# Notes

Earlier when you trained for extra epochs you had an issue where your loss might change. It might have taken a bit of time for you to wait for the training to do that, and you might have thought 'wouldn't it be nice if I could stop the training when I reach a desired value?' -- i.e. 95% accuracy might be enough for you, and if you reach that after 3 epochs, why sit around waiting for it to finish a lot more epochs....So how would you fix that? Like any other program...you have callbacks! Let's see them in action...

```python
import tensorflow as tf
print(tf.__version__)

class myCallback(tf.keras.callbacks.Callback):
  def on_epoch_end(self, epoch, logs={}):
    if(logs.get('loss')<0.4):
      print("\nReached 60% accuracy so cancelling training!")
      self.model.stop_training = True

callbacks = myCallback()

mnist = tf.keras.datasets.fashion_mnist
(train_images, training_labels), (test_images, test_labels) = mnist.load_data()

train_images=train_images/255.0
test_images=test_images/255.0

model = tf.keras.models.Sequential([
  tf.keras.layers.Flatten(),
  tf.keras.layers.Dense(512, activation=tf.nn.relu),
  tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy')
model.fit(train_images, training_labels, epochs=5, callbacks=[callbacks])

```

```
1.13.1
Epoch 1/5
60000/60000 [==============================] - 19s 316us/sample - loss: 0.4767
Epoch 2/5
59872/60000 [============================>.] - ETA: 0s - loss: 0.3590
Reached 60% accuracy so cancelling training!
60000/60000 [==============================] - 17s 279us/sample - loss: 0.3588
<tensorflow.python.keras.callbacks.History at 0x7faf5dc59110>
```

### convolutional 2d layer

{% embed url="<https://bit.ly/2UGa7uH>" %}

{% embed url="<https://lodev.org/cgtutor/filtering.html>" %}

{% embed url="<https://gombru.github.io/2018/05/23/cross_entropy_loss/>" %}

{% embed url="<http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf>" %}

\----

<https://stackoverflow.com/questions/54854797/valueerror-validation-data-should-be-a-tuple-val-x-val-y-val-sample-weigh/56490365#56490365>

```
import keras

class Generator(keras.utils.Sequence):
    def __init__(self, data_file):
        self.data_file = data_file
        self.length = -1

    def __iter__(self):
        while True:
            with open(self.data_file, 'r') as f:
                reader = csv.reader(f)
                for row in reader:
                    yield row[0], row[1]

    def __len__(self):
        if self.length ==  -1:
            n_rows = 0
            with open(self.data_file, 'r') as f:
                reader = csv.reader(f)
                for row in reader:
                    n_rows += 1
            self.length = n_rows
        return self.length
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://stephanosterburg.gitbook.io/scrapbook/coding/intro-to-tensorflow-for-ai-ml-and-dl/notes.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.