I'm trying to make a Face Recognition app using insightface, I wrote this code on Tensorflow 2.1.0 and Keras 2.3.1 and it worked well but due to some issues I have to migrate to TensorFlow 2.2.0 and Keras 2.4.3, I understand that my problem is my embeddings. they are sparse but in a meaningful way. How can I avoid changing the meaningfulness for my embeddings and avoid the spares data? From the error, I understand (Consider casting elements to a supported type.) that TensorFlow can't convert my np.array to tensor because it is sparse.
what I tried
these arent the commands but I wrote them so you would have a notion of what I tried. np.array(data["embeddings"]).todense(),csr_matrix(data["embeddings"]), tf.convert_to_tensor(data["embeddings"]) and also tried to follow along this but couldn't get to model.fit_generator work.
>>> print(type(embeddings))
<class 'numpy.ndarray'>
>>> print(embeddings.shape)
(49, 512)
>>> print(embeddings)
[[ 0.02751185 0.0143353 0.0324492 ... -0.00347222 0.0154978
-0.01304669]
[ 0.09154768 -0.04196533 0.01197386 ... -0.08363352 0.03335601
0.01748604]
[ 0.00182035 -0.00307933 0.00386595 ... -0.04442558 0.04434329
0.06080627]
...
[-0.01564891 -0.01510727 0.0345119 ... -0.01690779 -0.00816008
0.08056415]
[-0.00543963 -0.03811216 -0.01148985 ... -0.05366111 0.07108331
-0.00186215]
[ 0.00627459 -0.04221528 0.00426272 ... 0.02838095 0.02116473
0.00491964]]
This is my code:
class SoftMax():
def __init__(self, input_shape, num_classes):
self.input_shape = input_shape
self.num_classes = num_classes
def build(self):
#create model
model = Sequential()
#add model layers
model.add(Dense(1024, activation='relu', input_shape=self.input_shape))
model.add(Dropout(0.5))
model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(self.num_classes, activation='softmax'))
# loss and optimizer
optimizer=Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, amsgrad=False)
model.compile(loss=categorical_crossentropy,
optimizer=optimizer,
metrics=['accuracy'])
return model
def make_model(args, classifier=SoftMax):
# Load the face embeddings
data = pickle.loads(open(args.embeddings, "rb").read())
num_classes = len(np.unique(data["names"]))
ct = ColumnTransformer([('myŁName', OneHotEncoder(), [0])])
labels = np.array(data["names"]).reshape(-1, 1)
labels = ct.fit_transform(labels)
embeddings = np.array(data["embeddings"])
# Initialize Softmax training model arguments
BATCH_SIZE = 32
EPOCHS = 32
input_shape = embeddings.shape[1]
# Build classifier
init_classifier = classifier(input_shape=(input_shape,), num_classes=num_classes)
model = init_classifier.build()
# Create KFold
cv = KFold(n_splits = 5, random_state = None, shuffle=True)
history = {'acc': [], 'val_acc': [], 'loss': [], 'val_loss': []}
# Train
for train_idx, valid_idx in cv.split(embeddings):
X_train, X_val, y_train, y_val = embeddings[train_idx], embeddings[valid_idx], labels[train_idx], labels[valid_idx]
his = model.fit(X_train, y_train, batch_size=BATCH_SIZE, epochs=EPOCHS, verbose=1, validation_data=(X_val, y_val))
# write the face recognition model to output
model.save(args.mymodel)
f = open(args.le, "wb")
f.write(pickle.dumps(LabelEncoder()))
f.close()
Error
TypeError: Failed to convert object of type <class 'tensorflow.python.framework.sparse_tensor.SparseTensor'> to Tensor. Contents: SparseTensor(indices=Tensor("DeserializeSparse:0", shape=(None, 2), dtype=int64), values=Tensor("DeserializeSparse:1", shape=(None,), dtype=float32), dense_shape=Tensor("stack:0", shape=(2,), dtype=int64)). Consider casting elements to a supported type.
Related
I'm newbie in Neural Network. I'm going to do a text classification research using MLP model with keras. Input layer consisting of 900 nodes, 2 hidden layers, and 2 outputs.
The code I use is as follows:
#Split data training & testing (90:10)
Train_X, Test_X, Train_Y, Test_Y = model_selection.train_test_split(dataset['review'],dataset['sentimen'],test_size=0.2, random_state=8)
Encoder = LabelEncoder()
Train_Y = Encoder.fit_transform(Train_Y)
Test_Y = Encoder.fit_transform(Test_Y)
Tfidf_vect = TfidfVectorizer(max_features=None)
Tfidf_vect.fit(dataset['review'])
Train_X_Tfidf = Tfidf_vect.transform(Train_X)
Test_X_Tfidf = Tfidf_vect.transform(Test_X)
#ANN Architecture
model = Sequential()
model.add(Dense(units = 100, activation = 'sigmoid', input_shape=(32, 900)))
model.add(Dense(units = 100, activation = 'sigmoid'))
model.add(Dense(units = 2, activation = 'sigmoid'))
opt = Adam (learning_rate=0.001)
model.compile(loss = 'binary_crossentropy', optimizer = opt,
metrics = ['accuracy'])
print(model.summary())
#Hyperparameter
epochs= 100
batch_size= 32
es = EarlyStopping(monitor="val_loss",mode='min',patience=10)
model_prediction = model.fit(Train_X_Tfidf, Train_Y, epochs=epochs,
batch_size=batch_size, verbose=1,
validation_split=0.1, callbacks =[es])
But getting Error:
/usr/local/lib/python3.8/dist-packages/keras/engine/data_adapter.py in train_validation_split(arrays, validation_split)
1478 unsplitable = [type(t) for t in flat_arrays if not _can_split(t)]
1479 if unsplitable:
-> 1480 raise ValueError(
1481 "`validation_split` is only supported for Tensors or NumPy "
1482 "arrays, found following types in the input: {}".format(unsplitable))
ValueError: `validation_split` is only supported for Tensors or NumPy arrays, found following types in the input: [<class 'scipy.sparse.csr.csr_matrix'>]
How to Fix it? Thank you so much.
I have an array of data and I'm trying to predict the probability if it's 1 or 0
I have a data set with more than 3000 rows as features and output data is either 1 or 0.
I'm quite new with neural networks, so I found an example online but now I'm having difficulties how to predict with unknown data.
In my case I want to predict the probability of 1 for row variable.
Here's the code
df = pd.read_csv("data.csv")
X = df.iloc[:,10:]
Y = df['output']
scaler = StandardScaler()
scaler.fit(X)
X = scaler.transform(X)
encoder = LabelEncoder()
encoder.fit(Y)
encoded_Y = encoder.transform(Y)
# larger model
def create_larger():
# create model
model = Sequential()
model.add(Dense(60, input_shape=(25,), activation='relu'))
model.add(Dense(30, activation='relu'))
model.add(Dense(15, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
# Compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp', KerasClassifier(model=create_larger, epochs=50, batch_size=5, verbose=2)))
pipeline = Pipeline(estimators)
kfold = StratifiedKFold(n_splits=5, shuffle=True)
results = cross_val_score(pipeline, X, encoded_Y, cv=kfold)
print("Larger: %.2f%% (%.2f%%)" % (results.mean()*100, results.std()*100))
row = [[4, 0.558, 0.493, 0.954, 0.895, 0.683, 8.7, 26, 0.155, 8.3, 21.8, 0.21, 0.723, 0.548, 0.466, 0.979, 0.887, 0.464, 11.8, 25.5, 0.184, 7.5, 18, 0.217, 0.651]]
scaler = StandardScaler()
row = np.array(row)
scaled_row = pipeline.fit(row)
print(pipeline.predict(scaled_row))
If I run this code I get an error
ValueError: Expected array-like (array or non-string sequence), got None
So now I'm kinda lost what to change it.
Thanks.
I'm worked on sentiment analysis task using universal sentence encoder embed_size=512 with CNN but have an error says: Input 0 is incompatible with layer conv1d_6: expected ndim=3, found ndim=2.
and wanna know if this is right to add universal sentence encoder with CNN in this way or not?
pickle_in=open("X.pickle","rb")
X=pickle.load(pickle_in)
X = X.tolist() #convert x to list as The embedding code works once I
converted
the pandas.series data type to list.
X = np.array(X, dtype=object)[:, np.newaxis]
pickle_in=open("Y.pickle","rb")
Y=pickle.load(pickle_in)
Y = np.asarray(pd.get_dummies(Y), dtype = np.int8)
import tensorflow as tf
import tensorflow_hub as hub
module_url = "https://tfhub.dev/google/universal-sentence-encoder-large/3"
embed = hub.Module(module_url)
X_train, X_test, Y_train, Y_test = train_test_split(X,Y, test_size = 0.15,
random_state = 42)
X_train, X_Val, Y_train, Y_Val = train_test_split(X_train,Y_train, test_size
= 0.15, random_state = 42)
print(X_train.shape,Y_train.shape)
print(X_test.shape,Y_test.shape)
print(X_Val.shape,Y_Val.shape)
type(Y_test)
embed_size = embed.get_output_info_dict()['default'].get_shape()[1].value
def UniversalEmbedding(x):
return embed(tf.squeeze(tf.cast(x, tf.string)),
signature="default", as_dict=True)["default"]
import keras
seed=7
np.random.seed(seed)
from keras.layers import Input, Dense, concatenate, Activation,
GlobalMaxPooling1D
from keras import layers
from keras.models import Model
input_text = layers.Input(shape=(1,), dtype=tf.string)
embedding = layers.Lambda(UniversalEmbedding,
output_shape=(embed_size,))(input_text)
bigram_branch = Conv1D(filters=64, kernel_size=1, padding='same',
activation='relu', strides=1)(embedding)
bigram_branch = GlobalMaxPooling1D()(bigram_branch)
trigram_branch = Conv1D(filters=64, kernel_size=2, padding='same',
activation='relu', strides=1)(embedding)
trigram_branch = GlobalMaxPooling1D()(trigram_branch)
fourgram_branch = Conv1D(filters=64, kernel_size=3, padding='same',
activation='relu', strides=1)(embedding)
fourgram_branch = GlobalMaxPooling1D()(fourgram_branch)
merged = concatenate([bigram_branch, trigram_branch, fourgram_branch],
axis=1)
merged = Dense(512, activation='relu')(merged)
merged = Dropout(0.8)(merged)
merged = Dense(2)(merged)
output = Activation('sigmoid')(merged)
model = Model(inputs=[tweet_input], outputs=[output])
adam=keras.optimizers.Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=None,
decay=0.0, amsgrad=False)
model.compile(loss='mean_squared_error',
optimizer= adam,
metrics=['accuracy'])
model.summary()
You can not directly pass Universal Sentence Encoder to Conv1D because Conv1D expected a tensor with shape [batch, sequence, feature] while the output of Universal Sentence Encoder is [batch, feature]. It is also stated in tfhub.dev:
The input is variable length English text and the output is a 512
dimensional vector.
How can I fix this?
In my view, the easiest possible solution is to use ELMo on Tensorhub. With ELMo you can map each sentence to [batch, sequence, feature] and then feed into the Conv1D.
I have a simple code, which DOES work, for training a Keras model in Tensorflow using numpy arrays as features and labels. If I then wrap these numpy arrays using tf.data.Dataset.from_tensor_slices in order to train the same Keras model using a tensorflow dataset, I get an error. I haven't been able to figure out why (it may be a tensorflow or keras bug, but I may also be missing something). I'm on python 3, tensorflow is 1.10.0, numpy is 1.14.5, no GPU involved.
OBS1: The possibility of using tf.data.Dataset as a Keras input is showed in https://www.tensorflow.org/guide/keras, under "Input tf.data datasets".
OBS2: In the code below, the code under "#Train with numpy arrays" is being executed, using numpy arrays. If this code is commented and the code under "#Train with tf.data datasets" is used instead, the error will be reproduced.
OBS3: In line 13, which is commented and starts with "###WORKAROUND 1###", if the comment is removed and the line is used for tf.data.Dataset inputs, the error changes, even though I can't completely understand why.
The complete code is:
import tensorflow as tf
import numpy as np
np.random.seed(1)
tf.set_random_seed(1)
print(tf.__version__)
print(np.__version__)
#Import mnist dataset as numpy arrays
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()#Import
x_train, x_test = x_train / 255.0, x_test / 255.0 #normalizing
###WORKAROUND 1###y_train, y_test = (y_train.astype(dtype='float32'), y_test.astype(dtype='float32'))
x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1]*x_train.shape[2])) #reshaping 28 x 28 images to 1D vectors, similar to Flatten layer in Keras
batch_size = 32
#Create a tf.data.Dataset object equivalent to this data
tfdata_dataset_train = tf.data.Dataset.from_tensor_slices((x_train, y_train))
tfdata_dataset_train = tfdata_dataset_train.batch(batch_size).repeat()
#Creates model
keras_model = tf.keras.models.Sequential([
tf.keras.layers.Dense(512, activation=tf.nn.relu),
tf.keras.layers.Dropout(0.2, seed=1),
tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])
#Compile the model
keras_model.compile(optimizer='adam',
loss=tf.keras.losses.sparse_categorical_crossentropy,
metrics=['accuracy'])
#Train with numpy arrays
keras_training_history = keras_model.fit(x_train,
y_train,
initial_epoch=0,
epochs=1,
batch_size=batch_size
)
#Train with tf.data datasets
#keras_training_history = keras_model.fit(tfdata_dataset_train,
# initial_epoch=0,
# epochs=1,
# steps_per_epoch=60000//batch_size
# )
print(keras_training_history.history)
The error observed when using tf.data.Dataset as input is:
(...)
ValueError: Tensor conversion requested dtype uint8 for Tensor with dtype float32: 'Tensor("metrics/acc/Cast:0", shape=(?,), dtype=float32)'
During handling of the above exception, another exception occurred:
(...)
TypeError: Input 'y' of 'Equal' Op has type float32 that does not match type uint8 of argument 'x'.
The error when removing the comment from line 13, as commented above in OBS3, is:
(...)
tensorflow.python.framework.errors_impl.InvalidArgumentError: In[0] is not a matrix
[[Node: dense/MatMul = MatMul[T=DT_FLOAT, _class=["loc:#training/Adam/gradients/dense/MatMul_grad/MatMul_1"], transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_sequential_input_0_0, dense/MatMul/ReadVariableOp)]]
Any help would be appreciated, including comments that you were able to reproduce the errors, so I can report the bug if it is the case.
I just upgraded to Tensorflow 1.10 to execute this code. I think that is the answer which is also discussed in the other Stackoverflow thread
This code executes but only if I remove the normalization as that line seems to use too much CPU memory. I see messages indicating that. I also reduced the cores.
import tensorflow as tf
import numpy as np
from tensorflow.keras.layers import Conv2D, MaxPool2D, Flatten, Dense, Dropout, Input
np.random.seed(1)
tf.set_random_seed(1)
batch_size = 128
NUM_CLASSES = 10
print(tf.__version__)
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
#x_train, x_test = x_train / 255.0, x_test / 255.0 #normalizing
def tfdata_generator(images, labels, is_training, batch_size=128):
'''Construct a data generator using tf.Dataset'''
def preprocess_fn(image, label):
'''A transformation function to preprocess raw data
into trainable input. '''
x = tf.reshape(tf.cast(image, tf.float32), (28, 28, 1))
y = tf.one_hot(tf.cast(label, tf.uint8), NUM_CLASSES)
return x, y
dataset = tf.data.Dataset.from_tensor_slices((images, labels))
if is_training:
dataset = dataset.shuffle(1000) # depends on sample size
# Transform and batch data at the same time
dataset = dataset.apply(tf.contrib.data.map_and_batch(
preprocess_fn, batch_size,
num_parallel_batches=2, # cpu cores
drop_remainder=True if is_training else False))
dataset = dataset.repeat()
dataset = dataset.prefetch(tf.contrib.data.AUTOTUNE)
return dataset
training_set = tfdata_generator(x_train, y_train,is_training=True, batch_size=batch_size)
testing_set = tfdata_generator(x_test, y_test, is_training=False, batch_size=batch_size)
inputs = Input(shape=(28, 28, 1))
x = Conv2D(32, (3, 3), activation='relu', padding='valid')(inputs)
x = MaxPool2D(pool_size=(2, 2))(x)
x = Conv2D(64, (3, 3), activation='relu')(x)
x = MaxPool2D(pool_size=(2, 2))(x)
x = Flatten()(x)
x = Dense(512, activation='relu')(x)
x = Dropout(0.5)(x)
outputs = Dense(NUM_CLASSES, activation='softmax')(x)
keras_model = tf.keras.Model(inputs, outputs)
#Compile the model
keras_model.compile('adam', 'categorical_crossentropy', metrics=['acc'])
#Train with tf.data datasets
keras_training_history = keras_model.fit(
training_set.make_one_shot_iterator(),
steps_per_epoch=len(x_train) // batch_size,
epochs=5,
validation_data=testing_set.make_one_shot_iterator(),
validation_steps=len(x_test) // batch_size,
verbose=1)
print(keras_training_history.history)
Installing the tf-nightly build, together with changing dtypes of some tensors (the error changes after installing tf-nightly), solved the problem, so it is an issue which (hopefully) will be solved in 1.11.
Related material: https://github.com/tensorflow/tensorflow/issues/21894
I am wondering how Keras is able to do 5 epochs when the
make_one_shot_iterator() which only supports iterating once through a
dataset?
could be given smth like iterations = len(y_train) * epochs - here shown for tf.v1
the code from Mohan Radhakrishnan still works in tf.v2 with little corrections in objects' belongings to new classes (in tf.v2) fixings - to make the code up-to-date... No more make_one_shot_iterator() needed
# >> author: Mohan Radhakrishnan
import tensorflow as tf
import tensorflow.keras
import numpy as np
from tensorflow.keras.layers import Conv2D, MaxPool2D, Flatten, Dense, Dropout, Input
np.random.seed(1)
tf.random.set_seed(1)
batch_size = 128
NUM_CLASSES = 10
print(tf.__version__)
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
#x_train, x_test = x_train / 255.0, x_test / 255.0 #normalizing
def tfdata_generator(images, labels, is_training, batch_size=128):
'''Construct a data generator using tf.Dataset'''
def preprocess_fn(image, label):
'''A transformation function to preprocess raw data
into trainable input. '''
x = tf.reshape(tf.cast(image, tf.float32), (28, 28, 1))
y = tf.one_hot(tf.cast(label, tf.uint8), NUM_CLASSES)
return x, y
dataset = tf.data.Dataset.from_tensor_slices((images, labels))
if is_training:
dataset = dataset.shuffle(1000) # depends on sample size
# Transform and batch data at the same time
dataset = dataset.apply( tf.data.experimental.map_and_batch(
preprocess_fn, batch_size,
num_parallel_batches=2, # cpu cores
drop_remainder=True if is_training else False))
dataset = dataset.repeat()
dataset = dataset.prefetch( tf.data.experimental.AUTOTUNE)
return dataset
training_set = tfdata_generator(x_train, y_train,is_training=True, batch_size=batch_size)
testing_set = tfdata_generator(x_test, y_test, is_training=False, batch_size=batch_size)
inputs = Input(shape=(28, 28, 1))
x = Conv2D(32, (3, 3), activation='relu', padding='valid')(inputs)
x = MaxPool2D(pool_size=(2, 2))(x)
x = Conv2D(64, (3, 3), activation='relu')(x)
x = MaxPool2D(pool_size=(2, 2))(x)
x = Flatten()(x)
x = Dense(512, activation='relu')(x)
x = Dropout(0.5)(x)
outputs = Dense(NUM_CLASSES, activation='softmax')(x)
keras_model = tf.keras.Model(inputs, outputs)
#Compile the model
keras_model.compile('adam', 'categorical_crossentropy', metrics=['acc'])
#Train with tf.data datasets
# training_set.make_one_shot_iterator() - 'PrefetchDataset' object has no attribute 'make_one_shot_iterator'
keras_training_history = keras_model.fit(
training_set,
steps_per_epoch=len(x_train) // batch_size,
epochs=5,
validation_data=testing_set,
validation_steps=len(x_test) // batch_size,
verbose=1)
print(keras_training_history.history)
not loading data locally, just easy DataFlow - that is very convinient - Thanks a lot - hope my corrections are proper
I've been trying to figure out how to use Keras when reading data from a .csv[1]. I have the following code:
dataframe = pd.read_csv("iris.csv", header=None)
dataset = dataframe.values
X = dataset[:, 0:4].astype(float)
Y = dataset[:, 4]
# encode class values as integers
encoder = LabelEncoder()
encoder.fit(Y)
encoded_Y = encoder.transform(Y)
# convert integers to dummy variables (i.e. one hot encoded)
one_hot_y = keras.utils.to_categorical(encoded_Y)
X_train = X[:100]
X_test = X[50:]
Y_train = one_hot_y[:100]
Y_test = one_hot_y[50:]
print(X_train.shape)
# define baseline model
def baseline_model():
# create model
model = keras.models.Sequential()
model.add(keras.layers.Dense(8, input_shape=(4, ), activation='relu'))
model.add(keras.layers.Dense(3, activation='softmax'))
# Compile model
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
model = baseline_model()
history = model.fit(X_train, X_test, epochs=5)
test_loss, test_acc = model.evaluate(Y_train, Y_test)
print('Test accuracy:', test_acc)
However, when I run this, I get the error:
ValueError: Error when checking target: expected dense_1 to have shape (3,) but got array with shape (4,)
I find this odd as I was sure to set input_shape=(4, ). Any help with this would be appreciated.
[1] The CSV looks as follows:
5.1,3.5,1.4,0.2,Iris-setosa
...
You have only 3 output neurons, but the data you are using obviously has 4 classes, so you need to change this line:
model.add(keras.layers.Dense(3, activation='softmax'))
from 3 output classes to 4 output classes:
model.add(keras.layers.Dense(4, activation='softmax'))