CODEWITHSUNDEEP
pythonmachine-learningkerasneural-networkdeep-learning
Jacob
Jacob

Reputation: 23

Loss not decrasing and is very high keras

I'm learning deep learning in keras and I have a problem. The loss isn't decreasing and it's very high, about 650.

I'm working on MNIST dataset from tensorflow.keras.datasets.mnist There is no error, just my NN isn't learning.

There is my model:

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten
import tensorflow.nn as tfnn

inputdim = 28 * 28

model = Sequential()

model.add(Flatten())
model.add(Dense(inputdim, activation = tfnn.relu))
model.add(Dense(128, activation = tfnn.relu))
model.add(Dense(10, activation = tfnn.softmax))

model.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
model.fit(X_train, Y_train, epochs = 4)

and my output:

Epoch 1/4
60000/60000 [==============================] - 32s 527us/sample - loss: 646.0926 - acc: 6.6667e-05
Epoch 2/4
60000/60000 [==============================] - 39s 652us/sample - loss: 646.1003 - acc: 0.0000e+00 - l - ETA: 0s - loss: 646.0983 - acc: 0.0000e
Epoch 3/4
60000/60000 [==============================] - 35s 590us/sample - loss: 646.1003 - acc: 0.0000e+00
Epoch 4/4
60000/60000 [==============================] - 33s 544us/sample - loss: 646.1003 - acc: 0.0000e+00
```

Upvotes: 0

Views: 785

Answers (2)

Jacob
Jacob

Reputation: 23

Ok, I added BatchNormalization between lines and changed loss function to 'sparse_categorical_crossentropy'. That's how my NN looks like:

model = Sequential()

model.add(Flatten())
model.add(BatchNormalization(axis = 1, momentum = 0.99))
model.add(Dense(inputdim, activation = tfnn.relu))
model.add(BatchNormalization(axis = 1, momentum = 0.99))
model.add(Dense(128, activation = tfnn.relu))
model.add(BatchNormalization(axis = 1, momentum = 0.99))
model.add(Dense(10, activation = tfnn.softmax))

model.compile(loss = 'sparse_categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])

and thats a results:

Epoch 1/4
60000/60000 [==============================] - 68s 1ms/sample - loss: 0.2045 - acc: 0.9374
Epoch 2/4
60000/60000 [==============================] - 55s 916us/sample - loss: 0.1007 - acc: 0.9689

Thanks for your help!

Upvotes: 1

Amit
Amit

Reputation: 2098

You may try sparse_categorical_crossentropy loss function. Also what is your batch size? and as has already been suggested you may want to increase number of epochs.

Upvotes: 0

Related Questions