Convnet Intro – Deep Learning and Neural Networks with Python and Pytorch p.5




[ad_1]

Now that we’ve learned about the basic feed forward, fully connected, neural network, it’s time to cover a new one: the convolutional neural network, often referred to as a convnet or cnn.

Convolutional neural networks got their start by working with imagery.

Text-based tutorials and sample code: https://pythonprogramming.net/convolutional-neural-networks-deep-learning-neural-network-pytorch/

Linode Cloud GPUs $20 credit: https://linode.com/sentdex

Channel membership: https://www.youtube.com/channel/UCfzlCWGWYyIQ0aLC5w48gBQ/join
Discord: https://discord.gg/sentdex
Support the content: https://pythonprogramming.net/support-donate/
Twitter: https://twitter.com/sentdex
Instagram: https://instagram.com/sentdex
Facebook: https://www.facebook.com/pythonprogramming.net/
Twitch: https://www.twitch.tv/sentdex

#pytorch #deeplearning #machinelearning

Source


[ad_2]

Comment List

  • sentdex
    November 22, 2020
  • sentdex
    November 22, 2020

    When talking about the convolutional neural network, you mention that a 3*3 kernel is used to find simple features in the first layer, does this kernel typically become larger upon subsequent layers or is does higher complexity arise from feeding in the procesed, down-sampled image?

  • sentdex
    November 22, 2020

    Can any one plz explain How to deal with audio classification on this model?
    I dont have csv file only raw audio of different classes.
    any reference will help

  • sentdex
    November 22, 2020

    How do you find if there is an apple in the catvsdog dataset?
    What your network will predict about apple?

  • sentdex
    November 22, 2020

    can you send me one of that quadrotor??? they are really cool

  • sentdex
    November 22, 2020

    eye is for "I" in Identity matrix ig

  • sentdex
    November 22, 2020

    12:00 very smooth

  • sentdex
    November 22, 2020

    I have Tensorflow 1.13.2 version on CUDA 10.0 with cuDNN 7.4.2 version, and I want to install Pytorch according to CUDA 10.0 with cuDNN 7.4.2 version – so which Pytorch version is compatible with CUDA 10.0 with cuDNN 7.4.2 version? thank you.
    Website: https://pytorch.org/get-started/previous-versions/

    This person here used the same way I wanted (Website: https://tikoehle.github.io/pytorch_conda_jupyterhub/nvidia_cuDNN.html) but I want to be sure, so I am asking; because there is no clear answer in internet for this specific question above.

    I will be very glad if someone would reply, thank you.

  • sentdex
    November 22, 2020

    np.eye -> Identity Matrix. It's a heritage from matlab. lots of np functions use the same name as in matlab

  • sentdex
    November 22, 2020

    eye –> identity matrix

  • sentdex
    November 22, 2020

    It is much mor intuitive for anyone to read
    $ one_hot_vectors = np.array([[1, 0], [0, 1]])

    than
    $ np.eye(2)

  • sentdex
    November 22, 2020

    Hi sentdex I have a comment. Your visualizations might not be 3dBlue but your oratory skills are amazing! Great explanation about how and why conv nets work. You've moved my confusion up to the next step.

  • sentdex
    November 22, 2020

    the "be my subscriber" doorbell is very good you got me man

  • sentdex
    November 22, 2020

    Eye for identity matrix as this function creates an identity matrix which is denoted by letter “I”.

  • sentdex
    November 22, 2020

    Me new to programming: Wow, what wonders await?

    Python: A L L O W P I C K L E C A N N O T B E F A L S E

  • sentdex
    November 22, 2020

    You did not mention the step size with which you slide the window. I think the number of features we are seeking depends upon how we slide the window? I mean with what step size. In your case, you slide it by 2 If I am not wrong.

  • sentdex
    November 22, 2020

    If anyone facing problem with "module" object is not callable then try to remove tqdm to os.listdir(label)

  • sentdex
    November 22, 2020

    Ah yes, classic dog person, ridiculing cats…

  • sentdex
    November 22, 2020

    using torch ImageFolder class will do all these steps for you!

  • sentdex
    November 22, 2020

    I am a beginner in learning neural networks, I had soo many difficulties in understanding how they work, and even the implementation, but since I found this link I am at peace now and I just see things flow, thank you for your great work.

  • sentdex
    November 22, 2020

    have a basic question. When Forward and background propagation happens, does it enumerate any number of time back and forth to go to minimize loss or do we need to iterate in a loop? So the training loop is for each image, but then the Forward and Backward goes any number of times to optimize, correct?

  • sentdex
    November 22, 2020

    34:20 THAT SHIT'S GETTING SENTIENT

  • sentdex
    November 22, 2020

    Sentdex: I don't think I'm the greatest at visuals
    Me: Yeah I know but cant be that bad
    Sentdex: So let's say we got an image of a cat
    hardest laugh in weeks

    no front lol… love your videos..and they are really helpful…thanks

  • sentdex
    November 22, 2020

    "attempt" at being a dog. Man I cracked up at that xD

  • sentdex
    November 22, 2020

    Why can't I join that community? The link does not open apparently

  • sentdex
    November 22, 2020

    np.eye() is eye because it represents identity matrix which is usually denoted by 'I' so pronounced 'eye'

  • sentdex
    November 22, 2020

    OpenCV Error: Assertion failed (ssize.width > 0 && ssize.height > 0) in resize, file /build/opencv-L2vuMj/opencv-3.2.0+dfsg/modules/imgproc/src/imgwarp.cpp
    anyone getting this issue?

  • sentdex
    November 22, 2020

    click 4 and 5 repeatedly while paused and look at sentdex

  • sentdex
    November 22, 2020

    Can you 26:32 duplicate images and not throw them away to achieve balance?

  • sentdex
    November 22, 2020

    Yeah numpy load is complaining because by default it does not want to use pickle. The numpy format is really meant to be used for numeric data, only; data which is some numpy data object such as arrays. Generally, you can serialize your objects with numpy, too (it uses pickle to do so) but the latter is generally not recommended (as of pickle documentation) since the binary data format of pickle changes here and there over the course of time, so it's not reliable. The clean way is to introduce some converter functions/methods to convert everything to numpy arrays, first, before saving and loading it. However, you can get away with it when you argue that the saved ".npy" file is not meant to be a long term storage format (e.g. for tracibility) but rather some intermediate step of the training pipe which you can easily rebuild as you have implemented here, too.

  • sentdex
    November 22, 2020

    Great that you added the discussion whether or not to go for greyscale! I often find that people do not really think about what are the features which actually enable the network to do the job but rather throw everything into the network which will work too but it adds unnecessary complexity.

  • sentdex
    November 22, 2020

    Yeah the condensing due to the convolution/filter is more like a side effect. It is worth mentioning that there is another mode where you can assume that all pixels which are beyond the image are zero. This provides the possibility to keep the dimension of your image the same. However, this leads to the issue that the pixels at the edges get less filtered than the pixels in the inner part of your image. This might or might not be a problem. Therefore, most of the time the people stick to the type of convolution that you have shown here. However, if you have rather small images and you still want to have a larger number of convolutional layers, you might not be able to have that much because at some layer you already condensed all images to a single pixel. In order to overcome this, you could use the other mode of convolution (after decreasing pooling size to something like 2×2 already of course).

  • sentdex
    November 22, 2020

    somehow it gave this exception : expected str, bytes or os.PathLike object, not tuple for every iteration.

    i did this as a solution:
    s = (label, f)

    path = os.path.join(*s)

  • sentdex
    November 22, 2020

    Sir,
    You did not initialize constructor . I m unable to understand how object of class can be called
    Please help🙏🙏🙏

  • sentdex
    November 22, 2020

    hi @sentdex, can you do tutorial on rnn and lstm for pytorch. thanks!

  • sentdex
    November 22, 2020

    Eye stands for identity matrix I I think

  • sentdex
    November 22, 2020

    Dunno if you still answer question but I just try:

    Your call operates with 800 it/s. Mine (using colab tho and images from drive) only runs with like 1-2 so it takes forever. Is colab the issue?

  • sentdex
    November 22, 2020
  • sentdex
    November 22, 2020

    hi, i searched for pytorch tutorial on youtube and found this course the first one.. good job.. and i hope when i finish this series i'll become pytorch expert xD

    anyway, i still don't understand what's the use of REBUILD_DATA does.. could you elaborate on that, please? thanks

  • sentdex
    November 22, 2020

    I like your visual! Very contemporary art.

  • sentdex
    November 22, 2020

    What do you think about the new FAA drone regs??
    (OT)

  • sentdex
    November 22, 2020

    little demons vs adorable creatures LOL

  • sentdex
    November 22, 2020

    what if its a catdog? [1,1]?

  • sentdex
    November 22, 2020

    "this isnt really a dog, its basically a cat"

  • sentdex
    November 22, 2020

    Just a quick note – I'm using ubuntu linux and I came across quite unpleasant problem: The images in MS dataset were unreadable by my computer, so I had to delete tens of images to get it running (try and except didn't help)

  • sentdex
    November 22, 2020

    The demons are my friends…

  • sentdex
    November 22, 2020

    That was a smooth transition to talk about join and subscribe buttons.

Write a comment