Lesson 2: Practical Deep Learning for Coders 2022

  Рет қаралды 172,737

Jeremy Howard

Jeremy Howard

Күн бұрын

Пікірлер: 106
@Karen-ls7hv
@Karen-ls7hv Жыл бұрын
thank you for making AI education free and accessible 😊
@howardjeremyp
@howardjeremyp Жыл бұрын
It's my pleasure
@nimbus1r
@nimbus1r Жыл бұрын
❤ This course will have a ripple effect for an entire generation of programming
@chuhaoliu5050
@chuhaoliu5050 Жыл бұрын
Update for 2023. In Gradio deployment notebook, `intf.launch(inline=False)` needs to change to `intf.launch(inline=False,share=True)` to have the public web link.
@cullenharris1837
@cullenharris1837 2 жыл бұрын
Where can we find the notebook at 41:32 for Dogs v Cats on your local?
@hawperify
@hawperify 2 жыл бұрын
Also wondering this, having trouble following along that this section...
@paulmest
@paulmest 2 жыл бұрын
It was covered in Lesson 1. Check out the Resources section here: course.fast.ai/Lessons/lesson1.html
@bampy81
@bampy81 Жыл бұрын
Got the same problem. It's the app.ipynb file that I can't find. Did you manage to find it?
@nostalgiccringeallhailchel3881
@nostalgiccringeallhailchel3881 Жыл бұрын
@@paulmest where is it in the resources section?
@nostalgiccringeallhailchel3881
@nostalgiccringeallhailchel3881 Жыл бұрын
@@bampy81 did you find it? if yes please lemme know
@saadorj
@saadorj 2 жыл бұрын
Thank you, Jeremy, and everyone involved in creating this great course. It only gets better with every new iteration!
@strikingpotato3572
@strikingpotato3572 Жыл бұрын
Just like a Neural Network no? :)
@prof.ravindravyas3035
@prof.ravindravyas3035 Ай бұрын
Dear Sir, Great Lecture and superb knowlege sharing session..............One thing I would like to quote is in start of lecture when speaker says " I am super excting to teach this lecture" .........students like me and others feel standing on race line and start running..........most enthusiastic teacher...........
@mikementele
@mikementele 5 ай бұрын
I've taken many ML courses over the years and I love the hands on nature of this with Jupyter notebooks, the extra background provided with the book, the quizzes, and the top down approach that orients you on breadth before depth. This is done right from a pedagogy standpoint.
@cojocarucosmin202
@cojocarucosmin202 2 жыл бұрын
Respect for giving out high quality information, you are the real deal and so few people actually know...
@arkadymarchenko1516
@arkadymarchenko1516 4 ай бұрын
Hi Jeremy, I love the education your giving through your videos and non-coding parts of your book but I often find you notebooks are pretty buggy and down work out of the box. The last notebook provided for lesson 1 (is it a bird) required me to import another image crawler to make it work. For this lesson, the ddg image search wasnt working properly as well and I had to make major modifications. I love everything you're doing but I would love if you updated this course to provided updated and working notebooks to make it seamless for people like me to learn deep learning
@palahnuk1
@palahnuk1 Жыл бұрын
Jeremy ... you are the real deal ... thanks for giving your personal time and energy to open the world of ML to mere mortals like us older engineers ... you are a real world blessing!
@piecucci
@piecucci 10 ай бұрын
10:57 I was getting an error after running dls = bears.dataloaders(path) from the cells further fown in the notebook. I needed to change the quotations marks in the cell with bear_types for the variable path = Path("bears") (double quotation marks)... Took me some googling around to make it work!
@piecucci
@piecucci 10 ай бұрын
I've also needed deindent the for loop for the bear_types and remove the folders created before running the code again. if not path.exists(): path.mkdir() for o in bear_types: dest = (path/o) dest.mkdir(exist_ok=True) download_images(dest, urls=search_images_ddg(f'{o} bear photo'))
@frankkranktrangtmohammedny807
@frankkranktrangtmohammedny807 10 ай бұрын
​@@piecucci I had the exact same problem. Thanks for commenting this!🙏
@zzznavarrete
@zzznavarrete 4 ай бұрын
Also, whoever is using Gradio's version 4.39 or above, the following is code is for the Gradio interface: # creating the gradio interface image = gr.Image(height=192, width=192) label = gr.Label() examples:list = ['./assets/dog.png', './assets/cat.png', './assets/dunno.png'] intf = gr.Interface(fn=classify_image, inputs=image, outputs=label, examples=examples) intf.launch(inline=False)
@TudiIveelt
@TudiIveelt Ай бұрын
thanks!
@lucianomarchezan2372
@lucianomarchezan2372 19 күн бұрын
thank you!!
@DeepakKumarDataScience
@DeepakKumarDataScience Жыл бұрын
What is the repo used for this set of jupyter notebooks? The Fastbook directory seems to have the textbook version that uses Azure SDK keys whereas Jeremy refers to the DDG alternative. I am not able to find the right folder under the fast ai repos.
@miskaknapek
@miskaknapek 2 ай бұрын
Thanks for this video too! I very much appreciate the content and the enthusiastic pedagogical style
@rahmanoff
@rahmanoff 10 ай бұрын
Thanks Jeremy! p.s. if you try to go step by step and got error "module 'gradio' has no attribute 'inputs'", try gradio==3.48. It works well for me.
@elvryn_
@elvryn_ Жыл бұрын
So fun hearing anecdotes of classifying images of a dog cat with your daughter
@dmoneyballa
@dmoneyballa 2 жыл бұрын
Thank you so much for adding the commands for wsl to add the drivers on ubuntu. this is the most time consuming part for me when I setup a new computer. I really appreciate it.
@datalifenyc
@datalifenyc 2 жыл бұрын
49:12 Looking at the source code for nbdev.export, there is no `notebook2script` function. The closest in functionality appears to be `nb_export(nbname, lib_path = None)`. nbdev version: 2.0.6. Did anyone run into the same issue?
@datalifenyc
@datalifenyc 2 жыл бұрын
This video is probably referencing v1 of nbdev. For v2, you can use: # Bash Terminal nbdev_export --path "app.ipynb" or # Jupyter Notebook from nbdev import nbdev_export nbdev_export("app.ipynb") A `nbdev` folder is created with the `app.py` file in it.
@dingding4898
@dingding4898 2 жыл бұрын
anything to convert an existing project to nbdev?
@JeffJohnston-l8x
@JeffJohnston-l8x Ай бұрын
Where do I find the "Dog v Cats" Notebook shown at 41:27?
@chuhaoliu5050
@chuhaoliu5050 Жыл бұрын
It's way more fun to learn by building something people can actually use!! Thanks a ton!
@AiEdgar
@AiEdgar Жыл бұрын
No fillers so much knowledge I wish all my teachers were this good.
@marktomm1959
@marktomm1959 8 ай бұрын
With gradio==4.28.3 the example code in the video won't work. error "module 'gradio' has no attribute 'inputs'" Fix: image = gr.Image(height=192, width = 192) label = gr.Label()
@bhanutadepalli
@bhanutadepalli 2 жыл бұрын
56:57 curl doesnt have --no-progress-meter option. If you are setting up on mac remove that option from the command
@hiankun
@hiankun 2 жыл бұрын
"And when I say one day, more specifically... today!" XD Today is a good day. 😀
@KiLVaiDeN
@KiLVaiDeN 2 жыл бұрын
This is very neat content, and your way of explaining those concepts is calm and posed, very enjoyable to watch ! Thank you.
@aworden
@aworden Жыл бұрын
Where can we get the locally run notebook that you used to create the python script for the gradio app? Could this be run in Kaggle instead of locally and exported / downloaded? It makes it confusing that you're jumping from Kaggle to colab to local notebooks. Is that necessary?
@kophaihoang
@kophaihoang 10 ай бұрын
The weird dog at 47:20 is "Chó Dúi" and he is from Vietnam, it is unlucky that he just passed away last year :(
@AnibalCarpio
@AnibalCarpio Жыл бұрын
Where can I look for the notebook to lesson 2 using ddg method?, cause on the fastai book website still show the version using key and Microsoft Azure
@ChrisLonsberry
@ChrisLonsberry 2 жыл бұрын
OMG, I'm so excited to see new updates to this course! EDIT: Is there somewhere that I can read about what has changed?
@ishitaraj7723
@ishitaraj7723 2 ай бұрын
where is the notebook at 41:27 coming from?
@enigmeta
@enigmeta Жыл бұрын
It seems that nbdev 2.0 works very differently, because the export doesn't work anymore. Is there a good tutorial on how to use the new version?
@jasonholtkamp8462
@jasonholtkamp8462 Жыл бұрын
You know what's hilarious is that I actually read the book chapter before watching the lesson and I had the hardest time finding my Azure Bing API Key after I made my account and whatnot... It literally took me longer to just do that step than the entire rest of the lesson lol. And then Jeremy just goes yeah screw that I'm going to use duckduckgo instead haha.
@zzznavarrete
@zzznavarrete 4 ай бұрын
for those who are using windows and got the following error message: "NotImplementedError: cannot instantiate 'PosixPath' on your system", the fix is: import pathlib temp = pathlib.PosixPath pathlib.PosixPath = pathlib.WindowsPath
@mamotivated
@mamotivated 2 жыл бұрын
@jeremy in the randomization/augmentation process in real-time in memory, does a single image and its variants all get included in a single batch? If they do, how does this affect the quality of the weight updates vs spreading some of the augemented images to other batches
@33gbm
@33gbm 3 ай бұрын
Nice course. But you are always changing the references in the video, it would be nice to find the ipy notebooks you are working on in a single place.
@05me39
@05me39 2 жыл бұрын
6:57 Need to import widgets before using ImageClassifierCleaner from fastai.vision.widgets import *
@devanshkmishra
@devanshkmishra Жыл бұрын
thanks
@djstr0b3
@djstr0b3 11 ай бұрын
Thank you for the amazing videos Prof. Howard!
@estrellaum9480
@estrellaum9480 2 жыл бұрын
I need triple the time of the video to understand it, but I am getting there, thanks! By the way, the dog-cat thing apparently is a puppy...
@shubh9207
@shubh9207 6 ай бұрын
Hello, is it fine to run Jupyter notebook on VS code instead of running it on a local browser?
@jonathangrant7788
@jonathangrant7788 2 жыл бұрын
You mention that the learner needs all the same functions it had in training. Is this due to using pickle? Can you just use cloudpickle instead and not provide the training environment?
@miladrahimi3283
@miladrahimi3283 Жыл бұрын
This tutorials is really helpful, thanks so much. you are boosting my knowledge.
@sayan7s
@sayan7s Жыл бұрын
Jeremy thank you so much for all the effort. It means a lot ! Really appreciate
@jimshtepa5423
@jimshtepa5423 Жыл бұрын
what does calling 'train' method on dls object do? does it show the images that are used to train the model? what does 'valid' method do?
@mehnaazmohiuddin
@mehnaazmohiuddin Жыл бұрын
In the step of cleaning the data . Are we moving the files in the folder ? Do we have to have to create the model again?
@ericflynn5799
@ericflynn5799 8 ай бұрын
I'm running into an issue where the ImageClassifierCleaner is not working properly in a Kaggle notebook. Anyone else face a similar issue and know a solution?
@MyselfTheodore
@MyselfTheodore 6 ай бұрын
Re-running all the cells from the start fixed it for me
@toromanow
@toromanow Жыл бұрын
It says fastpages is deprecated and one should use quattro instead. Thoughts?
@КсенияПак-ш6в
@КсенияПак-ш6в 2 жыл бұрын
Yes it can - don't despair!
@mikementele
@mikementele 5 ай бұрын
This course is amazing
@jordankuzmanovik5297
@jordankuzmanovik5297 2 жыл бұрын
Hi jeremy, as always great course. But what about practical deep learning from the foundation? I am waiting 2 years for those. Thanks
@neild7457
@neild7457 Жыл бұрын
Thank you very much for this course :)
@slf188
@slf188 2 жыл бұрын
Great lecture! Jeremy is amazing at explaining such cryptic concepts
@mistercakes
@mistercakes Жыл бұрын
thank you for the great content. do you recommend jupyter notebook over jupyter lab? (any reason, is nbdev supported in jupyter lab?) also you mention number of epochs recommended. it could be useful just to give a number on how many epochs were needed to do the original training on the model that we are fine tuning against to give some perspective.
@ashish31416
@ashish31416 2 жыл бұрын
Thank you for the amazing course.
@gblazerify
@gblazerify Жыл бұрын
Great educational video!
@nathanmcnaughton4468
@nathanmcnaughton4468 2 жыл бұрын
I created a hugging space faces page and created a new space called "minimal", selected apachie, radio, and public. Im on mac and copied the repo into the terminal. I then tried to do code . but it says "command not found: code" I am not sure what I did wrong.
@ladyblack679
@ladyblack679 2 жыл бұрын
I had the same issue First make sure you have downloaded Visual Studio Code Open Visual Studio Code Type Cmd+Shift+P and input '> shell command' and click Shell Command: Install 'code' command in PATH command. Restart your terminal In the terminal type in “cd minimal” Then input “code . "
@nostalgiccringeallhailchel3881
@nostalgiccringeallhailchel3881 Жыл бұрын
uninstall and reinstall vscode. Sometimes the environment path get corrupted and the updates don't happen properly
@nigeljdean
@nigeljdean Жыл бұрын
I had the same issue. It worked straight after I had restarted the windows 11 PC
@bhanutadepalli
@bhanutadepalli 2 жыл бұрын
mamba install jupyter notebook is required nbdev alone doesnt install jupyter on Mac
@vikramsandu6054
@vikramsandu6054 Жыл бұрын
Loved every bit of it. Thanks, jph00. ;)
@gregfaruch7886
@gregfaruch7886 2 жыл бұрын
Really cool ! Thank you to share with us.
@정민혁-f9v
@정민혁-f9v Жыл бұрын
I love your lecture! 😄
@nostalgiccringeallhailchel3881
@nostalgiccringeallhailchel3881 Жыл бұрын
btw that dog cat image is actually a puppy that looks like a cat
@derekcarday
@derekcarday Жыл бұрын
Is there a reason why you use windows? I've been working industry as a developer for 7 years now and have only seen one person use windows and they always had issues. Just curious if it's cuz microsoft now ships with linux kernel or if there's any benefits for deep learning.
@howardjeremyp
@howardjeremyp Жыл бұрын
I like being able to use a stylus directly on the screen. I use WSL (Linux) or SSH into a Linux server for nearly all my work though.
@priyanshutiwary9500
@priyanshutiwary9500 Жыл бұрын
how to study this course. does it only have 8 lectures ?
@howardjeremyp
@howardjeremyp Жыл бұрын
No there's 25 lectures. Go to course.fast.ai/ .
@davisisibor3509
@davisisibor3509 6 ай бұрын
Watching this last few sections of this video as a frontend developer . Was one of my best moments 😂😂😂😂. I skipped the entire thing 😂😂😂😂😂
@mansamusa559
@mansamusa559 2 жыл бұрын
Love the course !! But I really recommend streamlit instead of gradio.. :D
@JoelOrellana
@JoelOrellana 10 ай бұрын
so amazing classss
@taitonium6262
@taitonium6262 Жыл бұрын
this is bery good thank you ;)
@chawaphiri1196
@chawaphiri1196 Ай бұрын
The dunno worked on my computer. it said 60% cat and 40% dog. it was just brilliant
@juanmontero883
@juanmontero883 2 жыл бұрын
Thank you so much!
@NotaUserIam
@NotaUserIam Жыл бұрын
Love the course but I do hate the way you code. I have spent way too much time figuring out which imports are giving me which function I’m using
@howardjeremyp
@howardjeremyp Жыл бұрын
To find out what import provides a function, type the function name and hit shift-enter.
@JoshGodwinArt
@JoshGodwinArt 2 жыл бұрын
The one thing that didn't seem super clear to me is why he is doing everything in a Linux environment in the first place. Why not just install python and all the libraries on regular windows without that extra step of having to go to linux first.
@bloody_albatross
@bloody_albatross Жыл бұрын
That dog-cat has an AI generated feel to me.
@oshanmodi
@oshanmodi Жыл бұрын
so cool
@tarshsingh4198
@tarshsingh4198 Жыл бұрын
43:32
@daniilsmirnov3153
@daniilsmirnov3153 Жыл бұрын
13:32
@wayneqwele8847
@wayneqwele8847 2 жыл бұрын
yo this is an amazing.
@alecmorgan3541
@alecmorgan3541 7 ай бұрын
You wouldn't download 600 images of bears!
@shoelessone
@shoelessone Жыл бұрын
First, thanks for the great lesson, I really appreciate it! Second, any Magento developers get excited when the Magento logo came up? kzbin.info/www/bejne/fGXXp4Bqi8dmd5I
10 ай бұрын
dog? pig? loaf of bread. SYSTEM ERROR
@vorandrew
@vorandrew Жыл бұрын
Thank you Jeremy, but we are programmers... 80% of time you spent on showing stuff we already know... git, jupiter etc... can you make 30 minute course with core concepts of fastai framework. What models when used etc...
@khuyendominh4032
@khuyendominh4032 2 жыл бұрын
it is a dog
@jimshtepa5423
@jimshtepa5423 Жыл бұрын
has anyone managed to solve 'NotImplementedError: The operator 'aten::_linalg_solve_ex.result' is not currently implemented for the MPS device. ' issue on macos m series?
@moritzsur997
@moritzsur997 11 ай бұрын
no but I have the same problem. I just did it in Google Colab.
Lesson 3: Practical Deep Learning for Coders 2022
1:30:25
Jeremy Howard
Рет қаралды 119 М.
Practical Deep Learning for Coders: Lesson 1
1:22:56
Jeremy Howard
Рет қаралды 381 М.
Sigma Kid Mistake #funny #sigma
00:17
CRAZY GREAPA
Рет қаралды 30 МЛН
How to treat Acne💉
00:31
ISSEI / いっせい
Рет қаралды 108 МЛН
Chain Game Strong ⛓️
00:21
Anwar Jibawi
Рет қаралды 41 МЛН
The End of Finetuning - with Jeremy Howard of Fast.ai
1:24:48
Latent Space
Рет қаралды 20 М.
Lesson 4: Practical Deep Learning for Coders 2022
1:34:37
Jeremy Howard
Рет қаралды 97 М.
Lesson "0": Practical Deep Learning for Coders (fast.ai)
55:31
Jeremy Howard
Рет қаралды 52 М.
Why Does Diffusion Work Better than Auto-Regression?
20:18
Algorithmic Simplicity
Рет қаралды 401 М.
Transformers (how LLMs work) explained visually | DL5
27:14
3Blue1Brown
Рет қаралды 4,1 МЛН
Generative AI in a Nutshell - how to survive and thrive in the age of AI
17:57
A Hackers' Guide to Language Models
1:31:13
Jeremy Howard
Рет қаралды 538 М.
MIT Introduction to Deep Learning | 6.S191
1:09:58
Alexander Amini
Рет қаралды 793 М.
Sigma Kid Mistake #funny #sigma
00:17
CRAZY GREAPA
Рет қаралды 30 МЛН