Why my loss function or accuracy does not improve? - keras

I have 3D CNN U-net architecture to solve segmentation problem. I am using Adam optimisation together with binary cross entropy and the metric is "accuracy". I try to understand why it does not improve.
Train on 2774 samples, validate on 694 samples
Epoch 1/20
2774/2774 [==============================] - 166s 60ms/step - loss: 0.5189 - acc: 0.7928 - val_loss: 0.5456 - val_acc: 0.7674
Epoch 00001: val_loss improved from inf to 0.54555, saving model to model-tgs-salt-1.h5
Epoch 2/20
2774/2774 [==============================] - 170s 61ms/step - loss: 0.5170 - acc: 0.7928 - val_loss: 0.5485 - val_acc: 0.7674
Epoch 00002: val_loss did not improve from 0.54555
Epoch 3/20
2774/2774 [==============================] - 169s 61ms/step - loss: 0.5119 - acc: 0.7928 - val_loss: 0.5455 - val_acc: 0.7674
Epoch 00003: val_loss improved from 0.54555 to 0.54549, saving model to model-tgs-salt-1.h5
Epoch 4/20
2774/2774 [==============================] - 170s 61ms/step - loss: 0.5117 - acc: 0.7928 - val_loss: 0.5715 - val_acc: 0.7674
Epoch 00004: val_loss did not improve from 0.54549
Epoch 5/20
2774/2774 [==============================] - 169s 61ms/step - loss: 0.5126 - acc: 0.7928 - val_loss: 0.5566 - val_acc: 0.7674
Epoch 00005: val_loss did not improve from 0.54549
Epoch 6/20
2774/2774 [==============================] - 169s 61ms/step - loss: 0.5138 - acc: 0.7928 - val_loss: 0.5503 - val_acc: 0.7674
Epoch 00006: val_loss did not improve from 0.54549
Epoch 7/20
2774/2774 [==============================] - 170s 61ms/step - loss: 0.5103 - acc: 0.7928 - val_loss: 0.5444 - val_acc: 0.7674
Epoch 00007: val_loss improved from 0.54549 to 0.54436, saving model to model-tgs-salt-1.h5
Epoch 8/20
2774/2774 [==============================] - 169s 61ms/step - loss: 0.5137 - acc: 0.7928 - val_loss: 0.5454 - val_acc: 0.7674

If you use batch size in your network. let's try to increase that. I think it could be useful in speed of train.

Related

Validation Accuracy doesnt improve at all from the beggining

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?

Weird Model Summary

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...

Accuracy remains constant after every epoch

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.

Predicting the price of the natural gas using LSTM neural network

I want to build a model using Keras to predict the price of the natural gas.
The dataset contains the price for the gas daily and monthly since 1997 and it is available Here.
The following graph shows the prices during a sequence of days. X is days and Y is the price.
I have tried LSTM with 4,50,100 cell in hidden layer but the accuracy still not was bad and the model failed to predict future price.
I have added another two hidden layers (full connected) with 100 and 128 cell but it did not work too.
This is the model and the result form training process:
num_units = 100
activation_function = 'sigmoid'
optimizer = 'adam'
loss_function = 'mean_squared_error'
batch_size = 5
num_epochs = 10
log_file_name = f"{SEQ_LEN}-SEQ-{1}-PRED-{int(time.time())}"
# Initialize the model (of a Sequential type)
model = Sequential()
# Adding the input layer and the LSTM layer
model.add(LSTM(units = num_units, activation = activation_function,input_shape=(None, 1)))
# Adding the output layer
model.add(Dense(units = 1))
# Compiling the RNN
model.compile(optimizer = optimizer, loss = loss_function, metrics=['accuracy'])
# Using the training set to train the model
history = model.fit(train_x, train_y, batch_size = batch_size, epochs =num_epochs,validation_data=(test_x, test_y))
and the output is :
Train on 4362 samples, validate on 1082 samples
Epoch 1/10
4362/4362 [==============================] - 11s 3ms/step - loss: 0.0057 - acc: 2.2925e-04 - val_loss: 0.0016 - val_acc: 0.0018
Epoch 2/10
4362/4362 [==============================] - 9s 2ms/step - loss: 6.2463e-04 - acc: 4.5851e-04 - val_loss: 0.0013 - val_acc: 0.0018
Epoch 3/10
4362/4362 [==============================] - 9s 2ms/step - loss: 6.1073e-04 - acc: 2.2925e-04 - val_loss: 0.0014 - val_acc: 0.0018
Epoch 4/10
4362/4362 [==============================] - 8s 2ms/step - loss: 5.4403e-04 - acc: 4.5851e-04 - val_loss: 0.0014 - val_acc: 0.0018
Epoch 5/10
4362/4362 [==============================] - 7s 2ms/step - loss: 5.4765e-04 - acc: 4.5851e-04 - val_loss: 0.0012 - val_acc: 0.0018
Epoch 6/10
4362/4362 [==============================] - 8s 2ms/step - loss: 5.1991e-04 - acc: 4.5851e-04 - val_loss: 0.0013 - val_acc: 0.0018
Epoch 7/10
4362/4362 [==============================] - 7s 2ms/step - loss: 5.7324e-04 - acc: 2.2925e-04 - val_loss: 0.0011 - val_acc: 0.0018
Epoch 8/10
4362/4362 [==============================] - 7s 2ms/step - loss: 4.4248e-04 - acc: 4.5851e-04 - val_loss: 0.0011 - val_acc: 0.0018
Epoch 9/10
4362/4362 [==============================] - 7s 2ms/step - loss: 4.3868e-04 - acc: 4.5851e-04 - val_loss: 0.0011 - val_acc: 0.0018
Epoch 10/10
4362/4362 [==============================] - 7s 2ms/step - loss: 4.6654e-04 - acc: 4.5851e-04 - val_loss: 0.0011 - val_acc: 0.0018
How to know the number of layers and cells for problem like this? Anyone can suggest a netwrok structure that can solve this problem?

Comparing results of model training in keras tensorflow backend

I trained 6000 images on two cnn networks and they appear to be giving me similar results. The model is trained for binary classification the diffrence between the two models is in the dense layers Model A has following dense layer config
fc1 (Dense) (None, 512) 12845568
_________________________________________________________________
fc2 (Dense) (None, 256) 131328
_________________________________________________________________
output (Dense) (None, 2) 514
and result
Train on 4800 samples, validate on 1200 samples
Epoch 1/30
4800/4800 [===] - 98s - loss: 0.7923 - acc: 0.6865 - val_loss: 0.4599 - val_acc: 0.7858
Epoch 2/30
4800/4800 [===] - 80s - loss: 0.4263 - acc: 0.7996 - val_loss: 0.5913 - val_acc: 0.6350
Epoch 3/30
4800/4800 [===] - 80s - loss: 0.3912 - acc: 0.8133 - val_loss: 0.3199 - val_acc: 0.8625
Epoch 4/30
4800/4800 [===] - 80s - loss: 0.3562 - acc: 0.8402 - val_loss: 0.3086 - val_acc: 0.8708
Epoch 5/30
4800/4800 [===] - 80s - loss: 0.3251 - acc: 0.8558 - val_loss: 0.2784 - val_acc: 0.8817
Epoch 6/30
4800/4800 [===] - 80s - loss: 0.3150 - acc: 0.8631 - val_loss: 0.2792 - val_acc: 0.8817
Epoch 7/30
4800/4800 [===] - 80s - loss: 0.2997 - acc: 0.8692 - val_loss: 0.3615 - val_acc: 0.8342
Epoch 8/30
4800/4800 [===] - 80s - loss: 0.2990 - acc: 0.8662 - val_loss: 0.2630 - val_acc: 0.8908
Epoch 9/30
4800/4800 [===] - 80s - loss: 0.2594 - acc: 0.8867 - val_loss: 0.3102 - val_acc: 0.8700
Epoch 10/30
4800/4800 [===] - 80s - loss: 0.2846 - acc: 0.8785 - val_loss: 0.4234 - val_acc: 0.7842
Epoch 11/30
4800/4800 [===] - 80s - loss: 0.2510 - acc: 0.8969 - val_loss: 0.2952 - val_acc: 0.8742
Epoch 12/30
4800/4800 [===] - 80s - loss: 0.2288 - acc: 0.9090 - val_loss: 0.2680 - val_acc: 0.8858
Epoch 13/30
4800/4800 [===] - 80s - loss: 0.2277 - acc: 0.9044 - val_loss: 0.3745 - val_acc: 0.8600
Epoch 14/30
4800/4800 [===] - 80s - loss: 0.2659 - acc: 0.8873 - val_loss: 0.2438 - val_acc: 0.9025
Epoch 15/30
4800/4800 [===] - 80s - loss: 0.2101 - acc: 0.9133 - val_loss: 0.3176 - val_acc: 0.8667
Epoch 16/30
4800/4800 [===] - 80s - loss: 0.2094 - acc: 0.9146 - val_loss: 0.2763 - val_acc: 0.8875
Epoch 17/30
4800/4800 [===] - 80s - loss: 0.2058 - acc: 0.9125 - val_loss: 0.2677 - val_acc: 0.8925
Epoch 18/30
4800/4800 [===] - 80s - loss: 0.1839 - acc: 0.9296 - val_loss: 0.2449 - val_acc: 0.9117
Epoch 19/30
4800/4800 [===] - 80s - loss: 0.1918 - acc: 0.9221 - val_loss: 0.2471 - val_acc: 0.8992
Epoch 20/30
4800/4800 [===] - 80s - loss: 0.2014 - acc: 0.9225 - val_loss: 0.2709 - val_acc: 0.8808
Epoch 21/30
4800/4800 [===] - 80s - loss: 0.1540 - acc: 0.9425 - val_loss: 0.2541 - val_acc: 0.8933
Epoch 22/30
4800/4800 [===] - 80s - loss: 0.1803 - acc: 0.9294 - val_loss: 0.2289 - val_acc: 0.9058
Epoch 23/30
4800/4800 [===] - 80s - loss: 0.1548 - acc: 0.9425 - val_loss: 0.2417 - val_acc: 0.9175
Epoch 24/30
4800/4800 [===] - 80s - loss: 0.1754 - acc: 0.9294 - val_loss: 0.4914 - val_acc: 0.8183
Epoch 25/30
4800/4800 [===] - 80s - loss: 0.1449 - acc: 0.9419 - val_loss: 0.2281 - val_acc: 0.9125
Epoch 26/30
4800/4800 [===] - 80s - loss: 0.1529 - acc: 0.9385 - val_loss: 0.2328 - val_acc: 0.9217
Epoch 27/30
4800/4800 [===] - 80s - loss: 0.1237 - acc: 0.9533 - val_loss: 0.2646 - val_acc: 0.9167
Epoch 28/30
4800/4800 [===] - 80s - loss: 0.1236 - acc: 0.9531 - val_loss: 0.2485 - val_acc: 0.9100
Epoch 29/30
4800/4800 [===] - 80s - loss: 0.1301 - acc: 0.9500 - val_loss: 0.2726 - val_acc: 0.9042
Epoch 30/30
4800/4800 [===] - 80s - loss: 0.1335 - acc: 0.9500 - val_loss: 0.2803 - val_acc: 0.9183
Training time: 2440.315860271454
1200/1200 [===] - 27s
[INFO] loss=0.2803, accuracy: 91.8333%
=================================================================
Model B has following final dense layer config
fc1 (Dense) (None, 1024) 25691136
_________________________________________________________________
fc2 (Dense) (None, 512) 524800
_________________________________________________________________
output (Dense) (None, 2) 1026
Result
Train on 4800 samples, validate on 1200 samples
Epoch 1/30
4800/4800 [===] - 87s - loss: 0.4743 - acc: 0.7708 - val_loss: 0.4073 - val_acc: 0.8233
Epoch 2/30
4800/4800 [===] - 87s - loss: 0.3732 - acc: 0.8263 - val_loss: 0.3359 - val_acc: 0.8525
Epoch 3/30
4800/4800 [===] - 87s - loss: 0.3383 - acc: 0.8500 - val_loss: 0.3017 - val_acc: 0.8658
Epoch 4/30
4800/4800 [===] - 87s - loss: 0.3094 - acc: 0.8637 - val_loss: 0.3024 - val_acc: 0.8683
Epoch 5/30
4800/4800 [===] - 87s - loss: 0.3036 - acc: 0.8669 - val_loss: 0.3848 - val_acc: 0.8058
Epoch 6/30
4800/4800 [===] - 87s - loss: 0.2848 - acc: 0.8802 - val_loss: 0.2730 - val_acc: 0.8883
Epoch 7/30
4800/4800 [===] - 87s - loss: 0.2630 - acc: 0.8877 - val_loss: 0.3234 - val_acc: 0.8667
Epoch 8/30
4800/4800 [===] - 87s - loss: 0.2491 - acc: 0.8952 - val_loss: 0.2758 - val_acc: 0.8933
Epoch 9/30
4800/4800 [===] - 87s - loss: 0.2484 - acc: 0.8992 - val_loss: 0.3271 - val_acc: 0.8467
Epoch 10/30
4800/4800 [===] - 87s - loss: 0.2427 - acc: 0.8992 - val_loss: 0.2743 - val_acc: 0.8808
Epoch 11/30
4800/4800 [===] - 87s - loss: 0.2346 - acc: 0.9017 - val_loss: 0.2379 - val_acc: 0.9008
Epoch 12/30
4800/4800 [===] - 87s - loss: 0.2250 - acc: 0.9108 - val_loss: 0.2432 - val_acc: 0.9017
Epoch 13/30
4800/4800 [===] - 87s - loss: 0.1993 - acc: 0.9221 - val_loss: 0.2892 - val_acc: 0.8858
Epoch 14/30
4800/4800 [===] - 87s - loss: 0.2148 - acc: 0.9125 - val_loss: 0.3201 - val_acc: 0.8842
Epoch 15/30
4800/4800 [===] - 87s - loss: 0.1823 - acc: 0.9287 - val_loss: 0.5481 - val_acc: 0.8133
Epoch 16/30
4800/4800 [===] - 87s - loss: 0.1873 - acc: 0.9281 - val_loss: 0.2449 - val_acc: 0.9092
Epoch 17/30
4800/4800 [===] - 87s - loss: 0.1622 - acc: 0.9392 - val_loss: 0.2373 - val_acc: 0.9092
Epoch 18/30
4800/4800 [===] - 87s - loss: 0.1782 - acc: 0.9304 - val_loss: 0.2856 - val_acc: 0.8725
Epoch 19/30
4800/4800 [===] - 87s - loss: 0.1632 - acc: 0.9369 - val_loss: 0.2518 - val_acc: 0.9067
Epoch 20/30
4800/4800 [===] - 87s - loss: 0.1577 - acc: 0.9381 - val_loss: 0.2629 - val_acc: 0.9050
Epoch 21/30
4800/4800 [===] - 87s - loss: 0.1395 - acc: 0.9481 - val_loss: 0.2278 - val_acc: 0.9133
Epoch 22/30
4800/4800 [===] - 87s - loss: 0.1422 - acc: 0.9444 - val_loss: 0.2232 - val_acc: 0.9158
Epoch 23/30
4800/4800 [===] - 87s - loss: 0.1436 - acc: 0.9448 - val_loss: 0.2862 - val_acc: 0.9042
Epoch 24/30
4800/4800 [===] - 87s - loss: 0.1402 - acc: 0.9448 - val_loss: 0.3186 - val_acc: 0.8842
Epoch 25/30
4800/4800 [===] - 86s - loss: 0.1261 - acc: 0.9542 - val_loss: 0.2762 - val_acc: 0.9092
Epoch 26/30
4800/4800 [===] - 86s - loss: 0.1143 - acc: 0.9529 - val_loss: 0.2442 - val_acc: 0.9125
Epoch 27/30
4800/4800 [===] - 86s - loss: 0.1141 - acc: 0.9565 - val_loss: 0.3128 - val_acc: 0.8658
Epoch 28/30
4800/4800 [===] - 86s - loss: 0.1092 - acc: 0.9606 - val_loss: 0.2669 - val_acc: 0.9092
Epoch 29/30
4800/4800 [===] - 86s - loss: 0.0939 - acc: 0.9642 - val_loss: 0.2535 - val_acc: 0.8975
Epoch 30/30
4800/4800 [===] - 86s - loss: 0.1098 - acc: 0.9615 - val_loss: 0.2594 - val_acc: 0.9008
Training time: 2615.465226173401
1200/1200 [==============================] - 30s
[INFO] loss=0.2594, accuracy: 90.0833%
both models seem to give similar results.Is this a good result or is there any anomalies that I cant detect? Or is the model a good one?
Additional info Batch size 128,loss=categorical cross-entropy,optimizer-adadelta
Any suggestions for improvent is also appriciated
The next steps I would consider are:
What is happening to your training loss. This is can be a useful metric. If you see your training loss go to 100% try adding more regularization, such as L2 regularization.
Is your convolutional network using residual layers and batch normalization? Those residual networks using batch norm seem to be state of the art in most cases right now.
Test different numbers of filters in each convolutional layer. If you have too many filters you overfit if you have too few you underfit. There's a sweet spot in there and it makes a difference.
Your batch size can affect your results as well, play with it, I've done extensive hyperparameter searches on small vs. large datasets and come up with widely different ideal batch sizes
You might test the Adam optimizer. AdaDelta is solid as well though.
Train a number of models, random initialization will produce slightly different end results. Using an ensemble of models will do better still.
Randomly initializing with the Xavier Initializer may give you a small bump in accuracy (there's a different one for conv layers and fc layers).
Lower your learning rate after validation error plateaus, this typically improves performance some each time you lower it.
There are always many things you can try. Start running experiments, train a few models with various values of some of these suggestions and see where you get improvements.

Resources