I'm working on building a regressor. Currently the regressor will accept information through the network it appears up until the final dense layer when it throws an error. I'm new to these types of LSTM and would appreciate some help throubleshooting. I've looked through a few articles and haven't found anything that seems to work.
def generate_arrays(arrays=None, targets=None):
from random import shuffle
while True:
available_ids = list(range(len(arrays)))
shuffle(available_ids)
for i in available_ids:
frames = []
for image in arrays[i]:
# load the image
img = Image.open(image_path + image)
# convert image to numpy array
img = np.asarray(img) / 255
height = 220
width = 220
dim = (width, height)
img = cv2.resize(img, dim, interpolation=cv2.INTER_LINEAR)
# add to bigger np array
frames.append(img)
frames = np.array(frames)
frames = frames.reshape(-1, 3, 220, 220, 3)
target = targets[i]
yield (frames, category)
def build_model(frames=seq_len, channels=3, pixels_x=220, pixels_y=220):
model = Sequential()
model.add(
ConvLSTM2D(filters=10
, kernel_size=(2,2)
, data_format='channels_last'
, return_sequences = False
, activation='relu', input_shape=(frames, pixels_x, pixels_y, channels))
)
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dense(1, activation='linear'))
optimizer = tf.keras.optimizers.RMSprop(0.001)
model.compile(
loss = "mse",
optimizer = optimizer,
metrics=['mae', 'mse'])
return model
def evaluate_model(train_x, train_y, test_x, test_y):
# define model
model = build_model()
model.summary()
# fit network
model.fit_generator(
generate_arrays(train_x, train_y)
, steps_per_epoch = len(train_x)
, validation_data = generate_arrays(test_x, test_y)
, validation_steps = len(test_x)
, epochs = 100
, verbose = 1
, shuffle = False
, initial_epoch = 0
)
The model summary is as such:
Now, the error I'm getting appears to be the generic value error that means that something isn't getting passed correctly but I cannot figure out what it is...
ValueError: Error when checking target: expected dense_47 to have 2 dimensions, but got array with shape ()
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 trying to retrain VGG16 to classify Lego images. However, my model has a low accuracy (between 20%). What am I doing wrong? Maybe the number of FC is wrong, or my ImageDataGenerator. I have approx. 2k images per class and a total of 6 classes.
How I create the model:
def vgg16Model(self,image_shape,num_classes):
model_VGG16 = VGG16(include_top = False, weights = None)
model_input = Input(shape = image_shape, name = 'input_layer')
output_VGG16_conv = model_VGG16(model_input)
#Init of FC layers
x = Flatten(name='flatten')(output_VGG16_conv)
x = Dense(256, activation = 'relu', name = 'fc1')(x)
output_layer = Dense(num_classes,activation='softmax',name='output_layer')(x)
vgg16 = Model(inputs = model_input, outputs = output_layer)
vgg16.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
vgg16.summary()
return vgg16
I'm creating ImageDataGenerator and training:
path = "real_Legos_images/trainable_classes"
evaluate_path = "real_Legos_images/evaluation"
NN = NeuralNetwork()
gen = ImageDataGenerator(rotation_range=40, width_shift_range=0.02, shear_range=0.02,height_shift_range=0.02, horizontal_flip=True, fill_mode='nearest')
train_generator = gen.flow_from_directory(os.path.abspath(os.path.join(path)),
target_size = (224,224), color_mode = "rgb", batch_size = 16, class_mode='categorical')
validation_generator = gen.flow_from_directory(os.path.abspath(os.path.join(evaluate_path)),
target_size = (224,224), color_mode = "rgb", batch_size = 16, class_mode='categorical')
STEP_SIZE_TRAIN = train_generator.n//train_generator.batch_size
num_classes = len(os.listdir(os.path.abspath(os.path.join(path))))
VGG16 = NN.vgg16Model((224, 224, 3), num_classes)
VGG16.save_weights('weights.h5')
VGG16.fit_generator(train_generator, validation_data = validation_generator, validation_steps = validation_generator.n//validation_generator.batch_size,
steps_per_epoch = STEP_SIZE_TRAIN, epochs = 50)
The VGG16 model with the parameter include_top = False will return 512 dimensions feature maps. Usually, we should add a GlobalAveragePooling2D or GlobalMaxPooling2D layer after it first, then flat it to an one-dimensional array. Otherwise, you will get an array which is too long to fit.
You have set the weight property to 'None' for VGG which means your networks is initialized with random weights. This means you are not using the pre-trained weights. So, I would suggest to try setting the weights to 'imagenet' such that you can use the VGG networks that its weights are pretrained on imagenet dataset:
model_VGG16 = VGG16(include_top=False, weights='imagenet')
I am running MNIST prediction using Keras, with tensorflow backend.
I have code that runs with batches , using Keras fit() as
(X_train, y_train), (X_test, y_test) = mnist.load_data()
N1 = X_train.shape[0]
N2 = X_test.shape[0]
h = X_train.shape[1]
w = X_train.shape[2]
num_pixels = h*w
# reshape N1 samples to num_pixels
x_train = X_train.reshape(N1, num_pixels).astype('float32') # shape is now (60000,784)
x_test = X_test.reshape(N2, num_pixels).astype('float32') # shape is now (10000,784)
x_train = x_train / 255
x_test = x_test / 255
y_train = np_utils.to_categorical(y_train) #(60000,10)
y_test = np_utils.to_categorical(y_test) # (10000,10):
num_classes = y_test.shape[1]
def baseline_model():
# create model
model = Sequential()
model.add(Dense(num_pixels, input_dim=num_pixels, kernel_initializer='normal', activation='relu'))
model.add(Dense(num_classes, kernel_initializer='normal', activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
model = baseline_model()
batch_size = 200
epochs = 20
max_batches = 2 * len(x_train) / batch_size # 2*60000/200
# reshape to be [samples][width][height][ channel] for ImageDataGenerator
x_t = X_train.reshape(N1, w, h, 1).astype('float32')
datagen = ImageDataGenerator(rescale= 1./255)
train_gen = datagen.flow(x_t, y_train, batch_size=batch_size)
for e in range(epochs):
batches = 0
for x_batch, y_batch in train_gen:
# x_batch is of size [batch_sz,w,h,ch]: resize to [bth_sz,pixel_sz]: (200,28,28,1)-> (200,784)
# for model.fit
x_batch = np.reshape(x_batch, [-1, num_pixels])
model.fit(x_batch, y_batch,validation_split=0.15,verbose=0)
batches += 1
print("Epoch %d/%d, Batch %d/%d" % (e+1, epochs, batches, max_batches))
if batches >= max_batches:
break
scores = model.evaluate(x_test, y_test, verbose=0)
However, when I try to implement similar code using fit_generator(), I get an error.
the code is as below:
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# separate data into train and validation
from sklearn.model_selection import train_test_split
# Split the data
X_train, X_valid, y_train, y_valid = train_test_split(X_train, y_train, test_size=0.15, shuffle= True)
# number of training samples
N1 = X_train.shape[0] # training size
N2 = X_test.shape[0] # test size
N3 = X_valid.shape[0] # valid size
h = X_train.shape[1]
w = X_train.shape[2]
num_pixels = h*w
y_train = np_utils.to_categorical(y_train)
y_valid = np_utils.to_categorical(y_valid)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]
def baseline_model():
# create model
model = Sequential()
model.add(Dense(num_pixels, input_dim=num_pixels, kernel_initializer='normal', activation='relu'))
model.add(Dense(num_classes, kernel_initializer='normal', activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
model = baseline_model()
batch_size = 200
epochs = 20
steps_per_epoch_tr = int(N1/ batch_size) # 51000/200
steps_per_epoch_val = int(N3/batch_size)
# reshape to be [samples][width][height][ channel] for ImageData Gnerator->datagen.flow
x_t = X_train.reshape(N1, w, h, 1).astype('float32')
x_v = X_valid.reshape(N3, w, h, 1).astype('float32')
# define data preparation
datagen = ImageDataGenerator(rescale=1./255) # scales x_t/x_v
train_gen = datagen.flow(x_t, y_train, batch_size=batch_size)
valid_gen = datagen.flow(x_v,y_valid, batch_size=batch_size)
model.fit_generator(train_gen,steps_per_epoch = steps_per_epoch_tr,validation_data = valid_gen,
validation_steps = steps_per_epoch_val,epochs=epochs)
This gives an error:
This is due to expected image dimension error, but I am not sure where/how to fix this. any help is greatly appreciated.
Thanks
sedy
In the model.fit() case, this line flattened the input before feeding it for training.
x_batch = np.reshape(x_batch, [-1, num_pixels])
But in the generator case, there is nothing to flatten the input before feeding it to the Dense layer. The Dense layer cannot process 2D input (28 x 28). Adding, a Flatten() layer to the model should do the trick as shown below.
def baseline_model():
# create model
model = Sequential()
model.add(Flatten(input_shape=(28,28,1)))
model.add(Dense(num_pixels, input_dim=num_pixels, kernel_initializer='normal', activation='relu'))
model.add(Dense(num_classes, kernel_initializer='normal', activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
i have bulit a model to distinguish cats from dogs using kaggle's cats_vs_dogs data set. I have tried two ways to do it. For the first one, I used three existing models(ResNet50, Xception InceptionV3)to extract features, i put the traing data through these models's convolutional base,predict and concatenate the results, then use them for a standalone densely-connected classifier.The result is pretty good, after five epoches training, val_acc became 99.58%. Then i want to use data augmentation and fine-tuing, so i extended the those three models by adding layers on top, and running he whole thing end-to-end on the input data. The strange thing is the second way got good result in the traing but lousy one in the validation, and the val_acc is always a constant(0.5). i feel very confused, how come these two ways have such different results.
here is my code
from keras.models import *
from keras.layers import *
from keras.applications import *
from keras.preprocessing.image import *
res_net_input = Input((224, 224, 3), name='res_net')
res_net_base_model = ResNet50(input_tensor=res_net_input, weights='imagenet', include_top=False)
for layers in res_net_base_model.layers:
layers.trainable = False
xception_input = Input((299, 299, 3), name='xception')
xception_base_model = Xception(input_tensor=xception_input, weights='imagenet', include_top=False)
for layers in xception_base_model.layers:
layers.trainable = False
inception_input = Input((299, 299, 3), name='inception')
inception_base_model = InceptionV3(input_tensor=inception_input, weights='imagenet', include_top=False)
for layers in inception_base_model.layers:
layers.trainable = False
res_result = GlobalAveragePooling2D()(res_net_base_model.output)
xcp_result = GlobalAveragePooling2D()(xception_base_model.output)
icp_result = GlobalAveragePooling2D()(inception_base_model.output)
concatenated = concatenate([res_result, xcp_result, icp_result], axis=1)
x = Dropout(0.5)(concatenated)
x = Dense(1, activation='sigmoid')(x)
model = Model([res_net_base_model.input, xception_base_model.input, inception_base_model.input], x)
model.compile(optimizer='adadelta',
loss='binary_crossentropy',
metrics=['accuracy'])
train_imgen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
rotation_range=5.,
horizontal_flip = True)
validation_imgen = ImageDataGenerator(rescale = 1./255)
def generate_generator_multiple(generator,dir1, batch_size, img_size1, img_size2, img_size3):
genX1 = generator.flow_from_directory(dir1,
target_size = (img_size1[0],img_size1[1]),
class_mode = 'binary',
batch_size = batch_size,
shuffle=False,
)
genX2 = generator.flow_from_directory(dir1,
target_size = (img_size2[0],img_size2[1]),
class_mode = 'binary',
batch_size = batch_size,
shuffle=False,
seed=7)
genX3 = generator.flow_from_directory(dir1,
target_size = (img_size3[0],img_size3[1]),
class_mode = 'binary',
batch_size = batch_size,
shuffle=False,
seed=7)
while True:
X1i = genX1.next()
X2i = genX2.next()
X3i = genX3.next()
yield [X1i[0], X2i[0],X3i[0]], X1i[1]
tain_generator = generate_generator_multiple(train_imgen , '/output/keras/dog_vs_cat_full/train', 100, (224,224), (299, 299), (299, 299))
validation_generator = generate_generator_multiple(validation_imgen,'/output/keras/dog_vs_cat_full/validation', 100, (224,224), (299, 299), (299, 299))
history=model.fit_generator(tain_generator,
steps_per_epoch=200,
epochs = 5,
validation_data = validation_generator,
validation_steps = 50,
shuffle=False)