Source Code for 'Advanced Applied Deep Learning' by Umberto Michelucci
License: Other
This repository accompanies Advanced Applied Deep Learning by Umberto Michelucci (Apress, 2019).
Download the files as a zip using the green button, or clone the repository to your machine using Git.
Release v1.0 corresponds to the code in the published book, without corrections or updates.
See the file Contributing.md for more information on how you can contribute to this repository.
Sir,
In chapter 5 - Neural Style Transfer
These errors are on both 2 notebooks -
glass.jpg is renamed to mosaic.jpg (but not in code, thus causing file not found)
AND
!pip install tensorflow-gpu==2.0.0-alpha0
This line is causing error in Colab, without it works fine.
Rest works fine.
In Chapter 4 - Transfer Learning
These data folders are missing -
1.train
2.validation_data
Thus causing error in whole code
import tensorflow as tf
tf.enable_eager_execution()
book shows this code but it errors out.
i guess in Colab it's already installed
# Output chess board image (chess board image)
import numpy as np
import matplotlib.pyplot as plt
chessboard = np.zeros([8*20,8*20])
for row in range(0,8):
for column in range(0,8):
if((column+8*row) % 2 ==1) and (row % 2 == 0):
chessboard[row*20:row*20+20,column*20:column*20+20] = 1
elif((column+8*row) % 2 ==0) and (row % 2 == 1):
chessboard[row*20:row*20+20,column*20:column*20+20] = 1
#set the plot's title.
#plt.title('Chess Board')
plt.xlim(xmin=0,xmax=160)
plt.ylim(ymin=0,ymax=160)
plt.imshow(chessboard,cmap='binary_r')
# Print the chart
plt.show()
This book is perfect book. It is the author's painstaking work and will be remembered by us in the long river of history!
Thanks @michelucci !
conda deactivate
conda remove -y --name tensorflow-gpu-keras --all
conda create -y --name tensorflow-gpu-keras python=3.6.13
activate tensorflow-gpu-keras
python -V
conda install -y tensorflow-gpu==1.13.1
conda install -y keras
REM Install matplotlib
conda install -y matplotlib
REM Failed to import `pydot`
conda install -y pydot
REM Install cv2(opencv)
conda install -y opencv
REM Install sklearn
conda install -y scikit-learn
REM Install pandas
conda install -y pandas
REM Install seaborn
conda install -y seaborn
REM Install scikit-image
conda install -y scikit-image
conda deactivate
conda deactivate
conda remove -y --name tensorflow-2.3.0-gpu-keras --all
conda create -y --name tensorflow-2.3.0-gpu-keras python=3.7.16
activate tensorflow-2.3.0-gpu-keras
python -V
conda install -y tensorflow-gpu==2.3.0
conda install -y keras
REM Install matplotlib
conda install -y matplotlib
REM Failed to import `pydot`
conda install -y pydot
REM Install cv2(opencv)
conda install -y opencv
REM Install sklearn
conda install -y scikit-learn
REM Install pandas
conda install -y pandas
REM Install seaborn
conda install -y seaborn
REM Install scikit-image
conda install -y scikit-image
conda deactivate
Hello,
Great book ... been absorbing the info as quickly as I can!
I did notice that "elephant.jpg" from Chapter 4 (as referred to on page 143) seems to be missing from the github repo.
Or at least, I have not been able to find it.
Cheers,
Ion-Drive
Ref:
AttributeError: module 'keras.backend' has no attribute 'image_dim_ordering'
keras-team/keras#12649 (comment)
Change
import keras.backend as K
K.set_image_dim_ordering('th')
To
import keras.backend as K
K.common.set_image_dim_ordering('th')
@michelucci ,
In page 32 of this book, the y should be y_noise.
for i in range(iters):
optimizer.apply_gradients(grad(model,x,y_noise))
if i % 1000 == 0:
print("Iteration {}, loss: {}".format(i+1, loss(model,x,y_noise).numpy()))
@michelucci ,
Your Chinese book ‘深度学习进阶,卷积神经网络和对象检测’, it also contains the same error.
Do you afford the Chinese book‘s translators' emails? Yang Tao and Yanan Li. Thanks!
@michelucci ,
Your book is perfect! Thank you!
Here, I found a issue, I have fixed it. I posted the fixed method.
In tensorflow 1.13.1, I run your code, a issue encountered.
import tensorflow as tf
import keras
import numpy as np
import matplotlib.pyplot as plt
plt.style.use('default')
import tensorflow.contrib.eager as tfe
#from google.colab import files
tf.enable_eager_execution()
num_classes = 10
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
image_vector_size = 28*28
x_train = x_train.reshape(x_train.shape[0], image_vector_size).astype('float32')
x_test = x_test.reshape(x_test.shape[0], image_vector_size).astype('float32')
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
dataset = tf.data.Dataset.from_tensor_slices(
(tf.cast(x_train/255.0, tf.float32),
tf.cast(y_train,tf.int64)))
dataset = dataset.shuffle(60000).batch(64)
mnist_model = tf.keras.Sequential([
tf.keras.layers.Dense(1024, input_shape=(784,)), # must declare input shape
tf.keras.layers.Dense(1024), # must declare input shape
tf.keras.layers.Dense(10)
])
optimizer = tf.train.AdamOptimizer()
loss_history = []
#%%time
with tf.device('/cpu:0'):
for i in range(1): # Loop for the Epochs
print ("\nEpoch:", i)
for (batch, (images, labels)) in enumerate(dataset.take(60000)): # Loop for the mini-batches
if batch % 100 == 0:
print('.', end='')
with tf.GradientTape() as tape:
logits = mnist_model(images, training=True)
loss_value = tf.losses.sparse_softmax_cross_entropy(tf.argmax(labels, axis = 1), logits)
loss_history.append(loss_value.numpy())
grads = tape.gradient(loss_value, mnist_model.variables)
optimizer.apply_gradients(zip(grads, mnist_model.variables),
global_step=tf.train.get_or_create_global_step())
probs = tf.nn.softmax(mnist_model(x_train))
print(tf.reduce_mean(tf.cast(tf.equal(tf.argmax(probs, axis=1), tf.argmax(y_train, axis = 1)), tf.float32)))
Epoch: 0
..........
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-4-6753e0f3f94f> in <module>
54 global_step=tf.train.get_or_create_global_step())
55
---> 56 probs = tf.nn.softmax(mnist_model(x_train))
57 print(tf.reduce_mean(tf.cast(tf.equal(tf.argmax(probs, axis=1), tf.argmax(y_train, axis = 1)), tf.float32)))
D:\ProgramData\Anaconda3\envs\tensorflow-gpu-keras\lib\site-packages\tensorflow\python\keras\engine\base_layer.py in __call__(self, inputs, *args, **kwargs)
590 else:
591 # Eager execution on data tensors.
--> 592 outputs = self.call(inputs, *args, **kwargs)
593 self._handle_activity_regularization(inputs, outputs)
594 return outputs
D:\ProgramData\Anaconda3\envs\tensorflow-gpu-keras\lib\site-packages\tensorflow\python\keras\engine\sequential.py in call(self, inputs, training, mask)
228 def call(self, inputs, training=None, mask=None):
229 if self._is_graph_network:
--> 230 return super(Sequential, self).call(inputs, training=training, mask=mask)
231
232 outputs, _ = self._call_and_compute_mask(
D:\ProgramData\Anaconda3\envs\tensorflow-gpu-keras\lib\site-packages\tensorflow\python\keras\engine\network.py in call(self, inputs, training, mask)
813 outputs, _ = self._run_internal_graph(inputs,
814 training=training,
--> 815 mask=masks)
816 return outputs
817
D:\ProgramData\Anaconda3\envs\tensorflow-gpu-keras\lib\site-packages\tensorflow\python\keras\engine\network.py in _run_internal_graph(self, inputs, training, mask)
998 else:
999 if context.executing_eagerly():
-> 1000 output_tensors = layer(computed_tensor, **kwargs)
1001 else:
1002 output_tensors = layer.call(computed_tensor, **kwargs)
D:\ProgramData\Anaconda3\envs\tensorflow-gpu-keras\lib\site-packages\tensorflow\python\keras\engine\base_layer.py in __call__(self, inputs, *args, **kwargs)
590 else:
591 # Eager execution on data tensors.
--> 592 outputs = self.call(inputs, *args, **kwargs)
593 self._handle_activity_regularization(inputs, outputs)
594 return outputs
D:\ProgramData\Anaconda3\envs\tensorflow-gpu-keras\lib\site-packages\tensorflow\python\keras\layers\core.py in call(self, inputs)
973 outputs.set_shape(output_shape)
974 else:
--> 975 outputs = gen_math_ops.mat_mul(inputs, self.kernel)
976 if self.use_bias:
977 outputs = nn.bias_add(outputs, self.bias)
D:\ProgramData\Anaconda3\envs\tensorflow-gpu-keras\lib\site-packages\tensorflow\python\ops\gen_math_ops.py in mat_mul(a, b, transpose_a, transpose_b, name)
5321 else:
5322 message = e.message
-> 5323 _six.raise_from(_core._status_to_exception(e.code, message), None)
5324 # Add nodes to the TensorFlow graph.
5325 if transpose_a is None:
D:\ProgramData\Anaconda3\envs\tensorflow-gpu-keras\lib\site-packages\six.py in raise_from(value, from_value)
InvalidArgumentError: cannot compute MatMul as input #0(zero-based) was expected to be a float tensor but is a uint8 tensor [Op:MatMul]
Modify
x_train = x_train.reshape(x_train.shape[0], image_vector_size)
x_test = x_test.reshape(x_test.shape[0], image_vector_size)
To
x_train = x_train.reshape(x_train.shape[0], image_vector_size).astype('float32')
x_test = x_test.reshape(x_test.shape[0], image_vector_size).astype('float32')
Epoch: 0
..........tf.Tensor(0.88195, shape=(), dtype=float32)
Dear @michelucci,
There is no 'glass.jpg' image in chapter5.
layer1 = Dense(32,trainable=False)
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.