Convolutional Neural Networks - Deep Learning basics with Python, TensorFlow and Keras p.3

Показать описание

Welcome to a tutorial where we'll be discussing Convolutional Neural Networks (Convnets and CNNs), using one to classify dogs and cats with the dataset we built in the previous tutorial.

Рекомендации по теме

Комментарии

As a programmer/amateur data scientist, I have wanted to understand and use neural networks to take my craft to the next level for years, and sentdex, you are the first that has enabled me to actually break that glass ceiling and use neural networks for real-life problems. Thank you so much!

blendamosity

You can add layer with Activation inside:
model.add(Dense(256, activation='relu'))
It allows you to choose activation function to each of them separately

nikolaiivankin

You can add the "layers" as an array "model = Sequential ([ flatten(), Dense(10), Activation('relu') ])" instead of using the model.add() function every time.

aaronshed

you should definitely do a video on transfer learning in this series.

camdenparsons

15:55 Found the solution: If you did everything exactly the same throughout the previous video, just add this " y = np.array(y) " after the " X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 1)" so it look like this:
X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 1)
y = np.array(y)

It was giving me errors until adding that line too and reexecuting it

prohacker

Hi Harrison, doesn´t the Dense(64) layer at 11:30 need an activation function? I added another "relu" there and got better accuracy.

brotherlui

For anyone getting the following error "validation_split is only supported for Tensors or NumPy " add y = np.array(y) under X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 1)

ahmednayeem

you have some of the strangest coffee cups I have ever seen

waynefilkins

A tutorial on keras callbacks such as EarlyStopping and ModelCheckpoint would be nice.

Also, I would love if you could explain Image Augmentation in Keras for CNN.

gautamj

Hi, Sir. i found a problem with:
ValueError Traceback (most recent call last)
in <module>
----> 1 model.fit(X, y, batch_size = 32, epochs=3, validation_split=0.1)

in _method_wrapper(self, *args, **kwargs)

do you have any suggestion to solve this error?

tiarakusumadewi

It was a headache but I finally installed tensorflow-gpu on my windows pc. now I can run the epoch in 20 seconds!

mason

X=X/255.0 is giving me error unsupported operand type(s) for /: 'NoneType' and 'float'. How will I rectify the error ?

aniketpatra

hey sentdex, nice tutorial I've been binge watching your tutorial videos and compared to your previous convolutional neural network videos I noticed a few differences. For conv2D you didn't increase the number of features(for both layers you kept it at 64) whereas previously you increased it. Why is that? Moreover, why did we not use dropout and why did we use the 'sigmoid' activation function over 'softmax'? And also wanted to say thank you for the great content!

bharddwajvemulapalli

For anyone who had a negative loss by following this tutorial with your own dataset which had more than 2 categories of labels, don't forget to normalize your label array as well!! So y_normalized = y/ y_.max(). it will make your labels to be between 0-1 and then the whole thing works just fine

gangholdon_

Hi guys,

I tried the tutorial as showed here step by step, but I get this message when I try to run the CNN:

ValueError: Input 0 of layer conv2d is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: (None, 150, 150)

Any suggestion on why?

Thanks!

andreachiarello

how would i go about running this on the GPU instead of my CPU? it is taking ages to run a singular epoch

RRKS_TF

Hey sendex, may I ask what kind net structure are you using? CNN has a lot of net structure, like vgg-16, u-net, and etc. Therefore, what's the net structure you are using?

kevintsai

I am getting an error at validation split ValueError: `validation_split` is only supported for Tensors or NumPy arrays, found: (array([[[[ 36],

sanjanakonda

Hi, can I know what is the problem with this?

ValueError: logits and labels must have the same shape ((None, 1) vs (None, 100, 100, 1))

I followed your code but got this error at the end.

chanhwasheng

"I need more tea" cracks me
Thanks for the vid

Osirisdaro

Convolutional Neural Networks - Deep Learning basics with Python, TensorFlow and Keras p.3

What are Convolutional Neural Networks (CNNs)?

Convolutional Neural Networks (CNNs) explained

MIT 6.S191 (2023): Convolutional Neural Networks

Convolutional Neural Networks Explained (CNN Visualized)

But what is a convolution?

Simple explanation of convolutional neural network | Deep Learning Tutorial 23 (Tensorflow & Pyt...

Neural Networks Part 8: Image Classification with Convolutional Neural Networks (CNNs)

CNN: Convolutional Neural Networks Explained - Computerphile

Deep Learning Chapter 14 part 1 : Computer Vision Using Convolutional Neural Networks

How convolutional neural networks work, in depth

Convolutional Neural Networks - Deep Learning basics with Python, TensorFlow and Keras p.3

What is a convolutional neural network (CNN)?

Convolutional Neural Network from Scratch | Mathematics & Python Code

MIT 6.S191: Convolutional Neural Networks

Convolutional Neural Network Tutorial (CNN) | How CNN Works | Deep Learning Tutorial | Simplilearn

Hot Dog or Not Hot Dog – Convolutional Neural Network Course for Beginners

Groups, Depthwise, and Depthwise-Separable Convolution (Neural Networks)

C4W2L05 Network In Network

Convolutional Neural Networks | CNN | Kernel | Stride | Padding | Pooling | Flatten | Formula

Neural Networks Explained in 5 minutes

Convolutional Neural Networks (CNNs) | Deep Learning

But what is a neural network? | Chapter 1, Deep learning

Lecture 5 | Convolutional Neural Networks

Convolutional Neural Networks | Deep Learning Animated