Edited, memorised or added to reading queue

Do you want BuboFlash to help you learning these things? Click here to log in or create user.

Flashcard 7624073284876

Tags

#tensorflow #tensorflow-certificate

Question

from tensorflow.keras import Sequential
from tensorflow.keras.layers import [...]
import numpy as np

model = Sequential(Dense(1, input_shape=[1]))
model.compile(optimizer='sgd', loss='mean_squared_error')
xs = np.array([1,5,12,-1,10], dtype=float)
ys = np.array([5,13,27,1,23], dtype=float)
model.fit(xs, ys, epochs=500)
model.predict(x=[15])

Answer

Dense

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Tensorflow basics - typical flow of model building
from tensorflow.keras import Sequential from tensorflow.keras.layers import Dense import numpy as np model = Sequential(Dense(1, input_shape=[1])) model.compile(optimizer='sgd', loss='mean_squared_error') xs = np.array([1,5,12,-1,10], dtype=float) ys = np.array([5,13

Flashcard 7624089275660

Tags

#tensorflow #tensorflow-certificate

Question

import tensorflow as tf

#stop training after reaching accuract of 0.99
class MyCallback(tf.keras.callbacks.Callback):
  def on_epoch_end(self, epoch, logs={}):
    if logs.get('accuracy')>=0.99:
      print('\nAccuracy 0.99 achieved')
      self.model.[...] = True

Answer

stop_training

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Tensorflow - callbacks
r reaching accuract of 0.99 class MyCallback(tf.keras.callbacks.Callback): def on_epoch_end(self, epoch, logs={}): if logs.get('accuracy')>=0.99: print('\nAccuracy 0.99 achieved') self.model.<span>stop_training = True <span>

Flashcard 7625108229388

Tags

#tensorflow #tensorflow-certificate

Question

changeable_tensor = tf.Variable([10, 7])

changeable_tensor[0] = 77

Output:
TypeError: 'ResourceVariable' object does not support item assignment


changeable_tensor[0].assign(77)

Output:
<tf.Variable 'UnreadVariable' shape=([...]) dtype=int32, numpy=array([77,  7], dtype=int32)>

Answer

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Tensorflow basics
([10, 7]) changeable_tensor[0] = 77 Output: TypeError: 'ResourceVariable' object does not support item assignment changeable_tensor[0].assign(77) Output: <tf.Variable 'UnreadVariable' shape=(<span>2,) dtype=int32, numpy=array([77, 7], dtype=int32)> <span>

Flashcard 7625629371660

Tags

#tensorflow #tensorflow-certificate

Question

# Calculate MSE "by hand" in steps - identify functions

abs_err = tf.abs(tf.subtract([...](y_test, dtype=tf.float32), tf.squeeze(y_pred)))
sq_abs_err = tf.multiply(abs_err, abs_err)
sq_abs_err
tf.math.reduce_mean(sq_abs_err)



<tf.Tensor: shape=(), dtype=float32, numpy=155.11417>

Answer

tf.cast

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Calculate MSE "by hand" in steps - identify functions
# Calculate MSE "by hand" in steps - identify functions abs_err = tf.abs(tf.subtract(tf.cast(y_test, dtype=tf.float32), tf.squeeze(y_pred))) sq_abs_err = tf.multiply(abs_err, abs_err) sq_abs_err tf.math.reduce_mean(sq_abs_err) <tf.Tensor: shape=(), dtype=float32, numpy=155.1

Annotation 7625709063436

#deep-learning #keras #lstm #python #sequence

Integer Encoding

As a first step, each unique category value is assigned an integer value. For example, red is 1, green is 2, and blue is 3. This is called label encoding or an integer encoding and is easily reversible. For some variables, this may be enough. The integer values have a natural ordered relationship between each other and machine learning algorithms may be able to understand and harness this relationship. For example, ordinal variables like the place example above would be a good example where a label encoding would be sufficient

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

Parent (intermediate) annotation

Open it
3.2.1 How to Convert Categorical Data to Numerical Data This involves two steps: 1. Integer Encoding. 2. One Hot Encoding. Integer Encoding As a first step, each unique category value is assigned an integer value. For example, red is 1, green is 2, and blue is 3. This is called label encoding or an integer encoding and is easily reversible. For some variables, this may be enough. The integer values have a natural ordered relationship between each other and machine learning algorithms may be able to understand and harness this relationship. For example, ordinal variables like the place example above would be a good example where a label encoding would be sufficient

Original toplevel document (pdf)

cannot see any pdfs

Flashcard 7625711422732

Tags

#has-images #recurrent-neural-networks #rnn

[unknown IMAGE 7101511240972]

Question

The two calendar components – the month and week indicators – represent time-varying [...] information which is shared across the individuals within a given cohort. In addition, in this example, we include also an individual time-invariant covariate (gender) and a time-varying, individual-level covariate (marketing appeals)

Answer

contextual

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Parent (intermediate) annotation

Open it
The two calendar components – the month and week indicators – represent time-varying contextual information which is shared across the individuals within a given cohort. In addition, in this example, we include also an individual time-invariant covariate (gender) and a time-varyin

Original toplevel document (pdf)

cannot see any pdfs

Annotation 7625712995596

Changes in tensorflow

#tensorflow #tensorflow-certificate

From tensorflow version 2.7.0 model.fit() no longer automatically upscales inputs from shape (batch_size, ) to (batch_size, 1).

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

Flashcard 7625714830604

Tags

#tensorflow #tensorflow-certificate

Question

From tensorflow version 2.7.0 model.fit() no longer automatically upscales inputs from shape ([...] ) to (batch_size, 1).

Answer

batch_size,

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Changes in tensorflow
From tensorflow version 2.7.0 model.fit() no longer automatically upscales inputs from shape (batch_size, ) to (batch_size, 1).

Annotation 7625716403468

#tensorflow #tensorflow-certificate

OLD

Fit the model

model.fit(X, y, epochs=5) # this will break with TensorFlow 2.7.0+

New

Fit the model

model.fit(tf.expand_dims(X, axis=-1), y, epochs=5) # <- updated line

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

Flashcard 7625718238476

Tags

#tensorflow #tensorflow-certificate

Question

OLD

Fit the model

model.fit(X, y, epochs=5) # this will break with TensorFlow 2.7.0+

New

Fit the model

model.fit([...], y, epochs=5) # <- updated line

Answer

tf.expand_dims(X, axis=-1)

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Open it
OLD Fit the model model.fit(X, y, epochs=5) # this will break with TensorFlow 2.7.0+ New Fit the model model.fit(tf.expand_dims(X, axis=-1), y, epochs=5) # <- updated line

Annotation 7625719811340

#tensorflow #tensorflow-certificate

from tensorflow.keras.utils import plot_model

plot_model(model, show_shapes=True)

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

Flashcard 7625721646348

Tags

#tensorflow #tensorflow-certificate

Question

from tensorflow.keras.[...] import plot_model

plot_model(model, show_shapes=True)

Answer

utils

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Open it
from tensorflow.keras.utils import plot_model plot_model(model, show_shapes=True)

Annotation 7625723219212

#tensorflow #tensorflow-certificate

#### Def some functions to calculate losses (mae, mse)

def evaluate_mae(y_true, y_pred):
  return tf.keras.losses.mean_absolute_error(y_true = y_true,
                                      y_pred = tf.squeeze(y_pred))

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

Flashcard 7625725054220

Tags

#tensorflow #tensorflow-certificate

Question

#### Def some functions to calculate losses (mae, mse)

def evaluate_mae(y_true, y_pred):
  [...] tf.keras.losses.mean_absolute_error(y_true = y_true,
                                      y_pred = tf.squeeze(y_pred))

Answer

return

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Open it
#### Def some functions to calculate losses (mae, mse) def evaluate_mae(y_true, y_pred): return tf.keras.losses.mean_absolute_error(y_true = y_true, y_pred = tf.squeeze(y_pred))

Annotation 7625726627084

Deep learning advice

#tensorflow #tensorflow-certificate

You should minimize the time between your experiments (that's why you should start with smaller models). The more experiments you do, the more things you'll figure out that don't work.

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

Flashcard 7625728199948

Tags

#tensorflow #tensorflow-certificate

Question

You should [...] between your experiments (that's why you should start with smaller models). The more experiments you do, the more things you'll figure out that don't work.

Answer

minimize the time

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Deep learning advice
You should minimize the time between your experiments (that's why you should start with smaller models). The more experiments you do, the more things you'll figure out that don't work.

Annotation 7625729772812

Tensorflow fundamentals

#tensorflow #tensorflow-certificate

Tensorflow fundamentals

Basic operations on tensors in tensorflow

Introduction to tensors
Getting information from tensors
Manipulating tensors
Tensors wit NumPy
Using @tf.function (a way for speed up a regular python functions)
Using GPUs with tensorflow
Excersises

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

Flashcard 7625731607820

Tags

#tensorflow #tensorflow-certificate

Question

Tensorflow fundamentals

Basic operations on tensors in tensorflow

Introduction to tensors
Getting information from tensors
Manipulating tensors
Tensors wit NumPy
Using [...] (a way for speed up a regular python functions)
Using GPUs with tensorflow
Excersises

Answer

@tf.function

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Tensorflow fundamentals
Tensorflow fundamentals Basic operations on tensors in tensorflow Introduction to tensors Getting information from tensors Manipulating tensors Tensors wit NumPy Using @tf.function (a way for speed up a regular python functions) Using GPUs with tensorflow Excersises

Annotation 7625733180684

Tensorflow fundamentals

#tensorflow #tensorflow-certificate


another_matrix = tf.constant([[10. ,66.],
                              [5. , 9.],
                              [13. , 4.]], dtype=tf.float16)
another_matrix

Out:
<tf.Tensor: shape=(3, 2), dtype=float16, numpy=
array([[10., 66.],
       [ 5.,  9.],
       [13.,  4.]], dtype=float16)>

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

Flashcard 7625735015692

Tags

#tensorflow #tensorflow-certificate

Question


another_matrix = tf.[...]([[10. ,66.],
                              [5. , 9.],
                              [13. , 4.]], dtype=tf.float16)
another_matrix

Out:
<tf.Tensor: shape=(3, 2), dtype=float16, numpy=
array([[10., 66.],
       [ 5.,  9.],
       [13.,  4.]], dtype=float16)>

Answer

constant

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Tensorflow fundamentals
another_matrix = tf.constant([[10. ,66.], [5. , 9.], [13. , 4.]], dtype=tf.float16) another_matrix Out: <tf.Tensor: shape=(3, 2), dtype=float16, numpy= array([[10., 66.], [ 5., 9.], [13., 4.]], dtype=float16)&gt

Edited, memorised or added to reading queue

on 29-Apr-2024 (Mon)

Parent (intermediate) annotation

Original toplevel document (pdf)

Parent (intermediate) annotation

Original toplevel document (pdf)

OLD

Fit the model

New

Fit the model

OLD

Fit the model

New

Fit the model

Tensorflow fundamentals

Tensorflow fundamentals