I am trying to classify the severity of COVID XRay using 426 256x256 xray images and 4 classes present. However the validation accuracy doesnt improve at all. The validation loss also barely decreases from the start
This is the model I am using
from keras.models import Sequential
from keras.layers import Dense,Conv2D,MaxPooling2D,Dropout,Flatten
from tensorflow.keras.callbacks import EarlyStopping
from tensorflow.keras import regularizers
model=Sequential()
model.add(Conv2D(filters=64,kernel_size=(4,4),input_shape=image_shape,activation="relu"))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.2))
model.add(Conv2D(filters=128,kernel_size=(6,6),input_shape=image_shape,activation="relu"))
model.add(MaxPooling2D(pool_size=(3,3)))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(64,activation="relu"))
model.add(Dense(16,activation="relu"))
model.add(Dense(4,activation="softmax"))
model.compile(loss="categorical_crossentropy",optimizer="adam",metrics=["accuracy"])
These are the outputs I get
epochs = 20
batch_size = 8
model.fit(X_train, y_train, validation_data=(X_test, y_test),
epochs=epochs,
batch_size=batch_size
)
Epoch 1/20
27/27 [==============================] - 4s 143ms/step - loss: 0.1776 - accuracy: 0.9528 - val_loss: 3.7355 - val_accuracy: 0.2717
Epoch 2/20
27/27 [==============================] - 4s 142ms/step - loss: 0.1152 - accuracy: 0.9481 - val_loss: 4.0038 - val_accuracy: 0.2283
Epoch 3/20
27/27 [==============================] - 4s 142ms/step - loss: 0.0875 - accuracy: 0.9858 - val_loss: 4.1756 - val_accuracy: 0.2391
Epoch 4/20
27/27 [==============================] - 4s 142ms/step - loss: 0.0521 - accuracy: 0.9906 - val_loss: 4.1034 - val_accuracy: 0.2717
Epoch 5/20
27/27 [==============================] - 4s 142ms/step - loss: 0.0496 - accuracy: 0.9858 - val_loss: 4.8433 - val_accuracy: 0.3152
Epoch 6/20
27/27 [==============================] - 4s 142ms/step - loss: 0.0170 - accuracy: 0.9953 - val_loss: 5.6027 - val_accuracy: 0.3043
Epoch 7/20
27/27 [==============================] - 4s 142ms/step - loss: 0.2307 - accuracy: 0.9245 - val_loss: 4.2759 - val_accuracy: 0.3152
Epoch 8/20
27/27 [==============================] - 4s 142ms/step - loss: 0.6493 - accuracy: 0.7830 - val_loss: 3.8390 - val_accuracy: 0.3478
Epoch 9/20
27/27 [==============================] - 4s 142ms/step - loss: 0.2563 - accuracy: 0.9009 - val_loss: 5.0250 - val_accuracy: 0.2500
Epoch 10/20
27/27 [==============================] - 4s 142ms/step - loss: 0.0286 - accuracy: 1.0000 - val_loss: 4.6475 - val_accuracy: 0.2391
Epoch 11/20
27/27 [==============================] - 4s 142ms/step - loss: 0.0097 - accuracy: 1.0000 - val_loss: 5.2198 - val_accuracy: 0.2391
Epoch 12/20
27/27 [==============================] - 4s 142ms/step - loss: 0.0037 - accuracy: 1.0000 - val_loss: 5.7914 - val_accuracy: 0.2500
Epoch 13/20
27/27 [==============================] - 4s 142ms/step - loss: 0.0048 - accuracy: 1.0000 - val_loss: 5.4341 - val_accuracy: 0.2391
Epoch 14/20
27/27 [==============================] - 4s 142ms/step - loss: 0.0044 - accuracy: 1.0000 - val_loss: 5.6364 - val_accuracy: 0.2391
Epoch 15/20
27/27 [==============================] - 4s 143ms/step - loss: 0.0019 - accuracy: 1.0000 - val_loss: 5.8504 - val_accuracy: 0.2391
Epoch 16/20
27/27 [==============================] - 4s 143ms/step - loss: 0.0013 - accuracy: 1.0000 - val_loss: 5.9604 - val_accuracy: 0.2500
Epoch 17/20
27/27 [==============================] - 4s 149ms/step - loss: 0.0023 - accuracy: 1.0000 - val_loss: 6.0851 - val_accuracy: 0.2717
Epoch 18/20
27/27 [==============================] - 4s 142ms/step - loss: 0.0134 - accuracy: 0.9953 - val_loss: 4.9783 - val_accuracy: 0.2717
Epoch 19/20
27/27 [==============================] - 4s 141ms/step - loss: 0.0068 - accuracy: 1.0000 - val_loss: 5.7421 - val_accuracy: 0.2500
Epoch 20/20
27/27 [==============================] - 4s 142ms/step - loss: 0.0024 - accuracy: 1.0000 - val_loss: 5.8480 - val_accuracy: 0.2283
Any tips on how i can solve this or If i am doing something wrong?
Related
I am training a DNN model to classify an image in two class: perfect image or imperfect image. I have 60 image for training with 30 images of each class. As for the limited data, I decided to check the model by overfitting i.e. by providing the validation data same as the training data. Here, I hoped to achieve 100% accuracy on both training and validation data(since training data set and validation dataset are the same).The training loss and validation loss seems to decrease however both training and validation accuracy are constant.
import tensorflow as tf
import tensorflow.keras as keras
from sklearn.preprocessing import LabelBinarizer
from sklearn.metrics import classification_report
from keras.models import Sequential
from keras.layers import Dropout
from keras.layers.core import Dense
from keras.optimizers import SGD
from keras.datasets import cifar10
import matplotlib.pyplot as plt
import numpy as np
import argparse
import cv2
import glob
initial_lr=0.001
#getting labels from Directories
right_labels=[]
wrong_labels=[]
rightimage_path=glob.glob("images/right_location/*")
wrongimage_path=glob.glob("images/wrong_location/*")
for _ in rightimage_path:
right_labels.append(1)
#print(labels)
for _ in wrongimage_path:
wrong_labels.append(0)
labelNames=["right_location","wrong_location"]
right_images=[]
wrong_images=[]
#getting images data from Directories
for img in rightimage_path:
im=cv2.imread(img)
im2=cv2.resize(im,(64,64))
im2=np.expand_dims(im2,axis=0)
max_pool=keras.layers.MaxPooling2D(pool_size=(2, 2),strides=(1, 1))
output=max_pool(im2)
output=np.squeeze(output)
output=output.flatten()
output=output/255
right_images.append(output)
#wrong images
for img in wrongimage_path:
im=cv2.imread(img)
im2=cv2.resize(im,(64,64))
im2=np.expand_dims(im2,axis=0)
max_pool=keras.layers.MaxPooling2D(pool_size=(2, 2),strides=(1, 1))
output=max_pool(im2)
output=np.squeeze(output)
output=output.flatten()
output=output/255
wrong_images.append(output)
#print(len(wrong_images))
trainX=right_images[:30]+wrong_images[:30]
trainX=np.array(trainX)
trainY=right_labels[:30]+wrong_labels[:30]
trainY=np.array(trainY)
#print(trainX[0].shape)
testX=trainX
testY=trainY
#testX=right_images[31:]+wrong_images[31:]
#testX=np.array(testX)
#print(len(testX))
#print(len(right_labels[31:]))
#testY=right_labels[31:]+wrong_labels[31:]
#testY=np.array(testY)
#print(testY)
print(trainY)
print(testY)
#Contruction of Neural Network model
model = Sequential()
model.add(Dense(1024, input_shape=(11907,), activation="relu"))
model.add(Dense(512, activation="relu"))
model.add(Dense(256, activation="relu"))
model.add(Dense(1, activation="softmax"))
#Training model
print("[INFO] training network...")
decay_steps = 1000
sgd = SGD(initial_lr,momentum=0.8)
lr_decayed_fn = tf.keras.experimental.CosineDecay(initial_lr, decay_steps)
model.compile(loss="binary_crossentropy", optimizer=sgd,metrics=["accuracy"])
H = model.fit(trainX, trainY, validation_data=(testX, testY),epochs=100, batch_size=1)
#evaluating the model
print("[INFO] evaluating network...")
predictions = model.predict(testX, batch_size=32)
print(predictions)
print(classification_report(testY,predictions, target_names=labelNames))
Training results:
[INFO] training network...
Epoch 1/100
60/60 [==============================] - 3s 43ms/step - loss: 0.8908 - accuracy: 0.4867 - val_loss: 0.6719 - val_accuracy: 0.5000
Epoch 2/100
60/60 [==============================] - 2s 41ms/step - loss: 0.6893 - accuracy: 0.4791 - val_loss: 0.8592 - val_accuracy: 0.5000
Epoch 3/100
60/60 [==============================] - 2s 41ms/step - loss: 0.7008 - accuracy: 0.5290 - val_loss: 0.6129 - val_accuracy: 0.5000
Epoch 4/100
60/60 [==============================] - 2s 41ms/step - loss: 0.6971 - accuracy: 0.5279 - val_loss: 0.5619 - val_accuracy: 0.5000
Epoch 5/100
60/60 [==============================] - 2s 41ms/step - loss: 0.6770 - accuracy: 0.4745 - val_loss: 0.5669 - val_accuracy: 0.5000
Epoch 6/100
60/60 [==============================] - 2s 41ms/step - loss: 0.5685 - accuracy: 0.5139 - val_loss: 0.4953 - val_accuracy: 0.5000
Epoch 7/100
60/60 [==============================] - 2s 41ms/step - loss: 0.5679 - accuracy: 0.5312 - val_loss: 0.8273 - val_accuracy: 0.5000
Epoch 8/100
60/60 [==============================] - 2s 41ms/step - loss: 0.4373 - accuracy: 0.6591 - val_loss: 0.8112 - val_accuracy: 0.5000
Epoch 9/100
60/60 [==============================] - 2s 41ms/step - loss: 0.7427 - accuracy: 0.5848 - val_loss: 0.5419 - val_accuracy: 0.5000
Epoch 10/100
60/60 [==============================] - 2s 40ms/step - loss: 0.4719 - accuracy: 0.5377 - val_loss: 0.3118 - val_accuracy: 0.5000
Epoch 11/100
60/60 [==============================] - 2s 40ms/step - loss: 0.3253 - accuracy: 0.4684 - val_loss: 0.4851 - val_accuracy: 0.5000
Epoch 12/100
60/60 [==============================] - 3s 42ms/step - loss: 0.5194 - accuracy: 0.4514 - val_loss: 0.1976 - val_accuracy: 0.5000
Epoch 13/100
60/60 [==============================] - 2s 41ms/step - loss: 0.3114 - accuracy: 0.6019 - val_loss: 0.3483 - val_accuracy: 0.5000
Epoch 14/100
60/60 [==============================] - 2s 41ms/step - loss: 0.3794 - accuracy: 0.6003 - val_loss: 0.4723 - val_accuracy: 0.5000
Epoch 15/100
60/60 [==============================] - 2s 41ms/step - loss: 0.4172 - accuracy: 0.5873 - val_loss: 0.4992 - val_accuracy: 0.5000
Epoch 16/100
60/60 [==============================] - 2s 41ms/step - loss: 0.3110 - accuracy: 0.4338 - val_loss: 0.6209 - val_accuracy: 0.5000
Epoch 17/100
60/60 [==============================] - 2s 41ms/step - loss: 0.6362 - accuracy: 0.6615 - val_loss: 0.2337 - val_accuracy: 0.5000
Epoch 18/100
60/60 [==============================] - 3s 42ms/step - loss: 0.1652 - accuracy: 0.5617 - val_loss: 0.0841 - val_accuracy: 0.5000
Epoch 19/100
60/60 [==============================] - 3s 42ms/step - loss: 0.1050 - accuracy: 0.4714 - val_loss: 0.2853 - val_accuracy: 0.5000
Epoch 20/100
60/60 [==============================] - 2s 41ms/step - loss: 0.1031 - accuracy: 0.5254 - val_loss: 0.2085 - val_accuracy: 0.5000
Epoch 21/100
60/60 [==============================] - 2s 42ms/step - loss: 0.0375 - accuracy: 0.5124 - val_loss: 0.0564 - val_accuracy: 0.5000
Epoch 22/100
60/60 [==============================] - 2s 41ms/step - loss: 0.0298 - accuracy: 0.5482 - val_loss: 0.5937 - val_accuracy: 0.5000
Epoch 23/100
60/60 [==============================] - 2s 41ms/step - loss: 0.3126 - accuracy: 0.3884 - val_loss: 0.0527 - val_accuracy: 0.5000
Epoch 24/100
60/60 [==============================] - 2s 41ms/step - loss: 0.1054 - accuracy: 0.5572 - val_loss: 0.0356 - val_accuracy: 0.5000
Epoch 25/100
60/60 [==============================] - 3s 42ms/step - loss: 0.1067 - accuracy: 0.4170 - val_loss: 0.1262 - val_accuracy: 0.5000
Epoch 26/100
60/60 [==============================] - 2s 40ms/step - loss: 0.0551 - accuracy: 0.5608 - val_loss: 0.0255 - val_accuracy: 0.5000
Epoch 27/100
60/60 [==============================] - 2s 41ms/step - loss: 0.0188 - accuracy: 0.5816 - val_loss: 0.3153 - val_accuracy: 0.5000
Epoch 28/100
60/60 [==============================] - 2s 40ms/step - loss: 0.1106 - accuracy: 0.4583 - val_loss: 0.3419 - val_accuracy: 0.5000
Epoch 29/100
60/60 [==============================] - 2s 40ms/step - loss: 0.1493 - accuracy: 0.5334 - val_loss: 0.0351 - val_accuracy: 0.5000
Epoch 30/100
60/60 [==============================] - 2s 41ms/step - loss: 0.1099 - accuracy: 0.4537 - val_loss: 0.1217 - val_accuracy: 0.5000
Epoch 31/100
60/60 [==============================] - 3s 43ms/step - loss: 0.0893 - accuracy: 0.4828 - val_loss: 0.1276 - val_accuracy: 0.5000
Epoch 32/100
60/60 [==============================] - 3s 43ms/step - loss: 0.1806 - accuracy: 0.4265 - val_loss: 0.0157 - val_accuracy: 0.5000
Epoch 33/100
60/60 [==============================] - 3s 44ms/step - loss: 0.0154 - accuracy: 0.3411 - val_loss: 0.0152 - val_accuracy: 0.5000
Epoch 34/100
60/60 [==============================] - 3s 42ms/step - loss: 0.0088 - accuracy: 0.4385 - val_loss: 0.0075 - val_accuracy: 0.5000
Epoch 35/100
60/60 [==============================] - 2s 41ms/step - loss: 0.0068 - accuracy: 0.5450 - val_loss: 0.0045 - val_accuracy: 0.5000
Epoch 36/100
60/60 [==============================] - 2s 41ms/step - loss: 0.0051 - accuracy: 0.4283 - val_loss: 0.0039 - val_accuracy: 0.5000
Epoch 37/100
60/60 [==============================] - 2s 40ms/step - loss: 0.0026 - accuracy: 0.3970 - val_loss: 0.0035 - val_accuracy: 0.5000
Epoch 38/100
60/60 [==============================] - 2s 41ms/step - loss: 0.0037 - accuracy: 0.4758 - val_loss: 0.0030 - val_accuracy: 0.5000
Epoch 39/100
60/60 [==============================] - 2s 41ms/step - loss: 0.0021 - accuracy: 0.5036 - val_loss: 0.0025 - val_accuracy: 0.5000
Epoch 40/100
60/60 [==============================] - 2s 41ms/step - loss: 0.0028 - accuracy: 0.6088 - val_loss: 0.0022 - val_accuracy: 0.5000
Epoch 41/100
60/60 [==============================] - 2s 40ms/step - loss: 0.0023 - accuracy: 0.3521 - val_loss: 0.0020 - val_accuracy: 0.5000
Epoch 42/100
60/60 [==============================] - 2s 39ms/step - loss: 0.0023 - accuracy: 0.4832 - val_loss: 0.0020 - val_accuracy: 0.5000
Epoch 43/100
60/60 [==============================] - 2s 39ms/step - loss: 0.0019 - accuracy: 0.6031 - val_loss: 0.0019 - val_accuracy: 0.5000
Epoch 44/100
60/60 [==============================] - 2s 39ms/step - loss: 0.0014 - accuracy: 0.4757 - val_loss: 0.0017 - val_accuracy: 0.5000
Epoch 45/100
60/60 [==============================] - 2s 39ms/step - loss: 0.0012 - accuracy: 0.5074 - val_loss: 0.0016 - val_accuracy: 0.5000
Epoch 46/100
60/60 [==============================] - 2s 39ms/step - loss: 0.0019 - accuracy: 0.4907 - val_loss: 0.0014 - val_accuracy: 0.5000
Epoch 47/100
60/60 [==============================] - 2s 39ms/step - loss: 0.0013 - accuracy: 0.5113 - val_loss: 0.0013 - val_accuracy: 0.5000
Epoch 48/100
60/60 [==============================] - 2s 42ms/step - loss: 0.0013 - accuracy: 0.4616 - val_loss: 0.0012 - val_accuracy: 0.5000
Epoch 49/100
60/60 [==============================] - 3s 43ms/step - loss: 9.2667e-04 - accuracy: 0.4932 - val_loss: 0.0012 - val_accuracy: 0.5000
Epoch 50/100
60/60 [==============================] - 2s 40ms/step - loss: 0.0012 - accuracy: 0.5685 - val_loss: 0.0011 - val_accuracy: 0.5000
Epoch 51/100
60/60 [==============================] - 2s 41ms/step - loss: 0.0014 - accuracy: 0.4952 - val_loss: 0.0011 - val_accuracy: 0.5000
Epoch 52/100
60/60 [==============================] - 3s 44ms/step - loss: 9.6710e-04 - accuracy: 0.4953 - val_loss: 0.0010 - val_accuracy: 0.5000
Epoch 53/100
60/60 [==============================] - 2s 40ms/step - loss: 0.0013 - accuracy: 0.5196 - val_loss: 9.4684e-04 - val_accuracy: 0.5000
Epoch 54/100
60/60 [==============================] - 2s 39ms/step - loss: 0.0012 - accuracy: 0.6033 - val_loss: 9.0767e-04 - val_accuracy: 0.5000
Epoch 55/100
60/60 [==============================] - 2s 39ms/step - loss: 0.0011 - accuracy: 0.5339 - val_loss: 8.7093e-04 - val_accuracy: 0.5000
Epoch 56/100
60/60 [==============================] - 2s 40ms/step - loss: 7.3141e-04 - accuracy: 0.4408 - val_loss: 8.4973e-04 - val_accuracy: 0.5000
Epoch 57/100
60/60 [==============================] - 2s 40ms/step - loss: 5.9006e-04 - accuracy: 0.5258 - val_loss: 8.1935e-04 - val_accuracy: 0.5000
Epoch 58/100
60/60 [==============================] - 3s 43ms/step - loss: 7.8818e-04 - accuracy: 0.5216 - val_loss: 7.8448e-04 - val_accuracy: 0.5000
Epoch 59/100
60/60 [==============================] - 3s 42ms/step - loss: 9.2272e-04 - accuracy: 0.4472 - val_loss: 7.5098e-04 - val_accuracy: 0.5000
Epoch 60/100
60/60 [==============================] - 3s 42ms/step - loss: 0.0011 - accuracy: 0.5485 - val_loss: 7.2444e-04 - val_accuracy: 0.5000
Epoch 61/100
60/60 [==============================] - 2s 41ms/step - loss: 5.5459e-04 - accuracy: 0.4393 - val_loss: 7.1711e-04 - val_accuracy: 0.5000
Epoch 62/100
60/60 [==============================] - 3s 43ms/step - loss: 7.3943e-04 - accuracy: 0.6748 - val_loss: 7.0446e-04 - val_accuracy: 0.5000
Epoch 63/100
60/60 [==============================] - 2s 41ms/step - loss: 6.0513e-04 - accuracy: 0.4365 - val_loss: 6.5710e-04 - val_accuracy: 0.5000
Epoch 64/100
60/60 [==============================] - 3s 43ms/step - loss: 7.1400e-04 - accuracy: 0.5855 - val_loss: 6.3535e-04 - val_accuracy: 0.5000
Epoch 65/100
60/60 [==============================] - 2s 40ms/step - loss: 4.1557e-04 - accuracy: 0.4226 - val_loss: 6.1638e-04 - val_accuracy: 0.5000
Epoch 66/100
60/60 [==============================] - 2s 39ms/step - loss: 0.0010 - accuracy: 0.5130 - val_loss: 5.9961e-04 - val_accuracy: 0.5000
Epoch 67/100
60/60 [==============================] - 2s 40ms/step - loss: 4.2256e-04 - accuracy: 0.5745 - val_loss: 5.8452e-04 - val_accuracy: 0.5000
Epoch 68/100
60/60 [==============================] - 3s 44ms/step - loss: 4.6930e-04 - accuracy: 0.4256 - val_loss: 5.6929e-04 - val_accuracy: 0.5000
Epoch 69/100
60/60 [==============================] - 3s 43ms/step - loss: 5.0537e-04 - accuracy: 0.5201 - val_loss: 5.5308e-04 - val_accuracy: 0.5000
Epoch 70/100
60/60 [==============================] - 2s 40ms/step - loss: 4.2207e-04 - accuracy: 0.5162 - val_loss: 5.3811e-04 - val_accuracy: 0.5000
Epoch 71/100
60/60 [==============================] - 3s 42ms/step - loss: 4.2835e-04 - accuracy: 0.5187 - val_loss: 5.2421e-04 - val_accuracy: 0.5000
Epoch 72/100
60/60 [==============================] - 2s 41ms/step - loss: 6.9296e-04 - accuracy: 0.5396 - val_loss: 5.1115e-04 - val_accuracy: 0.5000
Epoch 73/100
60/60 [==============================] - 2s 42ms/step - loss: 6.4352e-04 - accuracy: 0.4772 - val_loss: 4.9949e-04 - val_accuracy: 0.5000
Epoch 74/100
60/60 [==============================] - 2s 41ms/step - loss: 4.0728e-04 - accuracy: 0.4406 - val_loss: 4.8785e-04 - val_accuracy: 0.5000
Epoch 75/100
60/60 [==============================] - 2s 41ms/step - loss: 6.5099e-04 - accuracy: 0.4769 - val_loss: 4.7489e-04 - val_accuracy: 0.5000
Epoch 76/100
60/60 [==============================] - 2s 40ms/step - loss: 5.3847e-04 - accuracy: 0.5610 - val_loss: 4.6401e-04 - val_accuracy: 0.5000
Epoch 77/100
60/60 [==============================] - 3s 43ms/step - loss: 3.2081e-04 - accuracy: 0.5025 - val_loss: 4.5471e-04 - val_accuracy: 0.5000
Epoch 78/100
60/60 [==============================] - 2s 41ms/step - loss: 4.1042e-04 - accuracy: 0.4055 - val_loss: 4.4509e-04 - val_accuracy: 0.5000
Epoch 79/100
60/60 [==============================] - 3s 46ms/step - loss: 4.0072e-04 - accuracy: 0.5982 - val_loss: 4.3807e-04 - val_accuracy: 0.5000
Epoch 80/100
60/60 [==============================] - 2s 40ms/step - loss: 3.6314e-04 - accuracy: 0.4305 - val_loss: 4.2492e-04 - val_accuracy: 0.5000
Epoch 81/100
60/60 [==============================] - 3s 42ms/step - loss: 4.9497e-04 - accuracy: 0.4644 - val_loss: 4.2099e-04 - val_accuracy: 0.5000
Epoch 82/100
60/60 [==============================] - 3s 42ms/step - loss: 4.3963e-04 - accuracy: 0.4163 - val_loss: 4.0970e-04 - val_accuracy: 0.5000
Epoch 83/100
60/60 [==============================] - 3s 42ms/step - loss: 2.3065e-04 - accuracy: 0.5292 - val_loss: 4.0007e-04 - val_accuracy: 0.5000
Epoch 84/100
60/60 [==============================] - 2s 40ms/step - loss: 3.6344e-04 - accuracy: 0.4781 - val_loss: 3.9164e-04 - val_accuracy: 0.5000
Epoch 85/100
60/60 [==============================] - 2s 41ms/step - loss: 3.2347e-04 - accuracy: 0.4355 - val_loss: 3.8515e-04 - val_accuracy: 0.5000
I am getting weird model summary using keras and ImageDataGenerator when used with Cats and dogs classification.
I am using Google Colab+GPU.
The problem is model summary seems to throw weird values and looks like loss function is not working.
Kindly suggest what is the problem.
My code is as below
train_datagen=ImageDataGenerator(rescale=1./255)
test_datagen=ImageDataGenerator(rescale=1./255)
train_generator=train_datagen.flow_from_directory(
train_dir,
target_size=(150,150),
batch_size=32,
class_mode='binary')
validation_generator=train_datagen.flow_from_directory(validation_dir,target_size=
(150,150),batch_size=50,class_mode='binary')
history=model.fit(train_generator,steps_per_epoch=31,epochs=20,validation_data=validation_generator,validation_steps=20)
Model Summary is as below
Epoch 1/20
31/31 [==============================] - 10s 241ms/step - loss: 0.1302 - acc: 1.0000 -
val_loss: 5.0506 - val_acc: 0.5000
Epoch 2/20
31/31 [==============================] - 6s 215ms/step - loss: 4.4286e-05 - acc: 1.0000 -
val_loss: 6.8281 - val_acc: 0.5000
Epoch 3/20
31/31 [==============================] - 7s 212ms/step - loss: 4.6900e-06 - acc: 1.0000 -
val_loss: 8.1907 - val_acc: 0.5000
Epoch 4/20
31/31 [==============================] - 6s 211ms/step - loss: 5.8646e-07 - acc: 1.0000 -
val_loss: 9.3841 - val_acc: 0.5000
Epoch 5/20
31/31 [==============================] - 6s 212ms/step - loss: 2.0634e-07 - acc: 1.0000 -
val_loss: 10.3554 - val_acc: 0.5000
Epoch 6/20
31/31 [==============================] - 6s 211ms/step - loss: 2.8432e-08 - acc: 1.0000 -
val_loss: 11.3546 - val_acc: 0.5000
Epoch 7/20
31/31 [==============================] - 6s 211ms/step - loss: 1.3657e-08 - acc: 1.0000 -
val_loss: 12.1012 - val_acc: 0.5000
Epoch 8/20
31/31 [==============================] - 7s 215ms/step - loss: 4.8156e-09 - acc: 1.0000 -
val_loss: 12.6892 - val_acc: 0.5000
Epoch 9/20
31/31 [==============================] - 7s 219ms/step - loss: 2.9152e-09 - acc: 1.0000 -
val_loss: 13.1079 - val_acc: 0.5000
Epoch 10/20
31/31 [==============================] - 7s 216ms/step - loss: 1.6705e-09 - acc: 1.0000 -
val_loss: 13.4230 - val_acc: 0.5000
Epoch 11/20
31/31 [==============================] - 7s 218ms/step - loss: 1.2603e-09 - acc: 1.0000 -
val_loss: 13.6259 - val_acc: 0.5000
Epoch 12/20
31/31 [==============================] - 7s 218ms/step - loss: 1.7701e-09 - acc: 1.0000 - val_loss:
13.7718 - val_acc: 0.5000
Epoch 13/20
31/31 [==============================] - 7s 218ms/step - loss: 1.6043e-09 - acc: 1.0000 - val_loss:
13.9099 - val_acc: 0.5000
Epoch 14/20
31/31 [==============================] - 7s 219ms/step - loss: 3.8831e-10 - acc: 1.0000 -
val_loss: 14.0405 - val_acc: 0.5000
Epoch 15/20
31/31 [==============================] - 7s 216ms/step - loss: 8.9113e-10 - acc: 1.0000 - val_loss:
14.1567 - val_acc: 0.5000
Epoch 16/20
31/31 [==============================] - 7s 218ms/step - loss: 8.5343e-10 - acc: 1.0000 -
val_loss: 14.2485 - val_acc: 0.5000
Epoch 17/20
31/31 [==============================] - 7s 217ms/step - loss: 2.8638e-10 - acc: 1.0000 -
val_loss: 14.3410 - val_acc: 0.5000
Epoch 18/20
31/31 [==============================] - 7s 218ms/step - loss: 5.3467e-10 - acc: 1.0000
- val_loss: 14.4225 - val_acc: 0.5000
Epoch 19/20
31/31 [==============================] - 7s 217ms/step - loss: 4.5269e-10 - acc: 1.0000
- val_loss: 14.4895 - val_acc: 0.5000
Epoch 20/20
31/31 [==============================] - 7s 216ms/step - loss: 3.4228e-10 - acc:
1.0000 - val_loss: 14.5428 - val_acc: 0.5000
You should use model.summary() instead of history = model.fit...
The Binarycrossentropy loss function does not converges.
It stagnates at 0.6933 = Binarycrossentropy(1.0,0.5) = Binarycrossentropy(0.0,0.5).
The net takes 8 images of size 224x224x3 representig a 3d object as input with batch_size = 16.
At least I would expect getting the net overfitting, but converge.
I hope someone has a hint for me.
Thank you.
nets, inputs=[], []
base_ResNet50 = ResNet50(weights='imagenet', include_top= False, input_shape=(image_size,image_size,channels))
for layer in base_ResNet50.layers:
layer.trainable = False
inputs = Input(shape=(views,image_size,image_size,channels))
pre_images = preprocess_input(inputs)
for x in tf.split(pre_images,num_or_size_splits=views, axis=1):
x = tf.reshape(x,[-1,image_size,image_size,channels])
x = base_model(x)
x = Flatten()(x)
nets.append(x)
out = tf.math.reduce_max(nets, [0])
out = Dense(100)(out)
out = Activation('relu')(out)
out = Dense(10)(out)
out = Activation('relu')(out)
out = layers.Dropout(0.5)(out)
out = Dense(1)(out)
out = Activation('sigmoid')(out)
model = Model(inputs=inputs, outputs=out)
optimizer=tf.keras.optimizers.Adam(lr=0.1)
model.compile(loss='binary_crossentropy', optimizer=optimizer,
metrics=['accuracy'])
```Epoch 1/50
592/592 [==============================] - 691s 1s/step - loss: 36731256.0000 - accuracy: 0.4958 - val_loss: 0.6938 - val_accuracy: 0.4933
Epoch 2/50
592/592 [==============================] - 724s 1s/step - loss: 0.6937 - accuracy: 0.5042 - val_loss: 0.6931 - val_accuracy: 0.5067
Epoch 3/50
592/592 [==============================] - 670s 1s/step - loss: 0.6936 - accuracy: 0.4789 - val_loss: 0.6931 - val_accuracy: 0.5067
Epoch 4/50
592/592 [==============================] - 673s 1s/step - loss: 0.6934 - accuracy: 0.4941 - val_loss: 0.6931 - val_accuracy: 0.5067
Epoch 5/50
592/592 [==============================] - 670s 1s/step - loss: 0.6934 - accuracy: 0.4823 - val_loss: 0.6931 - val_accuracy: 0.5067
Epoch 6/50
592/592 [==============================] - 666s 1s/step - loss: 0.6933 - accuracy: 0.4738 - val_loss: 0.6931 - val_accuracy: 0.5067
Epoch 7/50
592/592 [==============================] - 664s 1s/step - loss: 0.6933 - accuracy: 0.4941 - val_loss: 0.6932 - val_accuracy: 0.4933
Epoch 8/50
592/592 [==============================] - 673s 1s/step - loss: 0.6932 - accuracy: 0.4924 - val_loss: 0.6932 - val_accuracy: 0.4933
Epoch 9/50
592/592 [==============================] - 670s 1s/step - loss: 0.6932 - accuracy: 0.4941 - val_loss: 0.6932 - val_accuracy: 0.4933```
I am evaluating different CNN classifiers that have different parameters (i.e. learning rate, number of filters and dropouts).
I have sucessfully plot the accuracy of each model individually for both training and validation dataset over 100 epochs using the below code
history=classifier.fit_generator(training_set,
steps_per_epoch = nb_training_samples// batchsize,
epochs = 100,
validation_data =test_set,
validation_steps = nb_testing_samples // batchsize)
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.title('Model Accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
However, I am trying to have a single plot that compares the validation dataset accuracy throught 100 epochs from different classifiers that have different parameters. Is it feasible?
Yes, it is feasible to do so. These plots are also required when you are doing the hyper parameter tuning of learning rate, filter size, dropout, epoch etc.
In fact we can choose different combinations of Learning rate, kernel, dropout, epoch and other hyperparameters in a model and plot the validation accuracy of these combinations to choose the best.
Also we can do a grid search on the model to select best set of parameters. You can find more about Grid Search Hyperparameters for Deep Learning Models in Python With Keras here.
Here I have added two simple programs along with Validation Accuracy plots -
Model having Learning rate with increase of 0.01 over iterations.
Model with different optimizers.
Program 1: Model having Learning rate with increase of 0.01 over iterations.
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.optimizers import Adam
import os
import numpy as np
import matplotlib.pyplot as plt
_URL = 'https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip'
path_to_zip = tf.keras.utils.get_file('cats_and_dogs.zip', origin=_URL, extract=True)
PATH = os.path.join(os.path.dirname(path_to_zip), 'cats_and_dogs_filtered')
train_dir = os.path.join(PATH, 'train')
validation_dir = os.path.join(PATH, 'validation')
train_cats_dir = os.path.join(train_dir, 'cats') # directory with our training cat pictures
train_dogs_dir = os.path.join(train_dir, 'dogs') # directory with our training dog pictures
validation_cats_dir = os.path.join(validation_dir, 'cats') # directory with our validation cat pictures
validation_dogs_dir = os.path.join(validation_dir, 'dogs') # directory with our validation dog pictures
batch_size = 128
epochs = 15
IMG_HEIGHT = 150
IMG_WIDTH = 150
train_image_generator = ImageDataGenerator(rescale=1./255) # Generator for our training data
validation_image_generator = ImageDataGenerator(rescale=1./255) # Generator for our validation data
train_data_gen = train_image_generator.flow_from_directory(batch_size=batch_size,
directory=train_dir,
shuffle=True,
target_size=(IMG_HEIGHT, IMG_WIDTH),
class_mode='binary')
val_data_gen = validation_image_generator.flow_from_directory(batch_size=batch_size,
directory=validation_dir,
target_size=(IMG_HEIGHT, IMG_WIDTH),
class_mode='binary')
model = Sequential([
Conv2D(16, 3, padding='same', activation='relu', input_shape=(IMG_HEIGHT, IMG_WIDTH ,3)),
MaxPooling2D(),
Conv2D(32, 3, padding='same', activation='relu'),
MaxPooling2D(),
Conv2D(64, 3, padding='same', activation='relu'),
MaxPooling2D(),
Flatten(),
Dense(512, activation='relu'),
Dense(1)
])
lr=0.01
for i in range(5):
adam = Adam(lr)
print("Model using learning rate of",lr)
lr = lr + 0.01
model.compile(optimizer=adam,
loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
metrics=['accuracy'])
history = model.fit_generator(
train_data_gen,
steps_per_epoch=total_train // batch_size,
epochs=epochs,
validation_data=val_data_gen,
validation_steps=total_val // batch_size)
plt.plot(history.history['val_accuracy'])
plt.title('Model Accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['LR=0.01', 'LR=0.02', 'LR=0.03', 'LR=0.04', 'LR=0.05'], loc='upper left')
plt.show()
Output -
Found 2000 images belonging to 2 classes.
Found 1000 images belonging to 2 classes.
Model using learning rate of 0.01
Epoch 1/15
15/15 [==============================] - 8s 546ms/step - loss: 7.3135 - accuracy: 0.5073 - val_loss: 0.6920 - val_accuracy: 0.4989
Epoch 2/15
15/15 [==============================] - 8s 545ms/step - loss: 0.6929 - accuracy: 0.4968 - val_loss: 0.6931 - val_accuracy: 0.5000
Epoch 3/15
15/15 [==============================] - 8s 533ms/step - loss: 0.6932 - accuracy: 0.5016 - val_loss: 0.6932 - val_accuracy: 0.5134
Epoch 4/15
15/15 [==============================] - 8s 539ms/step - loss: 0.6932 - accuracy: 0.5080 - val_loss: 0.6930 - val_accuracy: 0.5100
Epoch 5/15
15/15 [==============================] - 8s 534ms/step - loss: 0.6934 - accuracy: 0.4893 - val_loss: 0.6932 - val_accuracy: 0.4978
Epoch 6/15
15/15 [==============================] - 8s 532ms/step - loss: 0.6932 - accuracy: 0.5000 - val_loss: 0.6931 - val_accuracy: 0.4944
Epoch 7/15
15/15 [==============================] - 8s 535ms/step - loss: 0.6932 - accuracy: 0.4995 - val_loss: 0.6931 - val_accuracy: 0.4955
Epoch 8/15
15/15 [==============================] - 8s 540ms/step - loss: 0.6934 - accuracy: 0.5101 - val_loss: 0.6932 - val_accuracy: 0.5022
Epoch 9/15
15/15 [==============================] - 8s 535ms/step - loss: 0.6935 - accuracy: 0.4850 - val_loss: 0.6931 - val_accuracy: 0.5033
Epoch 10/15
15/15 [==============================] - 8s 533ms/step - loss: 0.6932 - accuracy: 0.5021 - val_loss: 0.6931 - val_accuracy: 0.5022
Epoch 11/15
15/15 [==============================] - 8s 536ms/step - loss: 0.6932 - accuracy: 0.5053 - val_loss: 0.6932 - val_accuracy: 0.4877
Epoch 12/15
15/15 [==============================] - 8s 538ms/step - loss: 0.6932 - accuracy: 0.5032 - val_loss: 0.6932 - val_accuracy: 0.4967
Epoch 13/15
15/15 [==============================] - 8s 532ms/step - loss: 0.6932 - accuracy: 0.4973 - val_loss: 0.6932 - val_accuracy: 0.4911
Epoch 14/15
15/15 [==============================] - 8s 532ms/step - loss: 0.6932 - accuracy: 0.4995 - val_loss: 0.6933 - val_accuracy: 0.5089
Epoch 15/15
15/15 [==============================] - 8s 532ms/step - loss: 0.6932 - accuracy: 0.4979 - val_loss: 0.6931 - val_accuracy: 0.4877
Model using learning rate of 0.02
Epoch 1/15
15/15 [==============================] - 8s 538ms/step - loss: 0.6935 - accuracy: 0.5011 - val_loss: 0.6932 - val_accuracy: 0.4933
Epoch 2/15
15/15 [==============================] - 8s 524ms/step - loss: 0.6938 - accuracy: 0.5000 - val_loss: 0.6934 - val_accuracy: 0.5000
Epoch 3/15
15/15 [==============================] - 8s 533ms/step - loss: 0.6931 - accuracy: 0.5005 - val_loss: 0.6932 - val_accuracy: 0.5022
Epoch 4/15
15/15 [==============================] - 8s 538ms/step - loss: 0.6936 - accuracy: 0.4984 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 5/15
15/15 [==============================] - 8s 532ms/step - loss: 0.6931 - accuracy: 0.4984 - val_loss: 0.6930 - val_accuracy: 0.4900
Epoch 6/15
15/15 [==============================] - 8s 523ms/step - loss: 0.6934 - accuracy: 0.5096 - val_loss: 0.6934 - val_accuracy: 0.4933
Epoch 7/15
15/15 [==============================] - 8s 534ms/step - loss: 0.6933 - accuracy: 0.5043 - val_loss: 0.6931 - val_accuracy: 0.5033
Epoch 8/15
15/15 [==============================] - 8s 536ms/step - loss: 0.6936 - accuracy: 0.4850 - val_loss: 0.6937 - val_accuracy: 0.5022
Epoch 9/15
15/15 [==============================] - 8s 528ms/step - loss: 0.6935 - accuracy: 0.5048 - val_loss: 0.6932 - val_accuracy: 0.5011
Epoch 10/15
15/15 [==============================] - 8s 529ms/step - loss: 0.6933 - accuracy: 0.4952 - val_loss: 0.6931 - val_accuracy: 0.4967
Epoch 11/15
15/15 [==============================] - 8s 532ms/step - loss: 0.6934 - accuracy: 0.5048 - val_loss: 0.6931 - val_accuracy: 0.4989
Epoch 12/15
15/15 [==============================] - 8s 537ms/step - loss: 0.6933 - accuracy: 0.4989 - val_loss: 0.6932 - val_accuracy: 0.5056
Epoch 13/15
15/15 [==============================] - 8s 529ms/step - loss: 0.6933 - accuracy: 0.5016 - val_loss: 0.6931 - val_accuracy: 0.5089
Epoch 14/15
15/15 [==============================] - 8s 533ms/step - loss: 0.6935 - accuracy: 0.4995 - val_loss: 0.6932 - val_accuracy: 0.4989
Epoch 15/15
15/15 [==============================] - 8s 529ms/step - loss: 0.6931 - accuracy: 0.4920 - val_loss: 0.6932 - val_accuracy: 0.5000
Model using learning rate of 0.03
Epoch 1/15
15/15 [==============================] - 8s 534ms/step - loss: 0.6935 - accuracy: 0.5150 - val_loss: 0.6939 - val_accuracy: 0.4978
Epoch 2/15
15/15 [==============================] - 8s 538ms/step - loss: 0.6948 - accuracy: 0.4904 - val_loss: 0.6932 - val_accuracy: 0.5011
Epoch 3/15
15/15 [==============================] - 8s 531ms/step - loss: 0.6935 - accuracy: 0.5043 - val_loss: 0.6934 - val_accuracy: 0.5067
Epoch 4/15
15/15 [==============================] - 8s 521ms/step - loss: 0.6934 - accuracy: 0.4963 - val_loss: 0.6932 - val_accuracy: 0.5011
Epoch 5/15
15/15 [==============================] - 8s 528ms/step - loss: 0.6938 - accuracy: 0.5010 - val_loss: 0.6932 - val_accuracy: 0.5011
Epoch 6/15
15/15 [==============================] - 8s 536ms/step - loss: 0.6933 - accuracy: 0.5021 - val_loss: 0.6932 - val_accuracy: 0.5011
Epoch 7/15
15/15 [==============================] - 8s 532ms/step - loss: 0.6933 - accuracy: 0.5005 - val_loss: 0.6932 - val_accuracy: 0.5100
Epoch 8/15
15/15 [==============================] - 8s 536ms/step - loss: 0.6933 - accuracy: 0.4963 - val_loss: 0.6933 - val_accuracy: 0.5022
Epoch 9/15
15/15 [==============================] - 8s 529ms/step - loss: 0.6932 - accuracy: 0.5016 - val_loss: 0.6931 - val_accuracy: 0.5067
Epoch 10/15
15/15 [==============================] - 8s 553ms/step - loss: 0.6935 - accuracy: 0.4947 - val_loss: 0.6937 - val_accuracy: 0.5089
Epoch 11/15
15/15 [==============================] - 8s 540ms/step - loss: 0.6936 - accuracy: 0.5021 - val_loss: 0.6930 - val_accuracy: 0.5123
Epoch 12/15
15/15 [==============================] - 8s 535ms/step - loss: 0.6934 - accuracy: 0.4979 - val_loss: 0.6932 - val_accuracy: 0.5011
Epoch 13/15
15/15 [==============================] - 8s 530ms/step - loss: 0.6933 - accuracy: 0.5011 - val_loss: 0.6932 - val_accuracy: 0.4989
Epoch 14/15
15/15 [==============================] - 8s 540ms/step - loss: 0.6932 - accuracy: 0.5027 - val_loss: 0.6933 - val_accuracy: 0.4944
Epoch 15/15
15/15 [==============================] - 8s 537ms/step - loss: 0.6934 - accuracy: 0.4989 - val_loss: 0.6931 - val_accuracy: 0.4922
Model using learning rate of 0.04
Epoch 1/15
15/15 [==============================] - 8s 549ms/step - loss: 0.6935 - accuracy: 0.5134 - val_loss: 0.6942 - val_accuracy: 0.5000
Epoch 2/15
15/15 [==============================] - 8s 547ms/step - loss: 0.6948 - accuracy: 0.4840 - val_loss: 0.6931 - val_accuracy: 0.4933
Epoch 3/15
15/15 [==============================] - 8s 543ms/step - loss: 0.6934 - accuracy: 0.4979 - val_loss: 0.6933 - val_accuracy: 0.4989
Epoch 4/15
15/15 [==============================] - 8s 534ms/step - loss: 0.6934 - accuracy: 0.5027 - val_loss: 0.6932 - val_accuracy: 0.5000
Epoch 5/15
15/15 [==============================] - 8s 537ms/step - loss: 0.6935 - accuracy: 0.5027 - val_loss: 0.6932 - val_accuracy: 0.4978
Epoch 6/15
15/15 [==============================] - 8s 540ms/step - loss: 0.6937 - accuracy: 0.4984 - val_loss: 0.6934 - val_accuracy: 0.5045
Epoch 7/15
15/15 [==============================] - 8s 535ms/step - loss: 0.6932 - accuracy: 0.4979 - val_loss: 0.6931 - val_accuracy: 0.4877
Epoch 8/15
15/15 [==============================] - 8s 545ms/step - loss: 0.6936 - accuracy: 0.4963 - val_loss: 0.6931 - val_accuracy: 0.5033
Epoch 9/15
15/15 [==============================] - 8s 532ms/step - loss: 0.6931 - accuracy: 0.4984 - val_loss: 0.6932 - val_accuracy: 0.4978
Epoch 10/15
15/15 [==============================] - 8s 527ms/step - loss: 0.6936 - accuracy: 0.5069 - val_loss: 0.6932 - val_accuracy: 0.4933
Epoch 11/15
15/15 [==============================] - 8s 531ms/step - loss: 0.6934 - accuracy: 0.5069 - val_loss: 0.6931 - val_accuracy: 0.5022
Epoch 12/15
15/15 [==============================] - 8s 528ms/step - loss: 0.6936 - accuracy: 0.4866 - val_loss: 0.6939 - val_accuracy: 0.5022
Epoch 13/15
15/15 [==============================] - 8s 533ms/step - loss: 0.6938 - accuracy: 0.5150 - val_loss: 0.6939 - val_accuracy: 0.5000
Epoch 14/15
15/15 [==============================] - 8s 536ms/step - loss: 0.6939 - accuracy: 0.4915 - val_loss: 0.6933 - val_accuracy: 0.5011
Epoch 15/15
15/15 [==============================] - 8s 541ms/step - loss: 0.6933 - accuracy: 0.4989 - val_loss: 0.6932 - val_accuracy: 0.5011
Model using learning rate of 0.05
Epoch 1/15
15/15 [==============================] - 8s 551ms/step - loss: 0.6935 - accuracy: 0.5134 - val_loss: 0.6958 - val_accuracy: 0.4955
Epoch 2/15
15/15 [==============================] - 8s 548ms/step - loss: 0.6955 - accuracy: 0.4973 - val_loss: 0.6933 - val_accuracy: 0.5078
Epoch 3/15
15/15 [==============================] - 8s 545ms/step - loss: 0.6931 - accuracy: 0.4909 - val_loss: 0.6931 - val_accuracy: 0.4944
Epoch 4/15
15/15 [==============================] - 8s 538ms/step - loss: 0.6935 - accuracy: 0.4989 - val_loss: 0.6931 - val_accuracy: 0.5045
Epoch 5/15
15/15 [==============================] - 8s 527ms/step - loss: 0.6934 - accuracy: 0.4936 - val_loss: 0.6932 - val_accuracy: 0.5011
Epoch 6/15
15/15 [==============================] - 8s 531ms/step - loss: 0.6933 - accuracy: 0.5176 - val_loss: 0.6935 - val_accuracy: 0.5045
Epoch 7/15
15/15 [==============================] - 8s 556ms/step - loss: 0.6938 - accuracy: 0.4920 - val_loss: 0.6934 - val_accuracy: 0.5000
Epoch 8/15
15/15 [==============================] - 8s 533ms/step - loss: 0.6940 - accuracy: 0.4995 - val_loss: 0.6933 - val_accuracy: 0.5033
Epoch 9/15
15/15 [==============================] - 8s 537ms/step - loss: 0.6933 - accuracy: 0.5036 - val_loss: 0.6934 - val_accuracy: 0.4933
Epoch 10/15
15/15 [==============================] - 9s 573ms/step - loss: 0.6942 - accuracy: 0.4952 - val_loss: 0.6933 - val_accuracy: 0.4944
Epoch 11/15
15/15 [==============================] - 8s 540ms/step - loss: 0.6942 - accuracy: 0.4957 - val_loss: 0.6934 - val_accuracy: 0.5000
Epoch 12/15
15/15 [==============================] - 8s 536ms/step - loss: 0.6930 - accuracy: 0.5166 - val_loss: 0.6935 - val_accuracy: 0.4978
Epoch 13/15
15/15 [==============================] - 8s 543ms/step - loss: 0.6940 - accuracy: 0.4952 - val_loss: 0.6932 - val_accuracy: 0.5022
Epoch 14/15
15/15 [==============================] - 8s 558ms/step - loss: 0.6932 - accuracy: 0.4845 - val_loss: 0.6933 - val_accuracy: 0.4978
Epoch 15/15
15/15 [==============================] - 8s 546ms/step - loss: 0.6940 - accuracy: 0.5139 - val_loss: 0.6937 - val_accuracy: 0.5033
Validation Accuracy Plot -
Program 2: Model with different optimizers.
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.optimizers import Adam
import os
import numpy as np
import matplotlib.pyplot as plt
_URL = 'https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip'
path_to_zip = tf.keras.utils.get_file('cats_and_dogs.zip', origin=_URL, extract=True)
PATH = os.path.join(os.path.dirname(path_to_zip), 'cats_and_dogs_filtered')
train_dir = os.path.join(PATH, 'train')
validation_dir = os.path.join(PATH, 'validation')
train_cats_dir = os.path.join(train_dir, 'cats') # directory with our training cat pictures
train_dogs_dir = os.path.join(train_dir, 'dogs') # directory with our training dog pictures
validation_cats_dir = os.path.join(validation_dir, 'cats') # directory with our validation cat pictures
validation_dogs_dir = os.path.join(validation_dir, 'dogs') # directory with our validation dog pictures
batch_size = 128
epochs = 15
IMG_HEIGHT = 150
IMG_WIDTH = 150
train_image_generator = ImageDataGenerator(rescale=1./255) # Generator for our training data
validation_image_generator = ImageDataGenerator(rescale=1./255) # Generator for our validation data
train_data_gen = train_image_generator.flow_from_directory(batch_size=batch_size,
directory=train_dir,
shuffle=True,
target_size=(IMG_HEIGHT, IMG_WIDTH),
class_mode='binary')
val_data_gen = validation_image_generator.flow_from_directory(batch_size=batch_size,
directory=validation_dir,
target_size=(IMG_HEIGHT, IMG_WIDTH),
class_mode='binary')
model = Sequential([
Conv2D(16, 3, padding='same', activation='relu', input_shape=(IMG_HEIGHT, IMG_WIDTH ,3)),
MaxPooling2D(),
Conv2D(32, 3, padding='same', activation='relu'),
MaxPooling2D(),
Conv2D(64, 3, padding='same', activation='relu'),
MaxPooling2D(),
Flatten(),
Dense(512, activation='relu'),
Dense(1)
])
optimizer = ['SGD', 'RMSprop', 'Adagrad', 'Adadelta', 'Adam', 'Adamax', 'Nadam']
for i in range(7):
print("Model using",optimizer[i],"optimizer")
model.compile(optimizer=optimizer[i],
loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
metrics=['accuracy'])
history = model.fit_generator(
train_data_gen,
steps_per_epoch=total_train // batch_size,
epochs=epochs,
validation_data=val_data_gen,
validation_steps=total_val // batch_size)
plt.plot(history.history['val_accuracy'])
plt.title('Validation Accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['SGD', 'RMSprop', 'Adagrad', 'Adadelta', 'Adam', 'Adamax', 'Nadam'], loc='upper left')
plt.show()
Output -
Found 2000 images belonging to 2 classes.
Found 1000 images belonging to 2 classes.
Model using SGD optimizer
Epoch 1/15
15/15 [==============================] - 8s 550ms/step - loss: 0.6923 - accuracy: 0.5026 - val_loss: 0.6909 - val_accuracy: 0.5033
Epoch 2/15
15/15 [==============================] - 8s 551ms/step - loss: 0.6898 - accuracy: 0.4989 - val_loss: 0.6900 - val_accuracy: 0.5045
Epoch 3/15
15/15 [==============================] - 8s 539ms/step - loss: 0.6893 - accuracy: 0.5005 - val_loss: 0.6889 - val_accuracy: 0.5022
Epoch 4/15
15/15 [==============================] - 8s 546ms/step - loss: 0.6875 - accuracy: 0.4989 - val_loss: 0.6880 - val_accuracy: 0.5056
Epoch 5/15
15/15 [==============================] - 8s 536ms/step - loss: 0.6860 - accuracy: 0.4882 - val_loss: 0.6864 - val_accuracy: 0.4944
Epoch 6/15
15/15 [==============================] - 8s 538ms/step - loss: 0.6868 - accuracy: 0.5048 - val_loss: 0.6846 - val_accuracy: 0.4877
Epoch 7/15
15/15 [==============================] - 8s 536ms/step - loss: 0.6857 - accuracy: 0.5032 - val_loss: 0.6837 - val_accuracy: 0.4866
Epoch 8/15
15/15 [==============================] - 8s 538ms/step - loss: 0.6830 - accuracy: 0.5016 - val_loss: 0.6832 - val_accuracy: 0.4955
Epoch 9/15
15/15 [==============================] - 8s 547ms/step - loss: 0.6819 - accuracy: 0.5107 - val_loss: 0.6816 - val_accuracy: 0.5022
Epoch 10/15
15/15 [==============================] - 8s 543ms/step - loss: 0.6804 - accuracy: 0.4882 - val_loss: 0.6805 - val_accuracy: 0.5033
Epoch 11/15
15/15 [==============================] - 8s 541ms/step - loss: 0.6798 - accuracy: 0.5037 - val_loss: 0.6800 - val_accuracy: 0.4955
Epoch 12/15
15/15 [==============================] - 8s 541ms/step - loss: 0.6796 - accuracy: 0.4941 - val_loss: 0.6791 - val_accuracy: 0.5022
Epoch 13/15
15/15 [==============================] - 8s 536ms/step - loss: 0.6763 - accuracy: 0.5118 - val_loss: 0.6782 - val_accuracy: 0.5056
Epoch 14/15
15/15 [==============================] - 8s 546ms/step - loss: 0.6758 - accuracy: 0.5048 - val_loss: 0.6743 - val_accuracy: 0.4944
Epoch 15/15
15/15 [==============================] - 8s 539ms/step - loss: 0.6715 - accuracy: 0.5064 - val_loss: 0.6767 - val_accuracy: 0.5000
Model using RMSprop optimizer
Epoch 1/15
15/15 [==============================] - 8s 544ms/step - loss: 2.3455 - accuracy: 0.4963 - val_loss: 0.6690 - val_accuracy: 0.4944
Epoch 2/15
15/15 [==============================] - 8s 545ms/step - loss: 0.6912 - accuracy: 0.5358 - val_loss: 0.6596 - val_accuracy: 0.5123
Epoch 3/15
15/15 [==============================] - 8s 545ms/step - loss: 0.6488 - accuracy: 0.5953 - val_loss: 0.6589 - val_accuracy: 0.5234
Epoch 4/15
15/15 [==============================] - 8s 555ms/step - loss: 0.6675 - accuracy: 0.5962 - val_loss: 0.6412 - val_accuracy: 0.5714
Epoch 5/15
15/15 [==============================] - 8s 540ms/step - loss: 0.6165 - accuracy: 0.6330 - val_loss: 0.6365 - val_accuracy: 0.6920
Epoch 6/15
15/15 [==============================] - 8s 542ms/step - loss: 0.6762 - accuracy: 0.6512 - val_loss: 0.6145 - val_accuracy: 0.6440
Epoch 7/15
15/15 [==============================] - 8s 541ms/step - loss: 0.5711 - accuracy: 0.6854 - val_loss: 0.5771 - val_accuracy: 0.6641
Epoch 8/15
15/15 [==============================] - 8s 549ms/step - loss: 0.7130 - accuracy: 0.6571 - val_loss: 0.6068 - val_accuracy: 0.6975
Epoch 9/15
15/15 [==============================] - 8s 550ms/step - loss: 0.4837 - accuracy: 0.7719 - val_loss: 0.5689 - val_accuracy: 0.7042
Epoch 10/15
15/15 [==============================] - 8s 548ms/step - loss: 0.5215 - accuracy: 0.7345 - val_loss: 0.8108 - val_accuracy: 0.6685
Epoch 11/15
15/15 [==============================] - 8s 539ms/step - loss: 0.4842 - accuracy: 0.7548 - val_loss: 0.5851 - val_accuracy: 0.6629
Epoch 12/15
15/15 [==============================] - 8s 540ms/step - loss: 0.4333 - accuracy: 0.7821 - val_loss: 0.5866 - val_accuracy: 0.7065
Epoch 13/15
15/15 [==============================] - 8s 541ms/step - loss: 0.4136 - accuracy: 0.8061 - val_loss: 0.6037 - val_accuracy: 0.7232
Epoch 14/15
15/15 [==============================] - 8s 544ms/step - loss: 0.3493 - accuracy: 0.8456 - val_loss: 0.8027 - val_accuracy: 0.5737
Epoch 15/15
15/15 [==============================] - 8s 541ms/step - loss: 0.3735 - accuracy: 0.8210 - val_loss: 0.6215 - val_accuracy: 0.6317
Model using Adagrad optimizer
Epoch 1/15
15/15 [==============================] - 8s 543ms/step - loss: 0.2212 - accuracy: 0.9017 - val_loss: 0.6342 - val_accuracy: 0.7199
Epoch 2/15
15/15 [==============================] - 8s 534ms/step - loss: 0.1544 - accuracy: 0.9482 - val_loss: 0.6781 - val_accuracy: 0.7087
Epoch 3/15
15/15 [==============================] - 8s 545ms/step - loss: 0.1409 - accuracy: 0.9498 - val_loss: 0.6718 - val_accuracy: 0.7188
Epoch 4/15
15/15 [==============================] - 8s 543ms/step - loss: 0.1133 - accuracy: 0.9610 - val_loss: 0.7026 - val_accuracy: 0.7288
Epoch 5/15
15/15 [==============================] - 8s 551ms/step - loss: 0.1023 - accuracy: 0.9698 - val_loss: 0.6959 - val_accuracy: 0.7243
Epoch 6/15
15/15 [==============================] - 8s 551ms/step - loss: 0.0906 - accuracy: 0.9744 - val_loss: 0.7243 - val_accuracy: 0.7299
Epoch 7/15
15/15 [==============================] - 8s 542ms/step - loss: 0.0821 - accuracy: 0.9813 - val_loss: 0.6867 - val_accuracy: 0.7400
Epoch 8/15
15/15 [==============================] - 8s 534ms/step - loss: 0.0751 - accuracy: 0.9808 - val_loss: 0.7433 - val_accuracy: 0.7388
Epoch 9/15
15/15 [==============================] - 8s 533ms/step - loss: 0.0683 - accuracy: 0.9813 - val_loss: 0.7392 - val_accuracy: 0.7467
Epoch 10/15
15/15 [==============================] - 8s 537ms/step - loss: 0.0584 - accuracy: 0.9877 - val_loss: 0.7992 - val_accuracy: 0.7366
Epoch 11/15
15/15 [==============================] - 8s 535ms/step - loss: 0.0581 - accuracy: 0.9888 - val_loss: 0.8050 - val_accuracy: 0.7355
Epoch 12/15
15/15 [==============================] - 8s 536ms/step - loss: 0.0534 - accuracy: 0.9899 - val_loss: 0.8280 - val_accuracy: 0.7299
Epoch 13/15
15/15 [==============================] - 8s 536ms/step - loss: 0.0455 - accuracy: 0.9920 - val_loss: 0.8068 - val_accuracy: 0.7254
Epoch 14/15
15/15 [==============================] - 8s 540ms/step - loss: 0.0483 - accuracy: 0.9893 - val_loss: 0.8482 - val_accuracy: 0.7411
Epoch 15/15
15/15 [==============================] - 8s 535ms/step - loss: 0.0394 - accuracy: 0.9952 - val_loss: 0.8483 - val_accuracy: 0.7444
Model using Adadelta optimizer
Epoch 1/15
15/15 [==============================] - 8s 541ms/step - loss: 0.0360 - accuracy: 0.9968 - val_loss: 0.8339 - val_accuracy: 0.7500
Epoch 2/15
15/15 [==============================] - 8s 536ms/step - loss: 0.0376 - accuracy: 0.9941 - val_loss: 0.8663 - val_accuracy: 0.7411
Epoch 3/15
15/15 [==============================] - 8s 537ms/step - loss: 0.0380 - accuracy: 0.9947 - val_loss: 0.8333 - val_accuracy: 0.7433
Epoch 4/15
15/15 [==============================] - 8s 536ms/step - loss: 0.0332 - accuracy: 0.9968 - val_loss: 0.8508 - val_accuracy: 0.7455
Epoch 5/15
15/15 [==============================] - 8s 535ms/step - loss: 0.0357 - accuracy: 0.9952 - val_loss: 0.8521 - val_accuracy: 0.7444
Epoch 6/15
15/15 [==============================] - 8s 535ms/step - loss: 0.0364 - accuracy: 0.9952 - val_loss: 0.8440 - val_accuracy: 0.7433
Epoch 7/15
15/15 [==============================] - 8s 539ms/step - loss: 0.0362 - accuracy: 0.9953 - val_loss: 0.8540 - val_accuracy: 0.7388
Epoch 8/15
15/15 [==============================] - 8s 549ms/step - loss: 0.0344 - accuracy: 0.9957 - val_loss: 0.8276 - val_accuracy: 0.7500
Epoch 9/15
15/15 [==============================] - 8s 534ms/step - loss: 0.0364 - accuracy: 0.9952 - val_loss: 0.8934 - val_accuracy: 0.7355
Epoch 10/15
15/15 [==============================] - 8s 542ms/step - loss: 0.0372 - accuracy: 0.9947 - val_loss: 0.8400 - val_accuracy: 0.7422
Epoch 11/15
15/15 [==============================] - 8s 538ms/step - loss: 0.0336 - accuracy: 0.9963 - val_loss: 0.8363 - val_accuracy: 0.7500
Epoch 12/15
15/15 [==============================] - 8s 538ms/step - loss: 0.0361 - accuracy: 0.9952 - val_loss: 0.8305 - val_accuracy: 0.7533
Epoch 13/15
15/15 [==============================] - 8s 534ms/step - loss: 0.0341 - accuracy: 0.9963 - val_loss: 0.8525 - val_accuracy: 0.7433
...
Model using Adam optimizer
Epoch 1/15
15/15 [==============================] - 8s 552ms/step - loss: 0.3095 - accuracy: 0.8985 - val_loss: 0.6640 - val_accuracy: 0.7065
...
Model using Adamax optimizer
Epoch 1/15
15/15 [==============================] - 8s 540ms/step - loss: 0.0850 - accuracy: 0.9760 - val_loss: 1.1438 - val_accuracy: 0.7254
....
Model using Nadam optimizer
Epoch 1/15
15/15 [==============================] - 8s 544ms/step - loss: 0.2377 - accuracy: 0.9546 - val_loss: 1.0978 - val_accuracy: 0.6987
....
Validation Accuracy Plot -
I Have created a model to classify plane and cars images bu after very epoch the acc and val_acc remains same
import numpy as np
import matplotlib as plt
from keras.models import Sequential
from keras.layers import Convolution2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
from keras.preprocessing.image import ImageDataGenerator
from keras.preprocessing.image import image
import os
model=Sequential()
model.add(Convolution2D(32,(3,3),input_shape=(64,64,3),activation="relu"))
model.add(MaxPooling2D(2,2))
model.add(Convolution2D(64,(3,3),activation="relu"))
model.add(MaxPooling2D(2,2))
model.add(Convolution2D(64,(3,3),activation="sigmoid"))
model.add(MaxPooling2D(2,2))
model.add(Flatten())
model.add(Dense(32,activation="sigmoid"))
model.add(Dense(32,activation="sigmoid"))
model.add(Dense(32,activation="sigmoid"))
model.add(Dense(1,activation="softmax"))
model.compile(optimizer='adam', loss='binary_crossentropy',
metrics=['accuracy'])
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1./255)
train_set = train_datagen.flow_from_directory(
'train_images',
target_size=(64,64),
batch_size=32,
class_mode='binary')
test_set = train_datagen.flow_from_directory(
'val_set',
target_size=(64,64),
batch_size=32,
class_mode='binary')
model.fit_generator(
train_set,
steps_per_epoch=160,
epochs=25,
validation_data=test_set,
validation_steps=40)
Epoch 1/25
30/30 [==============================] - 18s 593ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 2/25
30/30 [==============================] - 15s 491ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 3/25
30/30 [==============================] - 19s 640ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 4/25
30/30 [==============================] - 14s 474ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 5/25
30/30 [==============================] - 16s 532ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 6/25
30/30 [==============================] - 14s 473ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 7/25
30/30 [==============================] - 14s 469ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 8/25
30/30 [==============================] - 14s 469ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 9/25
30/30 [==============================] - 14s 472ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 10/25
30/30 [==============================] - 16s 537ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 11/25
30/30 [==============================] - 18s 590ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 12/25
30/30 [==============================] - 13s 441ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 13/25
30/30 [==============================] - 11s 374ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 14/25
30/30 [==============================] - 11s 370ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 15/25
30/30 [==============================] - 13s 441ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 16/25
30/30 [==============================] - 13s 419ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 17/25
30/30 [==============================] - 12s 401ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 18/25
30/30 [==============================] - 16s 536ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 19/25
30/30 [==============================] - 16s 523ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 20/25
30/30 [==============================] - 16s 530ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 21/25
30/30 [==============================] - 16s 546ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 22/25
30/30 [==============================] - 15s 500ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 23/25
30/30 [==============================] - 16s 546ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 24/25
30/30 [==============================] - 16s 545ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
Epoch 25/25
30/30 [==============================] - 15s 515ms/step - loss: 7.9712 - acc: 0.5000 - val_loss:
7.9712 - val_acc: 0.5000
You have several issues in your model structure.
First of all, for the output of your model
model.add(Dense(1,activation="softmax"))
You are using a softmax, which means you try to solve a multi-class classification, not a binary classification. If it is really the case, you need to change your loss to categorical_crossentropy. In this way the compile line will turn into:
model.compile(optimizer='adam', loss='categorical_crossentropy',
metrics=['accuracy'])
If it is not the case and you want only solve a binary classification, you might be good, but I do suggest to change the last layer activation to sigmoid
Second: That is a bad idea to use sigmoid as the activation in the middle layer since it can easily cause the gradient to vanish (read more here ). Try to change all the sigmoid activation in the middle layer with wether relu or even better with leakyrelu
The problem is exactly here:
model.add(Dense(1,activation="softmax"))
You cannot use softmax with one neuron, as it normalizes over neurons, meaning that with one neuron it will always produce a constant 1.0 value. For binary classification you have to use sigmoid activation at the output:
model.add(Dense(1,activation="sigmoid"))
Also it is not wise to use sigmoid activations in hidden layers, as they will produce vanishing gradient problems. Please prefer ReLU or similar activations.