I'm going to learn data with 3Dtensor input.
My model is
from keras.models import Sequential
from keras.layers import Dense, InputLayer
import tensorflow as tf
from tensorflow import keras
class AnomalyDetector(Model):
def __init__(self):
super(AnomalyDetector, self).__init__()
self.encoder = tf.keras.Sequential([
tf.keras.layers.Dense(32,input_shape=(36,501), activation= "relu"),
tf.keras.layers.Dense(16, activation= "relu"),
tf.keras.layers.Dense(8, activation= "relu")
])
self.decoder = tf.keras.Sequential([
tf.keras.layers.Dense(16,input_shape=(36,501), activation= "relu"),
tf.keras.layers.Dense(32, activation= "relu"),
tf.keras.layers.Dense(140, activation= "sigmoid")
])
def call(self,x):
encoded = self.encoder(x)
decoded = self.decoder(encoded)
return decoded
model = AnomalyDetector()
The shape of the 3dtensor is
(1500, 36, 501)
model.compile(optimizer='adam', loss='mae', metrics=['accuracy'])
model.fit(train_X, train_y, epochs=100, batch_size = 512, validation_data=(vali_X, vali_y), shuffle=True)
and Error is...
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Input In [155], in <cell line: 12>()
9 print(e)
11 model.compile(optimizer='adam', loss='mae', metrics=['accuracy'])
---> 12 model.fit(train_X, train_y, epochs=100, batch_size = 512, validation_data=(vali_X, vali_y), shuffle=True)
.
.
.
ValueError: Input 0 of layer "sequential_58" is incompatible with the layer: expected shape=(None, 36, 501), found shape=(None, 36, 8)
Call arguments received by layer "anomaly_detector_30" (type AnomalyDetector):
• x=tf.Tensor(shape=(None, 36, 501), dtype=float32)
I already change encoder's Dense 8 to 501. but another error occurred.
How should I change this?
Dense doesn't take 3d input it takes 1d input for example :
input_shape = ( ,40) here 40 is the number of columns and i left a space because at start your model dosen't knows the length of data that's why in model.summary()
input_shape = (None,40) comes.
Is your input an image ?? if yes than Dense dosen't work on image use Conv2D or Conv3D as per your input data.
If i am wrong and Dense layer takes 3d input, correct me and please provide the link where you read about it.Thanks
Your problem is in the input of your decoder. The decoder sets to get tensors of size (36,501) but it gets the output of the encoder that is a tensor of size (36,8) if you change your decoder input your code work :
class AnomalyDetector(tf.keras.Model):
def __init__(self):
super(AnomalyDetector, self).__init__()
self.encoder = tf.keras.Sequential([
tf.keras.layers.Dense(32,input_shape=(36,501), activation= "relu"),
tf.keras.layers.Dense(16, activation= "relu"),
tf.keras.layers.Dense(8, activation= "relu")
])
self.decoder = tf.keras.Sequential([
tf.keras.layers.Dense(16,input_shape=(36,8), activation= "relu"),
tf.keras.layers.Dense(32, activation= "relu"),
tf.keras.layers.Dense(140, activation= "sigmoid")
])
def call(self,x):
encoded = self.encoder(x)
decoded = self.decoder(encoded)
return decoded
But be careful your encoder just embeds the second size of (Y) your image. I think you should flatten the image for your first layer which means something like this :
class AnomalyDetector(tf.keras.Model):
def __init__(self):
super(AnomalyDetector, self).__init__()
self.encoder = tf.keras.Sequential([
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(32, activation= "relu"),
tf.keras.layers.Dense(16, activation= "relu"),
tf.keras.layers.Dense(8, activation= "relu")
])
self.decoder = tf.keras.Sequential([
tf.keras.layers.Dense(16, activation= "relu"),
tf.keras.layers.Dense(32, activation= "relu"),
tf.keras.layers.Dense(140, activation= "sigmoid")
])
def call(self,x):
encoded = self.encoder(x)
decoded = self.decoder(encoded)
return decoded
Related
Currently I am trying to develop a multichannel CNN model for text classification. I am using the imdb dataset. I have vectorized the layer and transformed it into a tensor. The problem is that I don't know why the model fit method is not working.
The error message says:
ValueError: Failed to find data adapter that can handle input: (<class
'list'> containing values of types {"<class
'tensorflow.python.data.ops.dataset_ops.MapDataset'>"}), <class
'NoneType'>
Code for creating a channel.
# channel 1
inputs1 = tf.keras.Input(shape=(length,))
embedding1 = tf.keras.layers.Embedding(vocab_size, 100)(inputs1)
conv1 = tf.keras.layers.Conv1D(filters=32, kernel_size=4, activation='relu')(embedding1)
drop1 = tf.keras.layers.Dropout(0.5)(conv1)
pool1 = tf.keras.layers.MaxPool1D(pool_size=2)(drop1)
flat1 = tf.keras.layers.Flatten()(pool1)
# channel 2
inputs2 = tf.keras.Input(shape=(length,))
embedding2 = tf.keras.layers.Embedding(vocab_size, 100)(inputs2)
conv2 = tf.keras.layers.Conv1D(filters=32, kernel_size=6, activation='relu')(embedding2)
drop2 = tf.keras.layers.Dropout(0.5)(conv2)
pool2 = tf.keras.layers.MaxPooling1D(pool_size=2)(drop2)
flat2 = tf.keras.layers.Flatten()(pool2)
# channel 3
inputs3 = tf.keras.Input(shape=(length,))
embedding3 = tf.keras.layers.Embedding(vocab_size, 100)(inputs3)
conv3 = tf.keras.layers.Conv1D(filters=32, kernel_size=8, activation='relu')(embedding3)
drop3 = tf.keras.layers.Dropout(0.5)(conv3)
pool3 = tf.keras.layers.MaxPooling1D(pool_size=2)(drop3)
flat3 = tf.keras.layers.Flatten()(pool3)
# merge
merged = tf.keras.layers.concatenate([flat1, flat2, flat3])
print(type(merged))
# # interpretation
dense1 = tf.keras.layers.Dense(10, activation='relu')(merged)
outputs = tf.keras.layers.Dense(1, activation='sigmoid')(dense1)
model = tf.keras.Model(inputs=[inputs1, inputs2, inputs3], outputs=outputs)
# compile
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
# summarize
model.summary()
history = model.fit(
[train_dataset,train_dataset,train_dataset],
epochs=10,
batch_size=16)
Please have a look at the google colab: link
I am getting an error when trying to save a model with data augmentation layers with Tensorflow version 2.7.0.
Here is the code of data augmentation:
input_shape_rgb = (img_height, img_width, 3)
data_augmentation_rgb = tf.keras.Sequential(
[
layers.RandomFlip("horizontal"),
layers.RandomFlip("vertical"),
layers.RandomRotation(0.5),
layers.RandomZoom(0.5),
layers.RandomContrast(0.5),
RandomColorDistortion(name='random_contrast_brightness/none'),
]
)
Now I build my model like this:
# Build the model
input_shape = (img_height, img_width, 3)
model = Sequential([
layers.Input(input_shape),
data_augmentation_rgb,
layers.Rescaling((1./255)),
layers.Conv2D(16, kernel_size, padding=padding, activation='relu', strides=1,
data_format='channels_last'),
layers.MaxPooling2D(),
layers.BatchNormalization(),
layers.Conv2D(32, kernel_size, padding=padding, activation='relu'), # best 4
layers.MaxPooling2D(),
layers.BatchNormalization(),
layers.Conv2D(64, kernel_size, padding=padding, activation='relu'), # best 3
layers.MaxPooling2D(),
layers.BatchNormalization(),
layers.Conv2D(128, kernel_size, padding=padding, activation='relu'), # best 3
layers.MaxPooling2D(),
layers.BatchNormalization(),
layers.Flatten(),
layers.Dense(128, activation='relu'), # best 1
layers.Dropout(0.1),
layers.Dense(128, activation='relu'), # best 1
layers.Dropout(0.1),
layers.Dense(64, activation='relu'), # best 1
layers.Dropout(0.1),
layers.Dense(num_classes, activation = 'softmax')
])
model.compile(loss='categorical_crossentropy', optimizer='adam',metrics=metrics)
model.summary()
Then after the training is done I just make:
model.save("./")
And I'm getting this error:
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-84-87d3f09f8bee> in <module>()
----> 1 model.save("./")
/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py in
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
/usr/local/lib/python3.7/dist-
packages/tensorflow/python/saved_model/function_serialization.py in
serialize_concrete_function(concrete_function, node_ids, coder)
66 except KeyError:
67 raise KeyError(
---> 68 f"Failed to add concrete function '{concrete_function.name}' to
object-"
69 f"based SavedModel as it captures tensor {capture!r} which is
unsupported"
70 " or not reachable from root. "
KeyError: "Failed to add concrete function
'b'__inference_sequential_46_layer_call_fn_662953'' to object-based SavedModel as it
captures tensor <tf.Tensor: shape=(), dtype=resource, value=<Resource Tensor>> which
is unsupported or not reachable from root. One reason could be that a stateful
object or a variable that the function depends on is not assigned to an attribute of
the serialized trackable object (see SaveTest.test_captures_unreachable_variable)."
I inspected the reason of getting this error by changing the architecture of my model and I just found that reason came from the data_augmentation layer since the RandomFlip and RandomRotation and others are changed from layers.experimental.prepocessing.RandomFlip to layers.RandomFlip, but still the error appears.
This seems to be a bug in Tensorflow 2.7 when using model.save combined with the parameter save_format="tf", which is set by default. The layers RandomFlip, RandomRotation, RandomZoom, and RandomContrast are causing the problems, since they are not serializable. Interestingly, the Rescaling layer can be saved without any problems. A workaround would be to simply save your model with the older Keras H5 format model.save("test", save_format='h5'):
import tensorflow as tf
import numpy as np
class RandomColorDistortion(tf.keras.layers.Layer):
def __init__(self, contrast_range=[0.5, 1.5],
brightness_delta=[-0.2, 0.2], **kwargs):
super(RandomColorDistortion, self).__init__(**kwargs)
self.contrast_range = contrast_range
self.brightness_delta = brightness_delta
def call(self, images, training=None):
if not training:
return images
contrast = np.random.uniform(
self.contrast_range[0], self.contrast_range[1])
brightness = np.random.uniform(
self.brightness_delta[0], self.brightness_delta[1])
images = tf.image.adjust_contrast(images, contrast)
images = tf.image.adjust_brightness(images, brightness)
images = tf.clip_by_value(images, 0, 1)
return images
def get_config(self):
config = super(RandomColorDistortion, self).get_config()
config.update({"contrast_range": self.contrast_range, "brightness_delta": self.brightness_delta})
return config
input_shape_rgb = (256, 256, 3)
data_augmentation_rgb = tf.keras.Sequential(
[
tf.keras.layers.RandomFlip("horizontal"),
tf.keras.layers.RandomFlip("vertical"),
tf.keras.layers.RandomRotation(0.5),
tf.keras.layers.RandomZoom(0.5),
tf.keras.layers.RandomContrast(0.5),
RandomColorDistortion(name='random_contrast_brightness/none'),
]
)
input_shape = (256, 256, 3)
padding = 'same'
kernel_size = 3
model = tf.keras.Sequential([
tf.keras.layers.Input(input_shape),
data_augmentation_rgb,
tf.keras.layers.Rescaling((1./255)),
tf.keras.layers.Conv2D(16, kernel_size, padding=padding, activation='relu', strides=1,
data_format='channels_last'),
tf.keras.layers.MaxPooling2D(),
tf.keras.layers.BatchNormalization(),
tf.keras.layers.Conv2D(32, kernel_size, padding=padding, activation='relu'), # best 4
tf.keras.layers.MaxPooling2D(),
tf.keras.layers.BatchNormalization(),
tf.keras.layers.Conv2D(64, kernel_size, padding=padding, activation='relu'), # best 3
tf.keras.layers.MaxPooling2D(),
tf.keras.layers.BatchNormalization(),
tf.keras.layers.Conv2D(128, kernel_size, padding=padding, activation='relu'), # best 3
tf.keras.layers.MaxPooling2D(),
tf.keras.layers.BatchNormalization(),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(128, activation='relu'), # best 1
tf.keras.layers.Dropout(0.1),
tf.keras.layers.Dense(128, activation='relu'), # best 1
tf.keras.layers.Dropout(0.1),
tf.keras.layers.Dense(64, activation='relu'), # best 1
tf.keras.layers.Dropout(0.1),
tf.keras.layers.Dense(5, activation = 'softmax')
])
model.compile(loss='categorical_crossentropy', optimizer='adam')
model.summary()
model.save("test", save_format='h5')
Loading your model with your custom layer would look like this then:
model = tf.keras.models.load_model('test.h5', custom_objects={'RandomColorDistortion': RandomColorDistortion})
where RandomColorDistortion is the name of your custom layer.
You can also downgrade Keras and Tensorflow to version 2.6.
I am getting a ValueError: logits and labels must have the same shape ((None, 1) vs ()) when doing a model evaluate. I get the model to train but when I evaluate is when I have the problem. I used a tf.expand_dims for logits but wondering if this needs to be applied to the labels as well?
here is my code below.
import tensorflow as tf
import tensorflow_datasets as tfds
dataset, info = tfds.load('imdb_reviews', with_info=True,
as_supervised=True)
train_dataset, test_dataset = dataset['train'], dataset['test']
BUFFER_SIZE = 10000
BATCH_SIZE = 64
train_dataset = train_dataset.shuffle(BUFFER_SIZE).batch(BATCH_SIZE).prefetch(1)
VOCAB_SIZE, EMBED_SIZE, NUM_OOV_BUCKETS = 10000, 128, 1000
encoder = tf.keras.layers.experimental.preprocessing.TextVectorization(
max_tokens=VOCAB_SIZE)
encoder.adapt(train_dataset.map(lambda text, label: text))
class AttentionLayer(tf.keras.layers.Layer):
def __init__(self, **kwargs):
super(AttentionLayer, self).__init__(**kwargs)
self.query_layer = tf.keras.layers.Conv1D(
filters=100,
kernel_size=4,
padding='same'
)
self.value_layer = tf.keras.layers.Conv1D(
filters=100,
kernel_size=4,
padding='same'
)
self.attention_layer = tf.keras.layers.Attention()
def call(self, inputs):
query = self.query_layer(inputs)
value = self.value_layer(inputs)
attention = self.attention_layer([query, value])
return tf.keras.layers.concatenate([query, attention])
attention_layer = AttentionLayer()
model1 = tf.keras.models.Sequential([
tf.keras.Input(shape=(),batch_size=1, dtype=tf.string, name='InputLayer'),
encoder,
tf.keras.layers.Embedding(VOCAB_SIZE + NUM_OOV_BUCKETS, EMBED_SIZE, mask_zero=True, name='Embedding_Layer'),
attention_layer,
tf.keras.layers.Conv1D(filters=32, kernel_size=4, padding = 'same', activation = 'relu', name='Conv1DLayer'),
tf.keras.layers.MaxPooling1D(pool_size=2, name='MaxPoolLayer'),
tf.keras.layers.LSTM(64, dropout = 0.2, name='DropoutLayer'),
tf.keras.layers.Dense(250, activation = 'relu', name='DenseLayer'),
tf.keras.layers.Dense(1, activation='sigmoid', name='Output_Layer')
])
model.compile(loss="binary_crossentropy", optimizer="adam", metrics=["accuracy"])
def preprocess_y(x, y):
return x, tf.expand_dims(y, -1)
history1 = model1.fit(
train_dataset.map(preprocess_y),
batch_size=BATCH_SIZE,
epochs=1)
model1.evaluate(test_dataset)
ValueError: logits and labels must have the same shape ((None, 1) vs ())
I wanted to use this model but we cannot use merge anymore.
image_model = Sequential([
Dense(embedding_size, input_shape=(2048,), activation='relu'),
RepeatVector(max_len)
])
caption_model = Sequential([
Embedding(vocab_size, embedding_size, input_length=max_len),
LSTM(256, return_sequences=True),
TimeDistributed(Dense(300))
])
final_model = Sequential([
Merge([image_model, caption_model], mode='concat', concat_axis=1),
Bidirectional(LSTM(256, return_sequences=False)),
Dense(vocab_size),
Activation('softmax')
])
i rewrote this in following way,excluding final_model:
image_in = Input(shape=(2048,))
caption_in = Input(shape=(max_len, vocab_size))
merged = concatenate([image_model(image_in), caption_model(caption_in)],axis=0)
latent = Bidirectional(LSTM(256, return_sequences=False))(merged)
out = Dense(vocab_size, activation='softmax')(latent)
final_model = Model([image_in, caption_in], out)
final_model.compile(loss='categorical_crossentropy', optimizer=RMSprop(), metrics=['accuracy'])
final_model.summary()
This also gave me:
ValueError: "input_length" is 40, but received input has shape (None, 40, 8256).
Can anyone help to fix it?
source:https://github.com/yashk2810/Image-Captioning/blob/master/Image%20Captioning%20InceptionV3.ipynb
you should define the caption_in as 2D: Input(shape=(max_len,)). in your case, the concatenation must be operated on the last axis: axis=-1. the rest seems ok
embedding_size=300
max_len=40
vocab_size=8256
image_model = Sequential([
Dense(embedding_size, input_shape=(2048,), activation='relu'),
RepeatVector(max_len)
])
caption_model = Sequential([
Embedding(vocab_size, embedding_size, input_length=max_len),
LSTM(256, return_sequences=True),
TimeDistributed(Dense(300))
])
image_in = Input(shape=(2048,))
caption_in = Input(shape=(max_len,))
merged = concatenate([image_model(image_in), caption_model(caption_in)],axis=-1)
latent = Bidirectional(LSTM(256, return_sequences=False))(merged)
out = Dense(vocab_size, activation='softmax')(latent)
final_model = Model([image_in, caption_in], out)
final_model.compile(loss='categorical_crossentropy', optimizer=RMSprop(), metrics=['accuracy'])
final_model.summary()
As pointed out by Marco, the issue had to do with the input_length parameter. You can join the two models as such:
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import *
import tensorflow as tf
from numpy.random import randint
embedding_size = 300
max_len = 40
vocab_size = 8256
image_model = Sequential([
Dense(embedding_size, input_shape=(2048,), activation='relu'),
RepeatVector(max_len)
])
caption_model = Sequential([
Embedding(vocab_size, embedding_size, input_length=max_len),
LSTM(256, return_sequences=True),
TimeDistributed(Dense(300))
])
class MyModel(tf.keras.Model):
def __init__(self, image, caption):
super(MyModel, self).__init__()
self.image = image
self.caption = caption
self.concatenate = Concatenate()
self.lstm = Bidirectional(LSTM(256, return_sequences=False))
self.dense = Dense(vocab_size, activation='softmax')
def call(self, inputs, training=None, **kwargs):
a = self.image(inputs['image'])
b = self.caption(inputs['caption'])
x = self.concatenate([a, b])
x = self.lstm(x)
x = self.dense(x)
return x
model = MyModel(image_model, caption_model)
model({'image': randint(0, 10, (1, 2048)),
'caption': randint(0, 100, (1, 40))})
<tf.Tensor: shape=(1, 8256), dtype=float32, numpy=
array([[0.00011554, 0.00014183, 0.00011184, ..., 0.0001064 , 0.00014344,
0.00012491]], dtype=float32)>
I am trying to do Author Identification, my train_vecs_w2v.shape = (15663, 400).
y_train.shape = (15663,3) which has 3 label one hot encoded.
Now the problem is I am having an error in the Embedding layer. Indices[0,X] = -1 is not in [0, 15663). How to solve this? Is it my code or Keras/Tensorflow?
print('Building Model')
n=19579
max_features = 15663
max_length = 400
EMBEDDING_DIM = 100
model7 = Sequential()
model7.add(Embedding(len(train_vecs_w2v), EMBEDDING_DIM, input_length=max_length, dtype='float32', trainable=True, weights=None, embeddings_initializer='uniform', embeddings_regularizer=None, activity_regularizer=None, embeddings_constraint=None))
print(model7.output_shape)
model7.add(Convolution1D(filters =128, kernel_size = 3, strides=1, activation='relu', use_bias=False, border_mode='same'))
print(model7.output_shape)
model7.add(MaxPooling1D(pool_size = 3))
print(model7.output_shape)
model7.add(Convolution1D(filters = 64, kernel_size = 5, strides=1, activation='relu', border_mode='same'))
print(model7.output_shape)
model7.add(MaxPooling1D(pool_size = 5))
print(model7.output_shape)
model7.add(Flatten()) # model.output_shape == (None, 64*input_shape of convolution layer)
print(model7.output_shape)
model7.add(Dense(output_dim = 64, activation='relu')) # input_shape = (batch_size, input_dim)
print(model7.output_shape)
model7.add(Dense(output_dim = 32, activation='relu'))
print(model7.output_shape)
model7.add(Dense(output_dim = 3, activation='softmax'))
model7.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['categorical_accuracy'])
model7.fit(train_vecs_w2v, y_train_vec, epochs=50, batch_size=32, verbose=2)
The error I am getting
InvalidArgumentError (see above for traceback): indices[0,1] = -1 is not in [0, 15663)
[[Node: embedding_1/Gather = Gather[Tindices=DT_INT32, Tparams=DT_FLOAT, validate_indices=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](embedding_1/embeddings/read, embedding_1/Cast)]]
I think the problem here is with the word vectors count.
It should be
len(train_vecs_w2v) + 1