enter image description here
Code:
resnet_model = tf.keras.models.Sequential()
pretrained_model= tf.keras.applications.ResNet50(include_top=False,
input_shape=(48,48,1),
pooling='avg',classes=7,
weights='imagenet')
for layer in pretrained_model.layers:
layer.trainable=False
resnet_model.add(pretrained_model)
resnet_model.add(tf.keras.layers.Flatten())
resnet_model.add(tf.keras.layers.Dense(512, activation='relu'))
resnet_model.add(tf.keras.layers.Dense(5, activation='softmax'))
I want to use Resnet50 for 1 channel but I am getting the error. Is there any solution to this problem?
Related
I work on image classification with 10 classes.
each image is represented as a set of sequences (=75 sequence). Each sequence is represented as a set (=42 visual words) of visuel words. each word is encoded accoardind to a visual vocabulary (size=200)
so each image is represented as a tensor of shape (75, 42,200).
I want to use LSTM network to model this image representation using this code
model = Sequential()
model.add(LSTM(128, activation='relu', input_shape=(75, 42,200))))
model.add(Dense(10, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()
i get this error message:
ValueError Traceback (most recent call last)
<ipython-input-30-da9ec53d6d59> in <module>
1 model = Sequential()
----> 2 model.add(LSTM(128, activation='relu', input_shape=(75,42,200))) #number_of_hidden_units=128
3 model.add(Dense(10, activation='softmax')) #since number of output classes is 10
4 model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
5 model.summary()
2 frames
/usr/local/lib/python3.7/dist-packages/keras/engine/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
212 ndim = shape.rank
213 if ndim != spec.ndim:
--> 214 raise ValueError(f'Input {input_index} of layer "{layer_name}" '
215 'is incompatible with the layer: '
216 f'expected ndim={spec.ndim}, found ndim={ndim}. '
ValueError: Input 0 of layer "lstm_1" is incompatible with the layer: expected ndim=3, found ndim=4. Full shape received: (None, 75, 42, 200)
What is wrong. Please help
thank you
perform LSTM model with more than 3D image representation
I am very new in this field. I searched on the internet but I could not find a solution. I am waiting for the help of people who are interested in this field.
My model
def load_VGG16_model():
base_model = VGG16(weights='imagenet', include_top=False, input_shape=(256,256,3))
print("Model loaded..!")
return base_model
Summary of the model
load_VGG16_model().summary()
Adding Layers
def action_model(shape=(30, 256, 256, 3), nbout=len(classes)):
convnet = load_VGG16_model()
model = Sequential()
model.add(TimeDistributed(convnet, input_shape=shape))
model.add(LSTM(30,return_sequences=True,input_shape=(30,512))) # the error shows this line.
top_model.add(Dense(4096, activation='relu', W_regularizer=l2(0.1)))
top_model.add(Dropout(0.5))
top_model.add(Dense(4096, activation='relu', W_regularizer=l2(0.1)))
top_model.add(Dropout(0.5))
model.add(Dense(nbout, activation='softmax'))
return model
model.add(LSTM(30,return_sequences=True,input_shape=(30,512))) ==> the error shows this line.
Your problem is similar to this one Building CNN + LSTM in Keras for a regression problem. What are proper shapes?
Using reshape layer before the LSTM should work fine for you
def action_model(shape=(256, 256, 3), nbout=len(classes)):
convnet = load_VGG16_model()
model = Sequential()
model.add(convnet)
model.add(tf.keras.layers.Reshape((8*8, 512))) # Shape comes from the last output of covnet
model.add(LSTM(30,return_sequences=True,input_shape=(8*8,512))) # the error shows this line.
top_model.add(Dense(4096, activation='relu', W_regularizer=l2(0.1)))
top_model.add(Dropout(0.5))
top_model.add(Dense(4096, activation='relu', W_regularizer=l2(0.1)))
top_model.add(Dropout(0.5))
model.add(Dense(nbout, activation='softmax'))
return model
I am attempting to implement a custom loss functoin in Keras. It requires that I compute the sum of the inverse class frequencies for each y in B
It is the 1/epsilon(...) portion of the below function
The functoin is from this paper - Page 7
Note: I most definitely could be misinterpreting what the paper is describing to do. Please let me know if I am
I am currently trying to use a Keras Callback and the on_batch_start/end methods to try and determine the class frequency of the input batch (which means accessing y_true of the batch input), but am having little luck.
Thank you in advance for any help you can offer.
Edit: By "little luck" I mean I cannot find a way to access the y_true of an individual batch during training. Example: batch_size = 64, train_features.shape == (50000, 120, 20), I cannot find a way to access the y_true of an individual batch during training. I can access the keras model from on_batch_start/end (self.model), but I cannot find a way to access the actual y_true of the batch, size 64.
from tensorflow.python.keras.callbacks import Callback
class FreqReWeight(Callback):
"""
Update learning rate by batch label frequency distribution -- for use with LDAM loss
"""
def __init__(self, C):
self.C = C
def on_train_begin(self, logs={}):
self.model.custom_val = 0
def on_batch_end(self, batch, logs=None):
print('batch index', batch)
print('Model being trained', self.model)
# how can one access the y_true of the batch?
LDAM Loss Function
zj = "the j-th output of the model for the j-th class"
EDIT2
Loss Function - for testing when loss is called
def LDAM(C):
def loss(y_true, y_pred):
print('shape', y_true.shape) # only prints each epoch, not each batch
return K.mean(y_pred) + C # NOT LDAM, just dummy for testing purposes
return loss
Preparing Data, Compiling Model & Training
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()
y_train = to_categorical(y_train, 10)
y_test = to_categorical(y_test, 10)
m = 64 # batch_size
model = keras.Sequential()
model.add(Conv2D(32, (3, 3), padding='same',
input_shape=x_train.shape[1:]))
model.add(Activation('relu'))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(10))
model.add(Activation('softmax'))
model.compile(loss=LDAM(1), optimizer='sgd', metrics=['accuracy'])
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
model.fit(x_train, y_train,
batch_size=m,
validation_data=(x_test, y_test),
callbacks=[FreqReWeight(1)])
Solution
Ended up asking a more specific question regarding this.
Answer to both can be found here
I have the following (2D) convolutional neural network in Keras for image classification with binary labels:
model = keras.Sequential()
model.add(Conv2D(32, kernel_size=5, activation='relu', input_shape=(128, 128, 1)))
model.add(MaxPooling2D(pool_size=2))
model.add(Conv2D(64, kernel_size=5, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Flatten())
model.add(Dense(1024, activation="relu"))
model.add(Dense(2, activation="softmax"))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
To train it, I have a lot of (.jpeg) image files, but too many to load all at once. Hence I use the following generator (and preprocessing):
def load_preprocess(path):
img = img_to_array(load_img(path, target_size=(128, 128)))
output = rgb_to_grayscale(img)
output = tf.reshape(output, (-1,128, 128, 1))
return output
def image_generator(paths, labels, batch_size=32):
while True:
for i in range(0, len(paths), batch_size):
images = [load_preprocess(path) for path in paths[i:i+batch_size]]
target = labels[i:i+batch_size]
yield(images, target)
I tried training the network using
model.fit_generator(image_generator(train_paths, train_labels), steps_per_epoch=int(np.ceil(len(train_paths)/32)), epochs=1)
Here train_paths is a list of paths and train_labels is a binary numpy array with two columns.
However, this gives me the following error:
InvalidArgumentError: Requested tensor connection from unknown node: "conv2d_input:0".
What causes this error and how do I solve it? I tried googling it, but I found no hits at all.
I found the error: the images are tensors and should be converted to arrays. I do this as follows:
def image_generator(paths, labels, batch_size=32):
sess = tf.Session()
while True:
for i in range(0, len(paths), batch_size):
with sess.as_default():
images = [load_preprocess(path).eval() for path in paths[i:i+batch_size]]
target = labels[i:i+batch_size]
yield(np.array(images), target)
I am using Keras on Python2.
Does anyone know how to check and modify the learning rate for the ADAM optimizer please ? Here is my neural network and I defined my own optimizer. When training on batches with model.train_on_batch(...) I have no way to track the learning rate. Thanks for your help
def CNN_model():
# Create model
model = Sequential()
model.add(Conv2D(12, (5, 5), input_shape=(1, 256, 256), activation='elu'))
model.add(MaxPooling2D(pool_size=(3, 3)))
model.add(Conv2D(12, (5, 5), activation='elu'))
model.add(MaxPooling2D(pool_size=(4, 4)))
model.add(Conv2D(12, (3, 3), activation='elu'))
model.add(MaxPooling2D(pool_size=(3, 3)))
model.add(Flatten())
model.add(Dropout(0.3))
model.add(Dense(128, activation='elu'))
model.add(Dropout(0.3))
model.add(Dense(32, activation='elu'))
model.add(Dense(2, activation='softmax'))
# Compile model
my_optimizer = Adam(lr=0.001, decay=0.05)
model.compile(loss='categorical_crossentropy', optimizer=my_optimizer, metrics=['accuracy'])
return model
You can do it in several ways. The simplest thing in my mind is to do it through callbacks
from keras.callbacks import Callback
from keras import backend as K
class showLR( Callback ) :
def on_epoch_begin(self, epoch, logs=None):
lr = float(K.get_value(self.model.optimizer.lr))
print " epoch={:02d}, lr={:.5f}".format( epoch, lr )
You can use ReduceLROnPlateau callback. On your callbacks list add ReduceLROnPlateau callback and then just include your callback list to your train scheme.
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
callbacks= [ReduceLROnPlateau(monitor='val_acc',
patience=5,
verbose=1,
factor=0.5,
min_lr=0.00001)]
model=CNN_model()
model.fit(x_train, y_train, batch_size=batch_size,
epochs=epochs,
validation_data=(x_valid, y_valid),
callbacks = callbacks)