I recently started learning Tensorflow and am following this guide.
https://pythonprogramming.net/convolutional-neural-network-deep-learning-python-tensorflow-keras/
I am attempting to use my own data sheet with two labels as well (car and not car).
This is my code:
import tensorflow as tf
from tensorflow.keras.datasets import cifar10
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten
from tensorflow.keras.layers import Conv2D, MaxPooling2D
import pickle
pickle_in = open("X.pickle","rb")
X = pickle.load(pickle_in)
pickle_in = open("y.pickle","rb")
y = pickle.load(pickle_in)
X = X/255.0
model = Sequential()
model.add(Conv2D(256, (3, 3), input_shape=X.shape[1:]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(256, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten()) # this converts our 3D feature maps to 1D feature vectors
model.add(Dense(64))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.fit(X, y, batch_size=32, epochs=3, validation_split=0.3)
model.save('car.model')
However, I'm getting an error that I do not understand how to fix.
raise ValueError(msg)
ValueError: Data cardinality is ambiguous:
x sizes: 8406
y sizes: 0
Please provide data which shares the same first dimension.
Appreciate the help!
Related
I've created sound classifier build using Keras from some tutorials in the internet. Here is my model code
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, InputLayer, Dropout, Conv1D, Conv2D, Flatten, Reshape, MaxPooling1D, MaxPooling2D, BatchNormalization, TimeDistributed
from tensorflow.keras.optimizers import Adam
model = Sequential()
model.add(Reshape((int(input_length / 40), 40), input_shape=(input_length, )))
model.add(Conv1D(8, kernel_size=3, activation='relu', padding='same'))
model.add(MaxPooling1D(pool_size=2, strides=2, padding='same'))
model.add(Dropout(0.25))
model.add(Conv1D(16, kernel_size=3, activation='relu', padding='same'))
model.add(MaxPooling1D(pool_size=2, strides=2, padding='same'))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(classes, activation='softmax', name='y_pred'))
opt = Adam(lr=0.005, beta_1=0.9, beta_2=0.999)
# this controls the batch size, or you can manipulate the tf.data.Dataset objects yourself
BATCH_SIZE = 32
train_dataset = train_dataset.batch(BATCH_SIZE, drop_remainder=False)
validation_dataset = validation_dataset.batch(BATCH_SIZE, drop_remainder=False)
model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])
model.fit(train_dataset, epochs=1000, validation_data=validation_dataset, verbose=2, callbacks=callbacks)
My teacher ask me what is algorithm I use for classifying (he said something like K-NN, Naive Bayes, SVM or something like that), and I don't know what I'm using.
You're using a Convolutional Neural Network (CNN)
so I'm new right here and in Python also. I'm trying to make my own network. I found some pictures of docs and cats 15x15 and unfortunatly couldn't make this basic network...
So, these are libraries which I'm using
from tensorflow.keras.models import Sequential
from tensorflow.keras import utils
from tensorflow.keras.datasets import mnist
from tensorflow.keras.layers import Dense
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
import keras
from tensorflow.keras.layers import Conv2D
from tensorflow.keras.layers import MaxPooling2D
from tensorflow.keras.layers import GlobalMaxPooling2D
Body
train_dataset = tf.keras.preprocessing.image_dataset_from_directory(
'drive/MyDrive/cats vs dogs/cats vs dogs/training',
color_mode="rgb",
batch_size=32,
image_size=(150, 150),
shuffle=True,
seed=42,
validation_split=0.1,
subset='training',
interpolation="bilinear",
follow_links=False,
)
validation_dataset = tf.keras.preprocessing.image_dataset_from_directory(
'drive/MyDrive/cats vs dogs/cats vs dogs/training',
color_mode="rgb",
batch_size=32,
image_size=(150, 150),
shuffle=True,
seed=42,
validation_split=0.1,
subset='validation',
interpolation="bilinear",
follow_links=False,
)
test_dataset = tf.keras.preprocessing.image_dataset_from_directory(
'drive/MyDrive/cats vs dogs/cats vs dogs/test',
batch_size = 32,
image_size = (150, 150),
interpolation="bilinear"
)
model = Sequential()
model.add(keras.Input(shape=(150, 150, 3)))
model.add(Conv2D(32, 5, strides=2, activation="relu"))
model.add(Conv2D(32, 3, activation="relu"))
model.add(MaxPooling2D(3))
model.add(Dense(250, activation='sigmoid'))
model.add(Dense(100))
model.add(MaxPooling2D(3))
model.add(Dense(2))
model.summary()
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
history = model.fit(train_dataset, validation_data=validation_dataset, epochs=5, verbose=2)
And I get this error
Incompatible shapes: [29] vs. [29,7,7,2]
[[node gradient_tape/binary_crossentropy/mul_1/BroadcastGradientArgs
(defined at /usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/optimizer_v2.py:464)
]] [Op:__inference_train_function_4364]
Errors may have originated from an input operation.
Input Source operations connected to node
gradient_tape/binary_crossentropy/mul_1/BroadcastGradientArgs:
In[0] gradient_tape/binary_crossentropy/mul_1/Shape:
In[1] gradient_tape/binary_crossentropy/mul_1/Shape_1
I was trying to change from binary_crossentropy to categorical_crossentrapy but it didn't help, I suppose my mistake is in datasets or inputs but I don't know how to solve it :(
Really hope to find help here!
[my architecture][1]
[1]: https://i.stack.imgur.com/w4Y9N.png
You need to flatten your prediction somewhere, otherwise you are outputing an image (29 samples of size 7x7 with 2 channels), while you simply want a flat 2 dimensional logits (so shape 29x2). The architecture you are using is somewhat odd, did you mean to have flattening operation before first Dense layer, and then no "maxpooling2d" (as it makes no sense for flattened signal)? Mixing relu and sigmoid activations is also quite non standard, I would encourage you to start with established architectures rather than try to compose your own to get some intuitions.
model = Sequential()
model.add(keras.Input(shape=(150, 150, 3)))
model.add(Conv2D(32, 5, strides=2, activation="relu"))
model.add(Conv2D(32, 3, activation="relu"))
model.add(MaxPooling2D(3))
model.add(Flatten())
model.add(Dense(250, activation="relu"))
model.add(Dense(100, activation="relu"))
model.add(Dense(2))
model.summary()
I am following a tutorial at https://medium.com/#vijayabhaskar96/tutorial-image-classification-with-keras-flow-from-directory-and-generators-95f75ebe5720
I am using 'ImageDataGenerator' object and want to predict the out put using the following method.
pred=model.predict_generator(test_generator,
steps=10,
verbose=1)
predicted_class_indices=np.argmax(pred,axis=1)
labels = (train_generator.class_indices)
labels = dict((v,k) for k,v in labels.items())
predictions = [labels[k] for k in predicted_class_indices]
But I am using Keras 'ImageDataGenerator' and 'flow_from_dataframe' object.
'ImageDataGenerator' has no 'class_indices' attribute. How can I get the indices of the classes
End to End example which uses ImageDataGenerator.flow_from_dataframe and which answers your question of How can I get the indices of the classes
from tensorflow.keras.models import Sequential
#Import from keras_preprocessing not from keras.preprocessing
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.layers import Dense, Activation, Flatten, Dropout, BatchNormalization
from tensorflow.keras.layers import Conv2D, MaxPooling2D
from tensorflow.keras import regularizers, optimizers
import pandas as pd
import numpy as np
def append_ext(fn):
return fn+".png"
traindf=pd.read_csv("trainLabels.csv",dtype=str)
testdf=pd.read_csv("sampleSubmission.csv",dtype=str)
traindf["id"]=traindf["id"].apply(append_ext)
testdf["id"]=testdf["id"].apply(append_ext)
datagen=ImageDataGenerator(rescale=1./255.,validation_split=0.25)
train_generator=datagen.flow_from_dataframe(
dataframe=traindf,
directory="train/",
x_col="id",
y_col="label",
subset="training",
batch_size=32,
seed=42,
shuffle=True,
class_mode="categorical",
target_size=(32,32))
valid_generator=datagen.flow_from_dataframe(
dataframe=traindf,
directory="train/",
x_col="id",
y_col="label",
subset="validation",
batch_size=32,
seed=42,
shuffle=True,
class_mode="categorical",
target_size=(32,32))
test_datagen=ImageDataGenerator(rescale=1./255.)
test_generator=test_datagen.flow_from_dataframe(
dataframe=testdf,
directory="test/",
x_col="id",
y_col=None,
batch_size=32,
seed=42,
shuffle=False,
class_mode=None,
target_size=(32,32))
model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same',
input_shape=(32,32,3)))
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(Conv2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(64, (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, activation='softmax'))
model.compile(optimizers.RMSprop(lr=0.0001, decay=1e-6),loss="categorical_crossentropy",metrics=["accuracy"])
STEP_SIZE_TRAIN=train_generator.n//train_generator.batch_size
STEP_SIZE_VALID=valid_generator.n//valid_generator.batch_size
STEP_SIZE_TEST=test_generator.n//test_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
)
model.evaluate_generator(generator=valid_generator,
steps=STEP_SIZE_TEST)
test_generator.reset()
pred=model.predict_generator(test_generator,
steps=STEP_SIZE_TEST,
verbose=1)
predicted_class_indices=np.argmax(pred,axis=1)
labels = (train_generator.class_indices)
labels = dict((v,k) for k,v in labels.items())
predictions = [labels[k] for k in predicted_class_indices]
Finally, we print the Classes as shown below:
print(predictions)
Output of above print statement is:
['bird',
'dog',
'bird',
'cat',
'horse',
'deer',
'deer',
'airplane',
'cat',
'cat',
'ship',
'bird',
'automobile',..........]
For more information, please refer this Article written by Vijaya Bhaskar.
Hope this helps. Happy Learning!
I am working on a Speaker recognition problem, I have very big number of classes so I need to use, tf.nn.sampled_softmax_loss to speed up training time. The problem is I am using Keras with Tensorflow as Backend, but Keras doesnt implement Sampled_softmax so I need to use Tensorflow function, but its unclear which should be the inputs of the tf.nn.sampled_softmax_loss() function.
My model and input are as below:
from preprocess import *
import keras
from sklearn.model_selection import train_test_split
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D,AveragePooling2D
from keras.utils import to_categorical
from keras.utils import plot_model
from keras.models import load_model
from keras import regularizers
import numpy as np
from keras.callbacks import EarlyStopping
from keras import metrics
import os
import tensorflow as tf
from tensorflow.python.framework import dtypes
from importance_sampling.training import ImportanceTraining
epochs = 50
batch_size = 100
verbose = 1
labels= get_labels(big_numpy_files_path)
num_classes = len(labels)
#save_data_as_numpy_array(max_len = feature_dim_1, max_len2 = feature_dim_2,origin_path=data_set_path,destination_path=numpy_files_path)
#Get X & Y
X_train, X_valid, X_test ,y_train,y_valid,y_test = get_x_y_data(split_ratio=0.8, random_state=42,maxsamples=20,path=big_numpy_files_path)
#reshape X for input into CNN
X_train, X_valid, X_test = reshape_prepare_for_input(X1=X_train, X2=X_valid, X3=X_test,channel=1)
#Dimensions
dim_1 = X_train.shape[1]
dim_2 = X_train.shape[2]
dim_3 = X_train.shape[3]
#one hot encoding of Y
y_train_hot = to_categorical(y_train)
y_valid_hot = to_categorical(y_valid)
y_test_hot = to_categorical(y_test)
#Model
model = Sequential()
model.add(Conv2D(128, kernel_size=(6, 6),strides=2, activation='relu', input_shape=(X_train.shape[1], X_train.shape[2], X_train.shape[3])))
model.add(Conv2D(64, kernel_size=(2, 2),strides=1, activation='relu'))
model.add(Conv2D(32, kernel_size=(2, 2), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.3))
model.add(Flatten())
model.add(Dense(256, activation='relu', use_bias=True,kernel_regularizer=regularizers.l2(0.01)))
model.add(Dropout(0.2))
model.add(Dense(256, activation='relu',use_bias=True,kernel_regularizer=regularizers.l2(0.02)))
model.add(Dropout(0.3))
model.add(Dense(256, activation='relu',use_bias=True,kernel_regularizer=regularizers.l2(0.02)))
model.add(Dropout(0.3))
model.add(Dense(num_classes, activation='softmax'))
loss=keras.losses.categorical_crossentropy
model.compile(loss=loss,optimizer='adamax',metrics=['accuracy'])
earlystopping = EarlyStopping(monitor='val_loss', min_delta=0.001, patience=15, verbose=verbose, mode='auto')
model.fit(X_train, y_train_hot,batch_size=batch_size,callbacks=[earlystopping],epochs=epochs, verbose=verbose, validation_data=(X_valid, y_valid_hot))
If I want to replace the above loss function with Samled softmax, If I'm trying to do something like below, what should be the inputs give my above architecture and should I add tf.reduce_mean?
for more details on the code, is https://github.com/selimelawwa/Speaker_Verification
I want to create an image classifier using keras, and train it with a few example images. Then, i will be using pre-trained models and adding a few layers at the end, but first, i want to understand keras and CNNs.
My console prints the following error:
ValueError: Error when checking target: expected dense_2 to have shape
(None, 2) but got array with shape (321, 3)
Here is my code:
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import sys
import time
import numpy as np
import cv2
import time
from PIL import Image
import keras
import glob
from keras.models import Sequential
from keras.models import load_model
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.optimizers import SGD
from sklearn.preprocessing import LabelBinarizer
labels = ['buena', 'mala', 'otro']
def to_one_hot(labels, ys):
result = np.zeros((len(ys),len(labels)))
for i in range(result.shape[0]):
for j in range(result.shape[1]):
result[i,j] = int(ys[i] == labels[j])
return result
def build_dataset(labels):
num_classes = len(labels)
x = []
y = []
for label in labels:
for filename in (glob.glob('./tf_files/papas_fotos/'+label+'/*.jpg')):
img = cv2.imread(filename)
img = np.resize(img,(100,100, 3))
x.append(img)
y.append(label)
y = to_one_hot(labels, y)
# y = keras.utils.to_categorical(y, num_classes=3)
x = np.array(x)
x_train = x[20:]
y_train = y[20:]
x_test = x[:19]
y_test = y[:19]
print (x.shape, y.shape)
return x_train, y_train, x_test, y_test
model = Sequential()
# input: 100x100 images with 3 channels -> (100, 100, 3) tensors.
# this applies 32 convolution filters of size 3x3 each.
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(100, 100, 3)))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(256, 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)
x_train, y_train, x_test, y_test = build_dataset(labels)
model = load_model('thebestmodel.h5')
print (model)
model.fit(x_train, y_train, batch_size=32, epochs=20)
score = model.evaluate(x_test, y_test, batch_size=32)
model.save('thebestmodel.h5')
print (score)
What mistake am I making? I think that may be the size of my one hot encoded labels, but i can't make it work.
Thanks!
Although your code was fixed for this specific error, you're loading a saved model: model = load_model('thebestmodel.h5')
This is undoing everything before this line.