I am getting an error. It says:
Model was constructed with shape (None, 28) for input KerasTensor(type_spec=TensorSpec(shape=(None, 28), dtype=tf.float32, name='dense_45_input'), name='dense_45_input', description="created by layer 'dense_45_input'"), but it was called on an input with incompatible shape (None, 28, 28).
Mycode is here:
from keras.utils import np_utils
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, BatchNormalization, Dropout, Activation
import seaborn as sns
from keras.initializers import RandomNormal
from keras.initializers import he_normal
import matplotlib.pyplot as plt
(train_X, train_y), (test_X, test_y) = mnist.load_data()
output_dim = 10
input_dim = train_X.shape[1]
batch_size = 128
nb_epoch = 20
model_drop = Sequential()
model_drop.add(Dense(512, activation='relu', input_shape=(input_dim,),kernel_initializer=he_normal(seed=None)))
model_drop.add(BatchNormalization())
model_drop.add(Dropout(0.5))
model_drop.add(Dense(128, activation= 'relu', kernel_initializer=he_normal(seed=None)))
model_drop.add(BatchNormalization())
model_drop.add(Dropout(0.5))
model_drop.add(Dense(output_dim, activation = 'softmax'))
model_drop.summary()
model_drop.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
history = model_drop.fit(train_X, train_y, batch_size=batch_size, epochs=nb_epoch, verbose=1)
How can I fix this? Also I am adding error photo..
Your input dimensions in building the dense layer are wrong, if the image is 28x28 you need to be able to receive all the pixels (i.e. you need 28*28=784 input connections). To really get this working you also need to one-hot encode the y variables as well as reshape the images.
(train_X, train_y), (test_X, test_y) = mnist.load_data()
output_dim = 10
input_dim = train_X.shape[1]
batch_size = 128
nb_epoch = 20
model_drop = Sequential()
# see input_dim edit here
model_drop.add(Dense(512, activation='relu', input_shape=(input_dim*input_dim,),kernel_initializer=he_normal(seed=None)))
model_drop.add(BatchNormalization())
model_drop.add(Dropout(0.5))
model_drop.add(Dense(128, activation= 'relu', kernel_initializer=he_normal(seed=None)))
model_drop.add(BatchNormalization())
model_drop.add(Dropout(0.5))
model_drop.add(Dense(output_dim, activation = 'softmax'))
model_drop.summary()
model_drop.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
# encode Y_train and also shape X_train so it can feed to dense layer
Y_train = np_utils.to_categorical(train_y, num_classes=10)
X_train = train_X.reshape((-1, 28*28))
history = model_drop.fit(X_train, Y_train, batch_size=batch_size, epochs=nb_epoch, verbose=1)
Related
i'm newbie in machine learning, and i try to run lstm multi layers with keras. here's my code:
from keras.layers import Embedding
embedding_layer = Embedding(vocabulary_size, EMBEDDING_DIM, weights=[embedding_matrix], trainable=False)
from keras.layers import Input, Dense, Embedding, Dropout
from keras.layers.core import Reshape
from tensorflow.keras.optimizers import Adam
from keras.preprocessing.sequence import pad_sequences
from keras.models import Sequential
from keras.layers import LSTM
X_train = pad_sequences(sequences_train)
X_test = pad_sequences(sequences_test,maxlen=X_train.shape[1])
y_train = to_categorical(np.asarray(labels[train_data.index]))
y_test = to_categorical(np.asarray(labels[test_data.index]))
embed_dim = 128
lstm_out = 128
sequence_length = X_train.shape[1]
inputs = Input(shape=(sequence_length,))
embedding = embedding_layer(inputs)
reshape = Reshape((sequence_length,EMBEDDING_DIM,1))(embedding)
adam = Adam(lr=1e-1)
model = Sequential()
model.add(Embedding(input_dim = len(word_index)+1, output_dim = EMBEDDING_DIM, input_length = sequence_length, weights=[embedding_matrix], trainable=False))
model.add(LSTM(((lstm_out)), return_sequences=True))
model.add(Dropout(0.5))
model.add(Dense(len(labels), activation='softmax'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics = ['accuracy'])
history = model.fit(X_train, y_train, batch_size=64, epochs=5, validation_data=(X_test, y_test), shuffle = True)
print(model.summary())
and some errors appear
File "E:\Codes\LSTM_multi_Layers.py", line 31, in <module>
history = model.fit(X_train, y_train, batch_size=64, epochs=5, validation_data=(X_test, y_test), shuffle = True)
ValueError: logits and labels must have the same shape ((64, 20, 1440) vs (64, 2))
What does it mean? and what should be changed from my code? can somebody help me, please.
I have the following code:
import tensorflow as tf
import keras
from keras.datasets import cifar10
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
import numpy as np
x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], x_train.shape[2], 3))
print(x_train.shape)
x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], x_test.shape[2], 3))
print(x_test.shape)
x_train = x_train.astype('float32')/255.0
x_test = x_test.astype('float32')/255.0
from keras.utils import to_categorical
y_train = to_categorical(y_train, num_classes = 10)
y_test = to_categorical(y_test, num_classes = 10)
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten
model = Sequential()
#Defining layers of the model
model.add(Dense(2056, activation='relu', input_shape = (3072,)))
model.add(Dense(10, activation='softmax'))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.summary()
history = model.fit(x_train, y_train, batch_size=1000, epochs=50)
And I am facing the following error:
ValueError: Input 0 of layer sequential_2 is incompatible with the layer: expected axis -1 of input shape to have value 3072 but received input with shape (1000, 32, 32, 3)
I want to keep the input_shape as 3072 only. How can I reshape my y_test to solve this?
You should Flatten your input data before passing them to Dense layer.
model = Sequential()
#Defining layers of the model
model.add(Flatten(input_shape=(32,32,3)) # 32*32*3 = 3072
model.add(Dense(2056, activation='relu'))
model.add(Dense(10, activation='softmax'))
This should fix the problem.
Based on a previously trained feed-forward network, I tried to use SHAP to get the feature importance. I followed all the steps described in the documentation but I am still receiving the following error
ValueError: Dimension 1 in both shapes must be equal, but are 2 and 1. Shapes are [?,2] and [?,1]
The following code produces a reproduciple example that has the same error.
import pandas as pd
from numpy.random import randint
from keras.utils import to_categorical
from keras.models import Sequential
from keras.layers import Dense, BatchNormalization, Dropout, Activation
from keras.optimizers import Adam
import shap
# Train_x data creation
train_x = pd.DataFrame({
'v1': randint(2, 20, 1489),
'v2': randint(50, 200, 1489),
'v3': randint(30, 90, 1489),
'v4': randint(100, 150, 1489)
})
# Train_y data creation
train_y = randint(0, 2, 1489)
# One-hot encoding as I use categorical cross-entropy
train_y = to_categorical(train_y, num_classes=2)
# Start construction of a DNN Sequential model.
model = Sequential()
# First input layer with a dropout and batch normalization layer following
model.add(Dense(256, input_dim=train_x.shape[1]))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Dropout(rate=0.2))
# Output layer
model.add(Dense(2))
model.add(Activation('softmax'))
# Use the Adam optimizer
optimizer = Adam(lr=0.001)
# Compile the model
model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])
model.summary()
# Fit model
hist = model.fit(train_x, train_y, epochs=100, batch_size=128, shuffle=False, verbose=2)
# SHAP calculation
explainer = shap.DeepExplainer(model, train_x)
shap_values = explainer.shap_values(train_x[:500].values)
where I have an input shape of (None, 4) and a softmax activation function at the end with 2 neurons as I use it for binary classification. The train_x data on the following code snippet are a pandas data frame of shape (1489, 4).
I tried to change the train_x shape but I had a similar error. Any help would be much appreciated.
Please see below a working example for binary classification with TF:
from numpy.random import randint
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, BatchNormalization, Dropout, Activation
from tensorflow.keras.optimizers import Adam
import shap
import tensorflow
print(shap.__version__, "\n",tensorflow.__version__)
# Train_x data creation
train_x = pd.DataFrame({
'v1': randint(2, 20, 1489),
'v2': randint(50, 200, 1489),
'v3': randint(30, 90, 1489),
'v4': randint(100, 150, 1489)
})
# Train_y data creation
train_y = randint(0, 2, 1489)
# One-hot encoding as I use categorical cross-entropy
train_y = to_categorical(train_y, num_classes=2)
# Start construction of a DNN Sequential model.
model = Sequential()
# First input layer with a dropout and batch normalization layer following
model.add(Dense(256, input_dim=train_x.shape[1]))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Dropout(rate=0.2))
# Output layer
model.add(Dense(2))
model.add(Activation('softmax'))
# Use the Adam optimizer
optimizer = Adam(lr=0.001)
# Compile the model
model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])
# model.summary()
# Fit model
hist = model.fit(train_x, train_y, epochs=100, batch_size=128, shuffle=False, verbose=0)
# SHAP calculation
shap.explainers._deep.deep_tf.op_handlers["AddV2"] = shap.explainers._deep.deep_tf.passthrough
explainer = shap.DeepExplainer(model, train_x)
shap_values = explainer.shap_values(train_x[:500].values)
shap.summary_plot(shap_values[1])
0.38.2
2.2.0
Note couple of things:
Package versions (tf should be below 2.4 I believe)
Addition of "AddV2" (see discussion here)
My input is simply a csv file with 237124 rows and 37 columns :
The first 36 columns as features
The last column is a Binary class label
I am trying to train my data on the conv1D model.
I have tried to build a CNN with one layer, but I have some problems with it.
The compiler outputs:
ValueError:Error when checking input: expected conv1d_9_input to have shape
(213412, 36) but got array with shape (36, 1)
Code:
import pandas as pd
import numpy as np
import sklearn
from sklearn import metrics
from sklearn.model_selection import KFold
from sklearn.metrics import confusion_matrix
from sklearn.preprocessing import StandardScaler
import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.layers import Conv2D,Conv1D, MaxPooling2D,MaxPooling1D
from tensorflow.keras.layers import Activation
from tensorflow.keras.layers import Dropout,BatchNormalization
dataset=pd.read_csv("C:/Users/User/Desktop/data.csv",encoding='cp1252')
dataset.shape
#output: (237124, 37)
array = dataset.values
X = array[:,0:36]
Y = array[:,36]
kf = KFold(n_splits=10)
kf.get_n_splits(X)
for trainindex, testindex in kf.split(X):
Xtrain, Xtest = X[trainindex], X[testindex]
Ytrain, Ytest = Y[trainindex], Y[testindex]
Xtrain.shape[0]
#output: 213412
Xtrain.shape[1]
#output: 36
Ytrain.shape[0]
#output: 213412
n_timesteps, n_features, n_outputs =Xtrain.shape[0], Xtrain.shape[1],
Ytrain.shape[0]
model = Sequential()
model.add(Conv1D(filters=64, kernel_size=1,
activation='relu',input_shape=(n_timesteps,n_features)))
model.add(Conv1D(filters=64, kernel_size=1, activation='relu'))
model.add(Dropout(0.5))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dense(n_outputs, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=
['accuracy'])
# fit network
model.fit(Xtrain, Ytrain, epochs=10, batch_size=32, verbose=0)
# Testing CNN model BY X test
Predictions = model.predict(Xtest,batch_size =100)
rounded = [round(x[0]) for x in Predictions]
Y_predection = pd.DataFrame(rounded)
Y_predection = Y_predection.iloc[:, 0]
.
.
.
I tried to modify the code this way:
Xtrain = np.expand_dims(Xtrain, axis=2)
But the error remains the same.
There's a couple of problems I notice with your code.
Xtrain - Needs to be a 3D tensor. Because anything else, Conv1D cannot process. So if you have 2D data you need to add a new dimension to make it 3D.
Your input_shape needs to be changed to reflect that. For example, if you added only a single channel, it should be [n_features, 1].
# Here I'm assuming some dummy data
# Xtrain => [213412, 36, 1] (Note that you need Xtrain to be 3D not 2D - So we're adding a channel dimension of 1)
Xtrain = np.expand_dims(np.random.normal(size=(213412, 36)),axis=-1)
# Ytrain => [213412, 10]
Ytrain = np.random.choice([0,1], size=(213412,10))
n_timesteps, n_features, n_outputs =Xtrain.shape[0], Xtrain.shape[1], Ytrain.shape[1]
model = Sequential()
model.add(Conv1D(filters=64, kernel_size=1,
activation='relu',input_shape=(n_features,1)))
model.add(Conv1D(filters=64, kernel_size=1, activation='relu'))
model.add(Dropout(0.5))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dense(n_outputs, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
# fit network
model.fit(Xtrain, Ytrain, epochs=10, batch_size=32, verbose=0)
You need to specifi only how many dimension X has, not how many samples you will pass for the input layer.
model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(n_features,)))
This means that the input will be N samples of shape n_features
For the last layer you should change the number of units to how many classes you have instead of how many rows your data has.
I used this code to produce my dataset in keras. but when I implement my code it produces this error:
ValueError: Error when checking input: expected conv2d_1_input to
have 4 dimensions, but got array with shape (454, 512, 512)
and I can not solve it. could you please tell me what is the problem? I expand the dimension before using in network but it does not work! could you please answer me fast, due to I search for several days but I could not find the solution and I do not have enough time:
import os,cv2
import numpy as np
import matplotlib.pyplot as plt
from sklearn.utils import shuffle
from sklearn.cross_validation import train_test_split
from keras import backend as K
#K.set_image_dim_ordering('th')
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.optimizers import SGD,RMSprop,adam
#%%
PATH = os.getcwd()
# Define data path
data_path = r"E:\PhD\thesis\deepwatermark\databasetest\train"
data_dir_list = os.listdir(data_path)
img_rows=512
img_cols=512
num_channel=1
num_epoch=20
# Define the number of classes
num_classes = 7
labels_name={'CRP':0,'GF':1,'GN':2,'JPG':3,'MED':4,'ROT':5,'SP':6}
img_data_list=[]
labels_list = []
for dataset in data_dir_list:
img_list=os.listdir(data_path+'/'+ dataset)
print ('Loading the images of dataset-'+'{}\n'.format(dataset))
label = labels_name[dataset]
for img in img_list:
input_img=cv2.imread(data_path + '/'+ dataset + '/'+ img )
input_img=cv2.cvtColor(input_img, cv2.COLOR_BGR2GRAY)
input_img_resize=cv2.resize(input_img,(512,512))
img_data_list.append(input_img_resize)
labels_list.append(label)
img_data = np.array(img_data_list)
img_data = img_data.astype('float32')
img_data /= 255
print (img_data.shape)
labels = np.array(labels_list)
# print the count of number of samples for different classes
print(np.unique(labels,return_counts=True))
# convert class labels to on-hot encoding
Y = np_utils.to_categorical(labels, num_classes)
#Shuffle the dataset
x,y = shuffle(img_data,Y, random_state=2)
# Split the dataset
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=2)
img_data= np.expand_dims(img_data, axis=4)**
print (img_data.shape)
# Defining the model
input_shape=img_data[0].shape
model = Sequential()
model.add(Convolution2D(32, 3,3,border_mode='same',input_shape=input_shape))
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Convolution2D(64, 3, 3))
model.add(Activation('relu'))
#model.add(Convolution2D(64, 3, 3))
#model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))
#sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
#model.compile(loss='categorical_crossentropy', optimizer=sgd,metrics=["accuracy"])
model.compile(loss='categorical_crossentropy', optimizer='rmsprop',metrics=["accuracy"])
# Viewing model_configuration
model.summary()
model.get_config()
model.layers[0].get_config()
model.layers[0].input_shape
model.layers[0].output_shape
model.layers[0].get_weights()
np.shape(model.layers[0].get_weights()[0])
model.layers[0].trainable
#%%
# Training
hist = model.fit(X_train, y_train, batch_size=16, nb_epoch=num_epoch, verbose=1, validation_data=(X_test, y_test))
my new code with generator is here, did you see any problem? my dataset is the same as before.
import numpy as np
import matplotlib.pyplot as plt
from keras.preprocessing.image import ImageDataGenerator
from sklearn.utils import shuffle
from sklearn.cross_validation import train_test_split
from keras import backend as K
#K.set_image_dim_ordering('th')
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.optimizers import SGD,RMSprop,adam
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
#
valid_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
#
test_datagen = ImageDataGenerator(rescale=1./255)
#
train_generator = train_datagen.flow_from_directory(
directory=r"E:\databasetest\train",
target_size=(512, 512),
color_mode="grayscale",
batch_size=32,
class_mode="categorical",
shuffle=True,
seed=42
)
#
valid_generator = valid_datagen.flow_from_directory(
directory=r"E:\databasetest\validation",
target_size=(512, 512),
color_mode="grayscale",
batch_size=32,
class_mode="categorical",
shuffle=True,
seed=42
)
#
test_generator = test_datagen.flow_from_directory(
directory=r"E:\databasetest\test",
target_size=(512, 512),
color_mode="grayscale",
batch_size=16,
class_mode=None,
shuffle=False,
seed=42
)
#
## neural network model
model = Sequential()
model.add(Conv2D(32, (3,3),border_mode='same', input_shape = (512, 512, 1), activation = 'relu'))
model.add(Activation('relu'))
model.add(Conv2D(32, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Conv2D(64, 3, 3))
model.add(Activation('relu'))
#model.add(Convolution2D(64, 3, 3))
#model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(7))
model.add(Activation('softmax'))
model.summary()
model.compile(loss = 'categorical_crossentropy',
optimizer = 'rmsprop',
metrics = ['accuracy'])
STEP_SIZE_TRAIN=train_generator.n//train_generator.batch_size
STEP_SIZE_VALID=valid_generator.n//valid_generator.batch_size
model.fit_generator(generator=train_generator,
steps_per_epoch=STEP_SIZE_TRAIN,
validation_data=valid_generator,
validation_steps=STEP_SIZE_VALID,
epochs=10
)
but when I implement it I received this error again:
ResourceExhaustedError: OOM when allocating tensor with shape[32,32,512,512] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[Node: conv2d_1/convolution = Conv2D[T=DT_FLOAT, data_format="NCHW", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](conv2d_1/convolution-0-TransposeNHWCToNCHW-LayoutOptimizer, conv2d_1/kernel/read)]]
for img in img_list:
input_img=cv2.imread(data_path + '/'+ dataset + '/'+ img )
input_img=cv2.cvtColor(input_img, cv2.COLOR_BGR2GRAY)
input_img_resize=cv2.resize(input_img,(512,512))
--->input_img_resize = np.expand_dims(input_img_resize, axis=-1)
img_data_list.append(input_img_resize)
labels_list.append(label)
this will make all your arrays 512x512x1, which should do the trick and ends up zith an array of shape (454, 512, 512, 1). You sure you want to use grayscaled images though?
Another thing is this snippet of code
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, `random_state=2)`
img_data= np.expand_dims(img_data, axis=4)**
print (img_data.shape)
You apply another dimension to your img_data, after you've already declared x_train, etc. And in the end you feed x_train, which is not extended, hence the error. If you do it in the beginning, and remove the expanding in the end, then your code should work.
EDIT OOM
I recommend creating a separate question for the OOM problem, so more people see it. Possible problems are the size of the images and the batch size. Reduce the image size to 64 x 64 and change the batch size to 5. If that still raises the error, try also kicking out this dense layer.
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
If these reductions still cause the error then I have the following questions: are you running on GPU/CPU, and which one?
Just to repeat myself: the code is fine, just needs a few changes perhaps.