About epochs and images in Machine learning

Question

I have image 186 images in train_images and 174 images in valid_images when I pass to CNN model It only train 6 images. I did not create any batch size. The dataset name is Lego minifigure.

 '''
    print(train_images.shape)
    print(type(train_images))
    print(valid_images.shape)
    print(type(valid_images))
    print(train_targets.shape)
    print(valid_targets.shape)
    print(type(train_targets))
    print(type(valid_targets))
    '''
    output is 
    
    (186, 20, 20, 3)
    <class 'numpy.ndarray'>
    (174, 20, 20, 3)
    <class 'numpy.ndarray'>
    (186, 33)
    (174, 33)
    <class 'numpy.ndarray'>
    <class 'numpy.ndarray'>
    '''
    model
    model=tf.keras.Sequential()
    model.add(tf.keras.layers.Conv2D(20,(3,3),activation='relu',input_shape=(20,20,3)))
    model.add(tf.keras.layers.MaxPooling2D(2,2))
    model.add(tf.keras.layers.Flatten())
    model.add(tf.keras.layers.Dense(100,activation='relu'))
    model.add(tf.keras.layers.Dense(33,activation='softmax'))
    model.compile(loss='categorical_crossentropy',metrics=['accuracy'],optimizer='adam')
    model.summary()
    '''
    
    Model: "sequential_3"
    _________________________________________________________________
    Layer (type)                 Output Shape              Param #   
    =================================================================
    conv2d_3 (Conv2D)            (None, 18, 18, 20)        560       
    _________________________________________________________________
    max_pooling2d_3 (MaxPooling2 (None, 9, 9, 20)          0         
    _________________________________________________________________
    flatten_3 (Flatten)          (None, 1620)              0         
    _________________________________________________________________
    dense_4 (Dense)              (None, 100)               162100    
    _________________________________________________________________
    dense_5 (Dense)              (None, 33)                3333      
    =================================================================
    Total params: 165,993
    Trainable params: 165,993
    Non-trainable params: 0
    ___________________________
    '''
    hist=model.fit(train_images,train_targets,epochs=100,validation_data=(valid_images,valid_targets))
    
    '''
    Epoch 1/100
    6/6 [==============================] - 0s 10ms/step - loss: 2.7642 - accuracy: 0.4355 - val_loss: 3.1673 - val_accuracy: 0.1839

why it is training only 6 images? I am beginner in Ml ,so if someone helps it would be great help!

most likely its not 6 images, but 6 batches of images. – Marcin Nov 01 '20 at 15:18 — Marcin, Nov 01 '20 at 15:18

score 0 · Answer 1 · answered Nov 01 '20 at 14:58

0

batch_size equals to 32 on default

answered Nov 01 '20 at 14:58

Andrey

5,932
3
17
35

then it should take 32 images and it is taking only 6 images Why? – feefi feefe Nov 01 '20 at 18:35
6 is epoch number. 186 / 32 = 6 – Andrey Nov 01 '20 at 18:41
your explanation in comment should contribute to "rich quality answer" tag. Now its 1/r.q.a. by bots. – ZF007 Nov 01 '20 at 22:23

About epochs and images in Machine learning

1 Answers1