

I wrote the text classification code with two classes using the Roberta model and now I want to draw the confusion matrix. How to go about plotting the confusion matrix based of a Roberta model?
RobertaTokenizer = RobertaTokenizer.from_pretrained('roberta-base',do_lower_case=False)
roberta_model = TFRobertaForSequenceClassification.from_pretrained('roberta-base',num_labels=2)
input_ids=[]
attention_masks=[]
for sent in sentences:
bert_inp=RobertaTokenizer.encode_plus(sent,add_special_tokens = True,max_length =128,pad_to_max_length = True,return_attention_mask = True)
input_ids.append(bert_inp['input_ids'])
attention_masks.append(bert_inp['attention_mask'])
input_ids=np.asarray(input_ids)
attention_masks=np.array(attention_masks)
labels=np.array(labels)
#split
train_inp,val_inp,train_label,val_label,train_mask,val_mask=train_test_split(input_ids,labels,attention_masks,test_size=0.5)
print('Train inp shape {} Val input shape {}\nTrain label shape {} Val label shape {}\nTrain attention mask shape {} Val attention mask shape {}'.format(train_inp.shape,val_inp.shape,train_label.shape,val_label.shape,train_mask.shape,val_mask.shape))
log_dir='tensorboard_data/tb_roberta'
model_save_path='/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/callbacks.py'
callbacks = [tf.keras.callbacks.ModelCheckpoint(filepath=model_save_path,save_weights_only=True,monitor='val_loss',mode='min',save_best_only=True),keras.callbacks.TensorBoard(log_dir=log_dir)]
print('\nBert Model',roberta_model.summary())
loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
metric = tf.keras.metrics.SparseCategoricalAccuracy('accuracy')
optimizer = tf.keras.optimizers.Adam(learning_rate=2e-5,epsilon=1e-08)
roberta_model.compile(loss=loss,optimizer=optimizer,metrics=[metric]) history=roberta_model.fit([train_inp,train_mask],train_label,batch_size=16,epochs=2,validation_data=([val_inp,val_mask],val_label),callbacks=callbacks)
preds = roberta_model.predict([val_inp,val_mask],batch_size=16)
pred_labels = preds.argmax(axis=1)
f1 = f1_score(val_label,pred_labels)
print('F1 score',f1)
print('Classification Report')
print(classification_report(val_label,pred_labels,target_names=target_names))
c1 = confusion_matrix(val_label,pred_labels)
print('confusion_matrix ',c1)
I now have the following error:
AttributeError Traceback (most recent call last)
<ipython-input-13-abcbb1d223b8> in <module>()
106
107 preds = trained_model.predict([val_inp,val_mask],batch_size=16)
--> 108 pred_labels = preds.argmax(axis=1)
109 f1 = f1_score(val_label,pred_labels)
110 print('F1 score',f1)
AttributeError: 'TFSequenceClassifierOutput' object has no attribute 'argmax'

Instead of pred_labels = preds.argmax (axis = 1), replace the following code:
pred_labels = np.argmax(preds.logits, axis=1)

Related

list indices must be integers or slices, not ListWrapper

I'm having some trouble with a pretty basic model. Am unable to create a pre-processing layer that simply normalizes all features. It is likely that my conceptual understanding of the situation is problematic. My thinking was that the input layer is a list or a dictionary of tf.keras.Input objects, which refer to the input tensors by "name", and indicates their shape and datatypes. Normalizer layers are built by first adapting them over the training dataset, and those layers can be accrued in a list and concatenated. After the input layer is defined, the preprocessing layer takes as input the input layer, and passes its results downstream. Each item in an input layer list is a symbolic representation of the tensors that will flow, and each normalizer will get the right tensors by virtue of having been adapted on that feature.
The error I get is as follows:
TypeError Traceback (most recent call last)
Input In [11], in <cell line: 63>()
59 concatenated_preprocessing_layer = tf.keras.layers.Concatenate(preprocessing_layers)
61 #outputs = concatenated_preprocessing_layer(input_layer.values())
---> 63 outputs = concatenated_preprocessing_layer(all_inputs)
File ~/.pyenv/versions/3.8.5/lib/python3.8/site-packages/keras/utils/traceback_utils.py:67, in filter_traceback.<locals>.error_handler(*args, **kwargs)
65 except Exception as e: # pylint: disable=broad-except
66 filtered_tb = _process_traceback_frames(e.__traceback__)
---> 67 raise e.with_traceback(filtered_tb) from None
68 finally:
69 del filtered_tb
File ~/.pyenv/versions/3.8.5/lib/python3.8/site-packages/keras/layers/merge.py:509, in Concatenate.build(self, input_shape)
507 shape_set = set()
508 for i in range(len(reduced_inputs_shapes)):
--> 509 del reduced_inputs_shapes[i][self.axis]
510 shape_set.add(tuple(reduced_inputs_shapes[i]))
512 if len(shape_set) != 1:
TypeError: list indices must be integers or slices, not ListWrapper
And the code is as follows:
import tensorflow as tf
filepath='./taxi_data.csv'
CSV_COLUMNS = [
'fare_amount',
'pickup_datetime',
'pickup_longitude',
'pickup_latitude',
'dropoff_longitude',
'dropoff_latitude',
'passenger_count',
'key',
]
LABEL_COLUMN = 'fare_amount'
STRING_COLS = ['pickup_datetime']
NUMERIC_COLS = ['pickup_longitude', 'pickup_latitude',
'dropoff_longitude', 'dropoff_latitude',
'passenger_count']
DEFAULTS = [[0.0], ['na'], [0.0], [0.0], [0.0], [0.0], [0.0], ['na']]
DAYS = ['Sun', 'Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat']
def map_features_and_labels(row, target_name):
label = row.pop(target_name)
row.pop('key')
row.pop('pickup_datetime')
return row, label
def create_dataset(filepath, target_name, batch_size=1, mode=tf.estimator.ModeKeys.EVAL, CSV_COLUMNS=None, column_defaults=None ):
dataset = tf.data.experimental.make_csv_dataset(file_pattern=filepath, column_names=CSV_COLUMNS, column_defaults=DEFAULTS, num_epochs=1, batch_size=1)
dataset = dataset.map(lambda X: map_features_and_labels(X, target_name))
if mode == tf.estimator.ModeKeys.TRAIN:
dataset = dataset.shuffle(buffer_size=1000).repeat()
return dataset
train_ds = create_dataset(filepath, target_name=LABEL_COLUMN, batch_size=1, CSV_COLUMNS=CSV_COLUMNS, column_defaults=DEFAULTS )
#The input layer is usually a dictionary of feature_name: Input object
input_layer = {
'pickup_longitude': tf.keras.Input(shape=(0,), name='pickup_longitude', dtype=tf.dtypes.float32),
'pickup_latitude': tf.keras.Input(shape=(0,), name='pickup_latitude', dtype=tf.dtypes.float32),
'dropoff_longitude': tf.keras.Input(shape=(0,), name='dropoff_longitude', dtype=tf.dtypes.float32),
'dropoff_latitude': tf.keras.Input(shape=(0,), name='dropoff_latitude', dtype=tf.dtypes.float32),
'passenger_count': tf.keras.Input(shape=(0,), name='passenger_count', dtype=tf.dtypes.float32),
}
preprocessing_layers = []
all_inputs = []
for column in NUMERIC_COLS:
feature_ds = train_ds.map(lambda X, y: X[column])
normalizer = tf.keras.layers.Normalization(axis=None)
normalizer.adapt(feature_ds)
preprocessing_layers.append(normalizer)
all_inputs.append(tf.keras.Input(shape=(0,), name=column, dtype=tf.dtypes.float32, ))
concatenated_preprocessing_layer = tf.keras.layers.Concatenate(preprocessing_layers)
#outputs = concatenated_preprocessing_layer(input_layer.values())
outputs = concatenated_preprocessing_layer(all_inputs)
And here is some of the data in the taxi_data.csv file
17,2014-10-25 21:39:42 UTC,-73.978713,40.78303,-74.008102,40.73881,2,unused
14.9,2012-08-22 12:01:00 UTC,-73.987667,40.728747,-74.003272,40.715202,2,unused
21.5,2013-12-18 23:26:12 UTC,-74.008969,40.716853,-73.97688,40.780289,2,unused
23.5,2014-10-04 21:58:00 UTC,-73.954153,40.806257,-74.00343,40.731867,2,unused
34.3,2012-12-17 15:23:00 UTC,-73.866917,40.770342,-73.968872,40.757482,2,unused
16.1,2009-09-24 17:37:31 UTC,-73.967549,40.762828,-73.97961,40.723133,2,unused
17.3,2010-04-26 20:52:36 UTC,-73.981381,40.749913,-73.966612,40.691132,2,unused
35,2014-08-13 20:16:00 UTC,-73.866107,40.771245,-74.013987,40.676437,2,unused
17.3,2010-12-30 17:55:00 UTC,-73.997803,40.725982,-73.982382,40.772225,2,unused
I was able to get this to work. Like I suspected, it was my conceptual understanding that was the issue. Specifically, I wasn't correctly hooking up the Input (input_placeholder) to the normalizer. The modified code is below:
preprocessing_layers = []
all_inputs = []
for column in NUMERIC_COLS:
normalizer = get_normalization_layer(column, train_ds)
input_placeholder = tf.keras.Input(shape=(1,), name=column, dtype=tf.dtypes.float32, )
encoded_feature = normalizer(input_placeholder)
preprocessing_layers.append(encoded_feature)
all_inputs.append(input_placeholder)
concatenated_preprocessing_layer = tf.keras.layers.concatenate(preprocessing_layers)
#outputs = concatenated_preprocessing_layer(input_layer.values())
preprocessing_new_model = tf.keras.Model(inputs=all_inputs, outputs=concatenated_preprocessing_layer)
preprocessing_new_model(train_features)
You need to concatenate preprocessing_layers and all_inputs by using the code below:
concatenated_preprocessing_layer = tf.keras.layers.Concatenate((preprocessing_layers,all_inputs))
As you have used
concatenated_preprocessing_layer = tf.keras.layers.Concatenate(preprocessing_layers)
You can concatenate all_inputs by using:
outputs =tf.keras.layers.Concatenate((concatenated_preprocessing_layer,all_inputs))
Please refer to this working gist for your reference.

How to build a custom question-answering head when using hugginface transformers?

Using the TFBertForQuestionAnswering.from_pretrained() function, we get a predefined head on top of BERT together with a loss function that are suitable for this task.
My question is how to create a custom head without relying on TFAutoModelForQuestionAnswering.from_pretrained().
I want to do this because there is no place where the architecture of the head is explained clearly. By reading the code here we can see the architecture they are using, but I can't be sure I understand their code 100%.
Starting from How to Fine-tune HuggingFace BERT model for Text Classification is good. However, it covers only the classification task, which is much simpler.
'start_positions' and 'end_positions' are created following this tutorial.
So far, I've got the following:
train_dataset
# Dataset({
# features: ['input_ids', 'token_type_ids', 'attention_mask', 'start_positions', 'end_positions'],
# num_rows: 99205
# })
train_dataset.set_format(type='tensorflow', columns=['input_ids', 'token_type_ids', 'attention_mask'])
features = {x: train_dataset[x] for x in ['input_ids', 'token_type_ids', 'attention_mask']}
labels = [train_dataset[x] for x in ['start_positions', 'end_positions']]
labels = np.array(labels).T
tfdataset = tf.data.Dataset.from_tensor_slices((features, labels)).batch(16)
input_ids = tf.keras.layers.Input(shape=(256,), dtype=tf.int32, name='input_ids')
token_type_ids = tf.keras.layers.Input(shape=(256,), dtype=tf.int32, name='token_type_ids')
attention_mask = tf.keras.layers.Input((256,), dtype=tf.int32, name='attention_mask')
bert = TFAutoModel.from_pretrained("bert-base-multilingual-cased")
output = bert([input_ids, token_type_ids, attention_mask]).last_hidden_state
output = tf.keras.layers.Dense(2, name="qa_outputs")(output)
model = tf.keras.models.Model(inputs=[input_ids, token_type_ids, attention_mask], outputs=output)
num_train_epochs = 3
num_train_steps = len(tfdataset) * num_train_epochs
optimizer, schedule = create_optimizer(
init_lr=2e-5,
num_warmup_steps=0,
num_train_steps=num_train_steps,
weight_decay_rate=0.01
)
def qa_loss(labels, logits):
loss_fn = tf.keras.losses.SparseCategoricalCrossentropy(
from_logits=True, reduction=tf.keras.losses.Reduction.NONE
)
start_loss = loss_fn(labels[0], logits[0])
end_loss = loss_fn(labels[1], logits[1])
return (start_loss + end_loss) / 2.0
model.compile(
loss=loss_fn,
optimizer=optimizer
)
model.fit(tfdataset, epochs=num_train_epochs)
And I am getting the following error:
ValueError: `labels.shape` must equal `logits.shape` except for the last dimension. Received: labels.shape=(2,) and logits.shape=(256, 2)
It is complaining about the shape of the labels. This should not happen since I am using SparseCategoricalCrossentropy loss.
For future reference, I actually found a solution, which is just editing the TFBertForQuestionAnswering class itself. For example, I added an additional layer in the following code and trained the model as usual and it worked.
from transformers import TFBertPreTrainedModel
from transformers import TFBertMainLayer
from transformers.modeling_tf_utils import TFQuestionAnsweringLoss, get_initializer, input_processing
from transformers.modeling_tf_outputs import TFQuestionAnsweringModelOutput
from transformers import BertConfig
class MY_TFBertForQuestionAnswering(TFBertPreTrainedModel, TFQuestionAnsweringLoss):
# names with a '.' represents the authorized unexpected/missing layers when a TF model is loaded from a PT model
_keys_to_ignore_on_load_unexpected = [
r"pooler",
r"mlm___cls",
r"nsp___cls",
r"cls.predictions",
r"cls.seq_relationship",
]
def __init__(self, config: BertConfig, *inputs, **kwargs):
super().__init__(config, *inputs, **kwargs)
self.num_labels = config.num_labels
self.bert = TFBertMainLayer(config, add_pooling_layer=False, name="bert")
# This is the dense layer I added
self.my_dense = tf.keras.layers.Dense(
units=config.hidden_size,
kernel_initializer=get_initializer(config.initializer_range),
name="my_dense",
)
self.qa_outputs = tf.keras.layers.Dense(
units=config.num_labels,
kernel_initializer=get_initializer(config.initializer_range),
name="qa_outputs",
)
def call(
self,
input_ids = None,
attention_mask = None,
token_type_ids = None,
position_ids = None,
head_mask = None,
inputs_embeds = None,
output_attentions = None,
output_hidden_states = None,
return_dict = None,
start_positions = None,
end_positions= None,
training = False,
**kwargs,
):
r"""
start_positions (`tf.Tensor` or `np.ndarray` of shape `(batch_size,)`, *optional*):
Labels for position (index) of the start of the labelled span for computing the token classification loss.
Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
are not taken into account for computing the loss.
end_positions (`tf.Tensor` or `np.ndarray` of shape `(batch_size,)`, *optional*):
Labels for position (index) of the end of the labelled span for computing the token classification loss.
Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
are not taken into account for computing the loss.
"""
inputs = input_processing(
func=self.call,
config=self.config,
input_ids=input_ids,
attention_mask=attention_mask,
token_type_ids=token_type_ids,
position_ids=position_ids,
head_mask=head_mask,
inputs_embeds=inputs_embeds,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict,
start_positions=start_positions,
end_positions=end_positions,
training=training,
kwargs_call=kwargs,
)
outputs = self.bert(
input_ids=inputs["input_ids"],
attention_mask=inputs["attention_mask"],
token_type_ids=inputs["token_type_ids"],
position_ids=inputs["position_ids"],
head_mask=inputs["head_mask"],
inputs_embeds=inputs["inputs_embeds"],
output_attentions=inputs["output_attentions"],
output_hidden_states=inputs["output_hidden_states"],
return_dict=inputs["return_dict"],
training=inputs["training"],
)
sequence_output = outputs[0]
# You also have to add it here
my_logits = self.my_dense(inputs=sequence_output)
logits = self.qa_outputs(inputs=my_logits)
start_logits, end_logits = tf.split(value=logits, num_or_size_splits=2, axis=-1)
start_logits = tf.squeeze(input=start_logits, axis=-1)
end_logits = tf.squeeze(input=end_logits, axis=-1)
loss = None
if inputs["start_positions"] is not None and inputs["end_positions"] is not None:
labels = {"start_position": inputs["start_positions"]}
labels["end_position"] = inputs["end_positions"]
loss = self.hf_compute_loss(labels=labels, logits=(start_logits, end_logits))
if not inputs["return_dict"]:
output = (start_logits, end_logits) + outputs[2:]
return ((loss,) + output) if loss is not None else output
return TFQuestionAnsweringModelOutput(
loss=loss,
start_logits=start_logits,
end_logits=end_logits,
hidden_states=outputs.hidden_states,
attentions=outputs.attentions,
)
def serving_output(self, output: TFQuestionAnsweringModelOutput) -> TFQuestionAnsweringModelOutput:
hs = tf.convert_to_tensor(output.hidden_states) if self.config.output_hidden_states else None
attns = tf.convert_to_tensor(output.attentions) if self.config.output_attentions else None
return TFQuestionAnsweringModelOutput(
start_logits=output.start_logits, end_logits=output.end_logits, hidden_states=hs, attentions=attns
)

Expected to see 3 array(s), but instead got the following list of 1 arrays:

I am trying to train a triple loss model using a fit_generator. it requires three input and no output. so i have a function that generates hard triplets. the output from the triplets generator has a shape of (3,5,279) which is 3 inputs(anchor,positive and negative) for 5 batches and a total of 279 features. When i run the fit_generator it throws this error that "the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 3 array(s), but instead got the following list of 1 arrays" meanwhile i have passed a list of three arrays. the code is below. it works when i use the fit, however, i want to always call the generator function to generate my triplets as my batches. thanks in advance..this has taken me three days
def load_data():
path = "arrhythmia_data.txt"
f = open( path, "r")
data = []
#remove line breaker, comma separate and store in array
for line in f:
line = line.replace('\n','').replace('?','0')
line = line.split(",")
data.append(line)
f.close()
data = np.array(data).astype(np.float64)
#print(data.shape)
#create the class labels for input data
Y_train = data[:,-1:]
train = data[:,:-1]
normaliser = preprocessing.MinMaxScaler()
train = normaliser.fit_transform(train)
val = train[320:,:]
train = train[:320,:]
#create one hot encoding of the class labels of the data and separate them into train and test data
lb = LabelBinarizer()
encode = lb.fit_transform(Y_train)
nb_classes = int(len(encode[0]))
#one_hot_labels = keras.utils.to_categorical(labels, num_classes=10) this could also be used for one hot encoding
Y_val_e = encode[320:,:]
Y_train_e = encode[:320,:]
print(Y_train_e[0])
print(np.argmax(Y_train_e[0]))
val_in = []
train_in = []
#grouping and sorting the input data based on label id or name
for n in range(nb_classes):
images_class_n = np.asarray([row for idx,row in enumerate(train) if np.argmax(Y_train_e[idx])==n])
train_in.append(images_class_n)
images_class_n = np.asarray([row for idx,row in enumerate(val) if np.argmax(Y_val_e[idx])==n])
val_in.append(images_class_n)
#print(train_in[0].shape)
return train_in,val_in,Y_train_e,Y_val_e,nb_classes
train_in,val,Y_train,Y_val,nb_classes = load_data()
input_shape = (train_in[0].shape[1],)
def build_network(input_shape , embeddingsize):
'''
Define the neural network to learn image similarity
Input :
input_shape : shape of input images
embeddingsize : vectorsize used to encode our picture
'''
#in_ = Input(train.shape)
net = Sequential()
net.add(Dense(128, activation='relu', input_shape=input_shape))
net.add(Dense(128, activation='relu'))
net.add(Dense(256, activation='relu'))
net.add(Dense(4096, activation='sigmoid'))
net.add(Dense(embeddingsize, activation= None))
#Force the encoding to live on the d-dimentional hypershpere
net.add(Lambda(lambda x: K.l2_normalize(x,axis=-1)))
return net
class TripletLossLayer(Layer):
def __init__(self, alpha, **kwargs):
self.alpha = alpha
super(TripletLossLayer, self).__init__(**kwargs)
def triplet_loss(self, inputs):
anchor, positive, negative = inputs
p_dist = K.sum(K.square(anchor-positive), axis=-1)
n_dist = K.sum(K.square(anchor-negative), axis=-1)
return K.sum(K.maximum(p_dist - n_dist + self.alpha, 0), axis=0)
def call(self, inputs):
loss = self.triplet_loss(inputs)
self.add_loss(loss)
return loss
def build_model(input_shape, network, margin=0.2):
'''
Define the Keras Model for training
Input :
input_shape : shape of input images
network : Neural network to train outputing embeddings
margin : minimal distance between Anchor-Positive and Anchor-Negative for the lossfunction (alpha)
'''
# Define the tensors for the three input images
anchor_input = Input(input_shape, name="anchor_input")
positive_input = Input(input_shape, name="positive_input")
negative_input = Input(input_shape, name="negative_input")
# Generate the encodings (feature vectors) for the three images
encoded_a = network(anchor_input)
encoded_p = network(positive_input)
encoded_n = network(negative_input)
#TripletLoss Layer
loss_layer = TripletLossLayer(alpha=margin,name='triplet_loss_layer')([encoded_a,encoded_p,encoded_n])
# Connect the inputs with the outputs
network_train = Model(inputs=[anchor_input,positive_input,negative_input],outputs=loss_layer)
# return the model
return network_train
def get_batch_random(batch_size,s="train"):
# initialize result
triplets=[np.zeros((batch_size,m)) for i in range(3)]
for i in range(batch_size):
#Pick one random class for anchor
anchor_class = np.random.randint(0, nb_classes)
nb_sample_available_for_class_AP = X[anchor_class].shape[0]
#Pick two different random pics for this class => A and P. You can use same anchor as P if there is one one element for anchor
if nb_sample_available_for_class_AP<=1:
continue
[idx_A,idx_P] = np.random.choice(nb_sample_available_for_class_AP,size=2 ,replace=False)
#Pick another class for N, different from anchor_class
negative_class = (anchor_class + np.random.randint(1,nb_classes)) % nb_classes
nb_sample_available_for_class_N = X[negative_class].shape[0]
#Pick a random pic for this negative class => N
idx_N = np.random.randint(0, nb_sample_available_for_class_N)
triplets[0][i,:] = X[anchor_class][idx_A,:]
triplets[1][i,:] = X[anchor_class][idx_P,:]
triplets[2][i,:] = X[negative_class][idx_N,:]
return np.array(triplets)
def get_batch_hard(draw_batch_size,hard_batchs_size,norm_batchs_size,network,s="train"):
if s == 'train':
X = train_in
else:
X = val
#m, features = X[0].shape
#while True:
#Step 1 : pick a random batch to study
studybatch = get_batch_random(draw_batch_size,X)
#Step 2 : compute the loss with current network : d(A,P)-d(A,N). The alpha parameter here is omited here since we want only to order them
studybatchloss = np.zeros((draw_batch_size))
#Compute embeddings for anchors, positive and negatives
A = network.predict(studybatch[0])
P = network.predict(studybatch[1])
N = network.predict(studybatch[2])
#Compute d(A,P)-d(A,N)
studybatchloss = np.sum(np.square(A-P),axis=1) - np.sum(np.square(A-N),axis=1)
#Sort by distance (high distance first) and take the
selection = np.argsort(studybatchloss)[::-1][:hard_batchs_size]
#Draw other random samples from the batch
selection2 = np.random.choice(np.delete(np.arange(draw_batch_size),selection),norm_batchs_size,replace=False)
selection = np.append(selection,selection2)
triplets = [studybatch[0][selection,:], studybatch[1][selection,:],studybatch[2][selection,:]]
triplets = triplets.reshape(triplets.shape[0],triplets.shape[1],triplets.shape[2])
yield triplets
network = build_network(input_shape,embeddingsize=10)
hard = get_batch_hard(5,4,1,network,s="train")
network_train = build_model(input_shape,network)
optimizer = Adam(lr = 0.00006)
network_train.compile(loss=None,optimizer=optimizer)
#this works
#history = network_train.fit(hard,epochs=100,steps_per_epoch=1, verbose=2)
history = network_train.fit_generator(hard,epochs=10,steps_per_epoch=16, verbose=2)
# error:: the list of Numpy arrays that you are passing to your model is not the size the model
expected. Expected to see 3 array(s), but instead got the following list of 1 arrays:
I think that's beacause in your generator you are yielding the 3 inputs array in one list, you need to yield the 3 arrays independently:
triplet_1 = studybatch[0][selection,:]
triplet_2 = studybatch[1][selection,:]
triplet_3 = studybatch[2][selection,:]
yield [triplet_1, triplet_2, triplet_3]

Calling a basic LSTM cell within a custom Tensorflow cell

I'm trying to implement the MATCH LSTM from this paper: https://arxiv.org/pdf/1608.07905.pdf
I'm using Tensorflow. One part of the architecture is an RNN that uses the input and the previous state to compute an attention vector which it applies to a context before concatenating the result with the inputs and sending them into an LSTM. To build the first part of this RNN, I wrote a custom cell for Tensorflow to call. But I'm not sure how to send the results into an LSTM. Is it possible to call the basic LSTM cell within the custom cell I'm writing? I tried this a few different ways but kept getting the error "module' object has no attribute 'rnn_cell'" at the line where the LSTM cell is called. Any help would be much appreciated!
EDIT to add code:
import numpy as np
import tensorflow as tf
class MatchLSTMCell(tf.contrib.rnn.RNNCell):
def __init__(self, state_size, question_tensor, encoded_questions, batch_size):
self._state_size = state_size
self.question_tensor = question_tensor
self.encoded_questions = encoded_questions
self.batch_size = batch_size
#property
def state_size(self):
return self._state_size
#property
def output_size(self):
return self._state_size
def __call__(self, inputs, state, scope=None):
scope = scope or type(self).__name__
with tf.variable_scope(scope):
W_p = tf.get_variable("W_p", dtype=tf.float64, shape=[self.state_size, self.state_size], initializer=tf.contrib.layers.xavier_initializer())
W_r = tf.get_variable("W_r", dtype=tf.float64, shape=[self.state_size, self.state_size], initializer=tf.contrib.layers.xavier_initializer())
b_p = tf.get_variable("b_p", dtype=tf.float64, shape=[self.state_size])
w = tf.get_variable("w", dtype=tf.float64, shape=[1,self.state_size])
b = tf.get_variable("b", dtype=tf.float64, shape=[])
#print 'question tensor', np.shape(self.question_tensor)
#print 'inputs', np.shape(inputs)
#print 'insides', np.shape(tf.matmul(inputs, W_p) + tf.matmul(state, W_r) + b_p)
G = tf.nn.tanh(
tf.transpose(tf.transpose(self.question_tensor, perm=[1,0,2]) +
(tf.matmul(inputs, W_p) + tf.matmul(state, W_r) + b_p), perm=[1,0,2])
)
#print 'big G', np.shape(G)
attention_list = []
for i in range(self.batch_size):
attention_matrix = tf.matmul(G[i,:,:], tf.transpose(w))
attention_list.append(attention_matrix)
attention_scores = tf.stack(attention_list)
a = tf.nn.softmax(attention_scores + b)
a = tf.reshape(a, [self.batch_size, -1])
#print 'a shape is', np.shape(a)
weighted_question_list = []
for i in range(self.batch_size):
attention_vector = tf.matmul(tf.reshape(a[i], [1,-1]), self.encoded_questions[i])
weighted_question_list.append(attention_vector)
weighted_questions = tf.stack(weighted_question_list)
weighted_questions = tf.reshape(weighted_questions, [32, -1])
#print'weighted questions', np.shape(weighted_questions)
z = tf.concat([inputs, weighted_questions], 1)
lstm_cell = tf.nn.rnn_cell.LSTMCell(self.state_size)
output, new_state = lstm_cell.__call__(z, state)
return output, new_state
I'm also trying to reimplement Match_LSTM for Squad for experiment.
I use MurtyShikhar's as reference. It works! However, he had to customize AttentionWrapper and use existed BasicLSTM cell.
I also try to create a Match_LSTM_cell by putting z and state as (inputs,state) pair in Basic_LSTM:
def __call__(self, inputs,state):
#c is not a output. c somehow is a "memory keeper".
#Necessary to update and pass new_c through LSTM
c,h=state
#...Calculate your z
#...inputs will be each tokens in context(passage) respectively
#...Calculate alpha_Q
z=tf.concat([inputs,alpha_Q],axis=1)
########This part is reimplement of Basic_LSTM
with vs.variable_scope("LSTM_core"):
sigmoid=math_ops.sigmoid
concat=_linear([z,h],dimension*4,bias=True)
i,j,f,o=array_ops.split(concat,num_or_size_splits=4,axis=1)
new_c=(c*sigmoid(f+self._forget_bias)+sigmoid(i)*self._activation(j))
new_h = self._activation(new_c) * sigmoid(o)
new_state=(new_c,new_h)
return new_h,new_state

KeyError in Tensorflow when calling predict on trained model

I have trained a LinearRegressor with two features: x,y and the label: l
def train_input_fn():
x = [1,2,3,4]
y = [2,3,4,5]
feature_cols = tf.constant(x)
labels = tf.constant(y)
return feature_cols, labels
x = tf.contrib.layers.real_valued_column("x")
y = tf.contrib.layers.real_valued_column("y")
m = tf.contrib.learn.LinearRegressor(feature_columns=[ x,y],
model_dir=model_dir)
m.fit(input_fn=train_input_fn, steps=100)
After training I want to predict from two new values
new_sample = np.array([20,20])
m.predict(new_sample)
but I get this error message when calling predict
File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/layers/python/layers/feature_column.py", line 870, in insert_transformed_feature
input_tensor = columns_to_tensors[self.name]
KeyError: 'x'
Does anyone know why I get KeyError?
Try this:
my_feature_columns = [tf.contrib.layers.real_valued_column("", dimension=2)]
m = tf.contrib.learn.LinearRegressor(feature_columns=my_feature_columns,
model_dir=model_dir)
m.fit(input_fn=train_input_fn, steps=100)
I am not an expert in Tensorflow but this works for me:
new_sample = np.array([20,20],dtype='float32')
empty_y = np.zeros(len(new_sample),dtype='float32')
prediction_x = tf.contrib.learn.io.numpy_input_fn({"x":new_sample},empty_y, batch_size=45, num_epochs=100)
forecast = list(estimator.predict(input_fn=prediction_x,as_iterable=False))