We Keep Coding

Tensorflow expected 2 inputs but received 1 input tensor

Hey guys so I'm building a model based on the Roberta-Base and at the end when I try to fit the model I get a error saying: ValueError: Layer model_39 expects 2 input(s), but it received 1 input tensors. Inputs received: [<tf.Tensor 'IteratorGetNext:0' shape=(16, 128) dtype=float64>]
I'm using tf.data.Dataset to make the dataset:
def map_dataset(ids, masks, labels):
return {'input_ids': ids, 'input_mask': masks}, labels
# Create dataset
dataset = tf.data.Dataset.from_tensor_slices((ids, mask, labels))
dataset.map(map_dataset)
dataset = dataset.shuffle(10000).batch(BATCH_SIZE, drop_remainder=True)
Supposedly dataset is generating 2 inputs properly but for some reason fit is refusing to work and I'm not sure why.
Full code:
LEN_SEQ = 128
BATCH_SIZE = 16
TEST_TRAIN_SPLIT = 0.9
TRANSFORMER = 'roberta-base'
# Load roberta model
base_model = TFAutoModel.from_pretrained('roberta-base')
for layer in base_model.layers:
layer.trainable = False
# Define input layers
input_ids = tf.keras.layers.Input(shape=(LEN_SEQ,), name='input_ids', dtype='int32')
input_mask = tf.keras.layers.Input(shape=(LEN_SEQ,), name='input_mask', dtype='int32')
# Define hidden layers
embedding = base_model([input_ids, input_mask])[1]
layer = tf.keras.layers.Dense(LEN_SEQ * 2, activation='relu')(embedding)
layer = tf.keras.layers.Dense(LEN_SEQ, activation='relu')(layer)
# Define output
output = tf.keras.layers.Dense(1, activation='softmax', name='output')(layer)
model = tf.keras.Model(inputs=[input_ids, input_mask], outputs=[output])
model.compile(
optimizer = Adam(learning_rate=1e-3, decay=1e-4),
loss = CategoricalCrossentropy(),
metrics = [
CategoricalAccuracy('accuracy')
]
)
# Load data
df = pd.read_csv('train-processed.csv')
df = df.head(100)
samples_count = len(df)
# Tokenize data
tokenizer = AutoTokenizer.from_pretrained(TRANSFORMER)
tokens = tokenizer(
df['first_Phrase'].tolist(),
max_length=LEN_SEQ,
truncation=True,
padding='max_length',
add_special_tokens=True,
return_tensors='tf'
)
ids = tokens['input_ids']
mask = tokens['attention_mask']
def map_dataset(ids, masks, labels):
return {'input_ids': ids, 'input_mask': masks}, labels
# Create dataset
dataset = tf.data.Dataset.from_tensor_slices((ids, mask, labels))
dataset.map(map_dataset)
dataset = dataset.shuffle(10000).batch(BATCH_SIZE, drop_remainder=True)
# Split data intro train and test
train_size = int((samples_count / BATCH_SIZE) * TEST_TRAIN_SPLIT)
train = dataset.take(train_size)
test = dataset.skip(train_size)
# Train model
history = model.fit(
train,
validation_data=test,
epochs=2
)
Inside dataset -> <BatchDataset shapes: ((16, 128), (16, 128), (16, 5)), types: (tf.float64, tf.float64, tf.float64)>
Inside train -> <TakeDataset shapes: ((16, 128), (16, 128), (16, 5)), types: (tf.float64, tf.float64, tf.float64)>
Data example:
Any help appreciated. I'm new to transformers so please feel free to point any extra considerations.

So I managed to fix this as far as I know with the help of #Djinn.
I did remove dataset API and instead built my own datasets manually using the following code:
# Split into training and validation sets
train_size = int(samples_count * TEST_TRAIN_SPLIT)
train = [ids[:train_size], mask[:train_size]]
train_labels = labels[:train_size]
test = [ids[train_size:], mask[train_size:]], labels[train_size:]
# Train model
history = model.fit(
train, train_labels,
validation_data=test,
epochs=10
)
This seems to be working and fit() accepted this data, but feel free to point out if this is wrong or could be made differently.

Issue retrieiving value error `decode_predictions` expects a batch of predictions

I have the following code trying to perform predictions on part of resnet model. However, I am retrieving error.
def layer_input_shape(Model, layer_index):
input_shape = np.array(Model.layers[layer_index - 1].output_shape)
input_shape = np.ndarray.tolist(np.delete(input_shape, 0))
return input_shape
def resnet50_Model(Model, trainable=True):
input_shape = layer_input_shape(Model, 1)
input = tf.keras.layers.Input(shape=input_shape)
first_layer = Model.layers[0]
first_layer.trainable = trainable
out = first_layer(input)
for i in range(1, 12):
layer_i = Model.layers[i]
layer_i.trainable = trainable
out = layer_i(out)
out = Conv2D(filters=2, kernel_size=2, strides=(2,2), activation='relu')(out)
out = Flatten()(out)
out = Dense(units=2,activation='softmax')(out)
result_model = tf.keras.models.Model(inputs=[input], outputs=out)
return result_model
from tensorflow.keras.applications.resnet50 import preprocess_input, decode_predictions
img='/content/elephant.jpg'
img = image.load_img(img, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
preds = resnet_skip_model.predict(x)
print('Predicted:', decode_predictions(preds, top=3)[0])
Retrieving below error:
ValueError: `decode_predictions` expects a batch of predictions (i.e. a 2D array of shape (samples,
1000)). Found array with shape: (1, 3)

I added two output dense layer so I can only predict two classes and when I call decode it expects 1000 output last dense layer, therefore changed units from two to 1000
out = Dense(units=1000,activation='softmax')(out)

Using fit_generator with multiple inputs gives error at output dense layer

In my case I am using a set of sequential features and also non sequential features to train the model. Following is the architecture of my model
Sequential features -> LSTM -> Dense(1) --->>
\
\
-- Dense -> Dense -> Dense(1) ->output
/
Non-sequential features---/
I am using data generator to generate batches for sequential data. Here the batch size is varying for each batch. For one batch I am keeping the non-sequential feature fixed. Following is my data generator.
def training_data_generator(raw_data):
while True:
for index, row in raw_data.iterrows():
x_train, y_train = list(), list()
feature1 = row['xxx']
x_current_batch = []
y_current_batch = []
for j in range(yyy):
x_current_batch.append(row['zz1'])
y_current_batch.append(row['zz2'])
x_train.append(x_current_batch)
y_train.append(y_current_batch)
x_train = array(x_train)
y_train = array(y_train)
yield [x_train, np.reshape(feature1,1)], y_train
Note: x_train y_train sizes are varying.
Following is my model implementation.
seq_input = Input(shape=(None, 3))
lstm_layer = LSTM(50)(seq_input)
dense_layer1 = Dense(1)(lstm_layer)
non_seq_input = Input(shape=(1,))
hybrid_model = concatenate([dense_layer1, non_seq_input])
hidden1 = Dense(10, activation = 'relu')(hybrid_model)
hidden2 = Dense(10, activation='relu')(hidden1)
final_output = Dense(1, activation='sigmoid')(hidden2)
model = Model(inputs = [seq_input, non_seq_input], outputs = final_output)
model.compile(loss='mse',optimizer='adam')
model.fit_generator(training_data_generator(flatten), steps_per_epoch= 5017,
epochs = const.NUMBER_OF_EPOCHS, verbose=1)
I am getting error at the output dense layer
ValueError: Error when checking target:
expected dense_4 to have shape (1,) but got array with shape (4,)
I think the last layer is getting whole output of the generator but not as one by one.
What is the reason for this issue. Appreciate your insights on this issue.

The output gives a Dense layer with a size of 4. Since you've declared your output as a Dense layer with a size of 1, it crashes.
What you can do is change your output dense Layer to 4. And then manually convert this to one value.
Hopefully this answers your question.

How to fix - "ValueError: Input arrays should have the same number of samples as target arrays. Found 8 input samples and 33984 target samples."

I'm trying to fit RNN model on top of my data but it shows an input error : ValueError: Input arrays should have the same number of samples as target arrays. Found 8 input samples and 33984 target samples.
Attaching screenshot for reference.
https://drive.google.com/open?id=1UjO7yQjD2_52PhTLYAYoZGfQsl1bboSW
https://drive.google.com/open?id=13k2sUvEVYoJGV7bR_dxh25C-sC8Tva0L
def RNN():
inputs = Input(name='inputs',shape=[max_len])
layer = Embedding(max_words,50,input_length=max_len)(inputs)
layer = LSTM(64)(layer)
layer = Dense(256,name='FC1')(layer)
layer = Activation('relu')(layer)
layer = Dropout(0.5)(layer)
layer = Dense(1,name='out_layer')(layer)
layer = Activation('sigmoid')(layer)
model = Model(inputs=inputs,outputs=layer)
return model
model = RNN()
model.summary()
model.compile(loss='binary_crossentropy',optimizer=RMSprop(),metrics=['accuracy'])
model.fit(sequences_matrix,y_train,batch_size=128,epochs=10,
validation_split=0.2,callbacks= [EarlyStopping(monitor='val_loss',min_delta=0.0001)])
The shape of my data that i'm trying to fit into the run model:
X_train.shape = (33984, 8)
y_train.shape = (33984,)
X_test.shape = (14565, 8)
y_test.shape = (14565,)

Keras - Issues with tensors shape with TensorFlow backend

I am trying to transform a TensorFlow script into Keras. I have a classification model which predicts the presence of digits and 4 digits. I have two different losses and two outputs: one for the presence and one for the digits.
This is my model :
def get_training_model2():
inp, x = convolutional_layers2()
x = Flatten()(x)
x = Dense(2048)(x)
x = Activation('relu')(x)
y = Dense(1+5*len(DIGITS), activation='softmax')(x)
out1 = Lambda(lambda a: a[:,:1])(y)
out2 = Lambda(lambda a: a[:,1:])(y)
model = Model(inp, [out1, out2])
return model
This is my digit loss :
def digits_loss(y_true, y_pred):
digits_loss = losses.sparse_categorical_crossentropy(K.reshape(y_true, [-1, len(DIGITS)]),
K.reshape(y_pred, [-1, len(DIGITS)]))
digits_loss = np.sum(digits_loss)
return digits_loss
# Target
target = [y_train[:,:1], y_train[:,1:]]
When I launch :
model = model_keras.get_training_model2()
opt = Adam(lr=learn_rate)
model.compile(loss=[presence_loss, digits_loss],
optimizer=opt,
metrics=['accuracy'])
model.fit(X_train, target, batch_size=50,
epochs=50 ...)
I have this error :
File "train_keras.py", line 96, in digits_loss
K.reshape(y_pred, [-1, len(DIGITS)]))
logits and labels must have the same first dimension, got logits shape [250,11] and labels shape [2750]
I don't understand why I have this error because I am reshaping both labels and logits in the same way. Moreover, I don't understand why the shape is [250,11] although it's should be [50, 11] (batch_size).
Thank you for any help.