We Keep Coding

Model was constructed with shape (None, 28) problem

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)

ValueError: Shapes (None, 3) and (None, 30, 30, 3) are incompatible despite being one hot encoded

I'm working on a CNN but I keep running into this error:
ValueError: Shapes (None, 3) and (None, 30, 30, 3) are incompatible
My y_train and y_test are one hot encoded but that's having no impact.
Any advice?
import numpy as np
from numpy import random
import tensorflow as tf
from tensorflow.keras.models import Sequential
#from tensorflow.keras.utils import to_categorical
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten, Conv2D, MaxPooling2D
import pickle
from tensorflow.keras.optimizers import SGD
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.preprocessing import image
from tensorflow.keras.optimizers import RMSprop
import matplotlib.pyplot as plt
import cv2
import os
X_train = pickle.load(open("X_train.pickle","rb"))
y_train = pickle.load(open("y_train.pickle","rb"))
#y_train = np.array(y_train)
y_train = tf.keras.utils.to_categorical(y_train, num_classes=3)
X_test = pickle.load(open("X_test.pickle","rb"))
y_test = pickle.load(open("y_test.pickle","rb"))
#y_test = np.array(y_test)
y_test = tf.keras.utils.to_categorical(y_train, num_classes=3)
model = Sequential()
model.add(Dense(64, activation='relu',input_shape = X_train.shape[1:]))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(3, 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.fit(X_train, y_train,
epochs=2000,
batch_size=128,
validation_split = 0.1)

Shape incompatible error while using ImageDataGenerator for transfer learning

I want to create a classification model. For this purpose I have collected some images from 3 different classes. First, I have implemented Xception model ( freezed all layers except the last one). However, it overfitted. Then, I have decided to use data augmentation strategy. This is the first time I have used Keras module for this purpose. I belive that I have correctly used it. But getting error ValueError: Shapes (None, None) and (None, None, None, 3) are incompatible. I have tried what I found from the web, but did not works. Can anyone point the what I am doing wrong? Here is the code.
from tensorflow import keras
from matplotlib import pyplot as plt
from keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.preprocessing import image
from tensorflow.keras.applications.imagenet_utils import preprocess_input
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten, Activation
from tensorflow.keras.layers import Conv2D, MaxPooling2D
from tensorflow.keras.models import Model
# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1./255)
# this is a generator that will read pictures found in
# subfolers of 'data/train', and indefinitely generate
# batches of augmented image data
train_generator = train_datagen.flow_from_directory(
'data2/train', # this is the target directory
target_size=(299, 299), # all images will be resized to 299x299 for the Xception
batch_size=32,
class_mode="categorical")
# this is a similar generator, for validation data
validation_generator = test_datagen.flow_from_directory(
'data2/validation',
target_size=(299, 299),
batch_size=32,
class_mode="categorical")
Xception = keras.applications.Xception(weights='imagenet', include_top=False)
num_classes=3
inp = Xception.input
new_classification_layer = Dense(num_classes, activation='softmax')
out = new_classification_layer(Xception.layers[-2].output)
model_Xception = Model(inp, out)
model_Xception.summary()
for l, layer in enumerate(model_Xception.layers[:-1]):
layer.trainable = False
for l, layer in enumerate(model_Xception.layers[-1:]):
layer.trainable = True
opt=keras.optimizers.Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-07)
model_Xception.compile(loss='categorical_crossentropy',
optimizer=opt,
metrics=['accuracy'])
model_Xception.summary()
model_Xception.fit_generator(
train_generator,
epochs=5,
validation_data=validation_generator)
model_Xception.save_weights('first_try.h5')

That's because you are feeding a convolution's output to a Dense layer.
You need to add one of Flatten, GlobalMaxPooling2D or GlobalAveragePooling2D in order to transform your output to (batch_size, input_size). You can change these lines:
inp = Xception.input
out_xception = Xception.layers[-2].output
flatten = tf.keras.layers.Flatten()(out_xception)
new_classification_layer = tf.keras.layers.Dense(num_classes, activation='softmax')
out = new_classification_layer(flatten)
model_Xception = tf.keras.Model(inp, out)
model_Xception.summary()
Second thing is since you did not specify input_shape while defining the Xception model, Flatten will throw an error. Simply change it to:
Xception = tf.keras.applications.Xception(weights='imagenet', include_top=False,
input_shape = (299,299,3))

Im trying to do fine-tuning with Keras, but it doesnt work

im trying to do some finetuning with the infamous Diabetic Retinopaty Dataset.
So as i know, im followging those steps
-Train a VGG16 network without head layers, loading imagenet weights and freezing all conv layers for a few epochs.
-Unfreeze some conv layers (the last block) and training again.
The fact is that i always obtain the same acc score again and again. When i train the model with all layers frozen and the imagenet weights, i get almost 0.74. And when i unfreze some layers and train again, i get the exact same score, its seems like it does nothing.
Im using Tensorflow-Gpu 2.0 and Keras 2.3.0.
Here is my code:
from __future__ import absolute_import, division, print_function, unicode_literals
import os
import tensorboard
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dropout, Flatten, Dense
from tensorflow.keras.layers import Conv2D, MaxPooling2D, GlobalAveragePooling2D, GlobalMaxPooling2D, Input
import pandas as pandas
from tensorflow.keras.applications import vgg16
import tensorflow as tf
from tensorflow.keras.models import Model
import datetime
from keras.callbacks import TensorBoard
import pkg_resources
from keras import callbacks
from PIL import Image
import numpy as np
from pathlib import Path
import tensorflow.keras as k
for entry_point in pkg_resources.iter_entry_points('tensorboard_plugins'):
print(entry_point.dist)
#-----------------------------------------------------------
#Corregir el fallo de la CPU
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
#os.environ["PATH"].append("C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v10.0/bin/cudart64_100.dll")
print("Num GPUs Available: ", len(tf.config.experimental.list_physical_devices('GPU')))
#------------------------------------------------------------
trainLabels = pandas.read_csv("./trainLabels_cropped.csv", dtype=str)
#Hay que añadir la extension a la lista de imagenes
def append_ext(fn):
return fn+".jpeg"
trainLabels["image"]=trainLabels["image"].apply(append_ext)
#test_data["id_code"]=test_data["id_code"].apply(append_ext)
train_datagen = ImageDataGenerator(
zoom_range=[-0.5, 0.5],
width_shift_range=[-5, 5],
height_shift_range=[-5, 5],
rotation_range=5,
shear_range=5,
#samplewise_center=True,
#samplewise_std_normalization=True,
#fill_mode='nearest',
validation_split=0.25)
train_generator = train_datagen.flow_from_dataframe(
dataframe=trainLabels,
directory='resized_train_cropped/resized_train_cropped/',
x_col="image",
y_col="level",
target_size=(224, 224),
batch_size=10,
class_mode='categorical',
color_mode='rgb', #quitar o no quitar
subset='training')
validation_generator = train_datagen.flow_from_dataframe(
dataframe=trainLabels,
directory='resized_train_cropped/resized_train_cropped/',
x_col="image",
y_col="level",
target_size=(224, 224),
batch_size=10,
class_mode='categorical',
color_mode='rgb',
subset='validation')
basemodel=Sequential()
baseModel=vgg16.VGG16(weights="imagenet", include_top=False, input_tensor=Input(shape=(224, 224, 3)))
for l in baseModel.layers:
l.trainable=False
for layer in baseModel.layers:
print("{}: {}".format(layer, layer.trainable))
headModel = baseModel.output
headModel = Flatten(name="flatten")(headModel)
headModel = Dense(512, activation="relu")(headModel)
headModel = Dropout(0.5)(headModel)
headModel = Dense(5, activation="softmax")(headModel)
model = Model(inputs=baseModel.input, outputs=headModel)
optimizer=k.optimizers.Adam(learning_rate=1e-4)
model.compile(loss='categorical_crossentropy',
optimizer=optimizer,
metrics=['acc'])
#Model Summary
model.summary()
log_dir="logs\\fit\\" +'Prueba'+ datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard_callback = TensorBoard(log_dir=log_dir, histogram_freq=1)
parada=callbacks.callbacks.EarlyStopping(monitor='acc',mode='max',verbose=1,restore_best_weights=True,patience=2)
learningRate=callbacks.callbacks.ReduceLROnPlateau(monitor='acc', factor=0.1, verbose=1, mode='max', min_delta=0.0001, cooldown=0, min_lr=0,patience=2)
#checkpoint=keras.callbacks.callbacks.ModelCheckpoint('\\pesos\\weights', monitor='acc', verbose=0, save_best_only=True, save_weights_only=True, mode='auto', period=1)
model.fit_generator(
train_generator,
steps_per_epoch=250,
epochs=20,
validation_data=validation_generator,
validation_steps=250
#callbacks=[parada]
)
train_generator.reset()
validation_generator.reset()
for l in baseModel.layers[15:]:
l.trainable=True
for layer in baseModel.layers:
print("{}: {}".format(layer, layer.trainable))
optimizer=k.optimizers.Adam(learning_rate=1e-6)
model.compile(loss='categorical_crossentropy',
optimizer=optimizer,
metrics=['acc'])
model.fit_generator(
train_generator,
steps_per_epoch=250,
epochs=30,
validation_data=validation_generator,
validation_steps=250
#callbacks=[parada]
)

Try the following :
1) Add a couple of more dense layers.
2) Try using other activation functions such as 'tanh' and see if that helps. (ReLU could cause an update in a neuron that prevents any subsequent data points from altering it's weights via the gradient)

Keras CNN-LSTM RuntimeError

I'm trying to use the following model Inceptionv3 base CNN and LSTM layer for a regression problem. My input data is pictures with continuous target values. I'd like to feed the sequence of images to a CNN and after to an LSTM layer. However i get a
RuntimeError: You must compile your model before using it
message. Any idea what can be the cause? I tried to find out in github and on several pages but i didnt succeed.
from keras.applications.inception_v3 import InceptionV3
from keras.models import Sequential, Model
from keras.preprocessing.image import ImageDataGenerator
from keras.layers import Dense, Activation, Flatten, Dropout, BatchNormalization, Conv2D, MaxPooling2D, GlobalAveragePooling2D, LSTM, TimeDistributed, Input
from keras.optimizers import SGD, RMSprop
from keras.callbacks import EarlyStopping, ModelCheckpoint, CSVLogger, ReduceLROnPlateau
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
# custom R2-score metrics for keras backend
#https://www.kaggle.com/c/mercedes-benz-greener-manufacturing/discussion/34019
from keras import backend as K
def r2_keras(y_true, y_pred):
SS_res = K.sum(K.square(y_true - y_pred))
SS_tot = K.sum(K.square(y_true - K.mean(y_true)))
return ( 1 - SS_res/(SS_tot + K.epsilon()) )
train_data_dir = '...'
test_data_dir = '...'
train_df = pd.read_csv('...')
valid_df = pd.read_csv('...')
filepath_loss = '...'
filepath_csv = '...'
datagen=ImageDataGenerator(rescale=1./255.,)
img_width, img_height = 380, 380
frames = 5
channels = 3
pictures = Input(shape=(frames, img_width, img_height, channels))
train_generator=datagen.flow_from_dataframe(
dataframe=train_df,
directory=train_data_dir,
x_col="block_heights",
y_col="weighted_prices",
has_ext=False, #x_col column doesnt has the file extensions
#subset="training", if validation split is set in ImageDataGenerator
batch_size=16,
seed=42,
shuffle=False,
class_mode="other", #for regression other should be used
target_size=(img_width, img_height))
valid_generator=datagen.flow_from_dataframe(
dataframe=valid_df,
directory=train_data_dir,
x_col="block_heights",
y_col="weighted_prices",
has_ext=False, #x_col column doesnt has the file extensions
#subset="validation", if validation split is set in ImageDataGenerator
batch_size=16,
seed=42,
shuffle=False,
class_mode="other",
target_size=(img_width, img_height))
conv_base = InceptionV3(weights=None, include_top=False, input_shape=(img_width,img_height,3))
conv_base.trainable = True
model = Sequential()
model.add(TimeDistributed(conv_base))
model.add(TimeDistributed(Flatten()))
model.add(LSTM(10, return_sequences=True))
model.add(Dense(512, activation='relu'))
model.add(Dense(1, activation='linear'))
#error at callbacks if the learning rate is explicitly set somewhere
rms = RMSprop(lr=0.1, rho=0.9, epsilon=None, decay=0.0)
model.compile(loss='mse', optimizer=rms, metrics=['mae', r2_keras])
STEP_SIZE_TRAIN=train_generator.n//train_generator.batch_size
STEP_SIZE_VALID=valid_generator.n//valid_generator.batch_size
callbacks = [EarlyStopping(monitor='val_loss', patience=10, verbose=1, mode='auto'),
ReduceLROnPlateau(monitor='val_loss', factor=0.02, patience=3, min_lr=0.001),
ModelCheckpoint(filepath_loss, monitor='val_loss', verbose=1, save_best_only=True, mode='min'),
CSVLogger(filepath_csv, separator = ",", append = False)]
history = model.fit_generator(generator=train_generator,steps_per_epoch=STEP_SIZE_TRAIN, validation_data=valid_generator, validation_steps=STEP_SIZE_VALID, epochs=50, callbacks=callbacks)