Pratique du Shadowing: PyTorch in 100 Seconds - Apprendre l'anglais à l'oral avec la vidéo

Choisissez un mode d'entraînement

Chaque mode ouvre une salle d'entraînement en plein écran.

33 phrases
Si les phrases sont trop courtes ou trop longues, cliquez sur Edit pour les ajuster.
1
PyTorch, an open-source deep learning framework used to build some of the world's most famous artificial intelligence products.
2
It was created at the Meta AI Research Lab in 2016, but is actually derived from the Lua-based Torch library that dates back to 2002.
3
Fundamentally, it's a library for programming with tensors, which are basically just multi-dimensional arrays that represent data and parameters in deep neural networks.
4
Sounds complicated, but its focus on usability will have you training machine learning models with just a few lines of Python.
5
In addition, it facilitates high-performance parallel computing on a GPU, thanks to NVIDIA's CUDA platform.
6
Developers love prototyping with it because it supports a dynamic computational graph, allowing models to be optimized at runtime.
7
It does this by constructing a directed acyclic graph consisting of functions
8
that keeps track of all the executed operations on the tensors, allowing you to change the shape, size, and operations after every iteration if needed.
9
PyTorch has been used to train models for computer vision AI like Tesla Autopilot, image generators like Stable Diffusion, and speech recognition models like OpenAI Whisper, just to name a few.
10
To get started, install PyTorch, and optionally CUDA, if you want to accelerate computing on your GPU.
11
Now import it into a Python file or notebook.
12
Like I mentioned, a tensor is similar to a multi-dimensional array.
13
Create a 2D array or matrix with Python, then use Torch to convert it into a tensor.
14
Now we can run all kinds of computations on it, like we might convert all these integers into random floating points.
15
We can also perform linear algebra by taking multiple tensors and multiplying them together.
16
What you came here to do though is build a deep neural network, like an image classifier.
17
To handle that, we can define a new class that inherits from the Neural Network Module class.
18
Inside the constructor, we can build it out layer by layer.
19
The flattened layer will take a multi-dimensional input, like an image, and convert it to one dimension.
20
From there, Sequential is used to create a container of layers that the data will flow through.
21
Each layer has multiple nodes, where each node is like its own mini statistical model.
22
As each data point flows through it, it'll try to guess the output, and gradually update a mapping of weights to determine the importance of a given variable.
23
Linear is a fully connected layer that takes the flattened 28x28 image and transforms it to an output of 512.
24
This layer is followed by a non-linear activation function.
25
When activated, it means that feature might be important and outputs the node.
26
Otherwise, it just outputs zero.
27
And finally, we finish with a fully connected layer that outputs the 10 labels the model is trying to predict.
28
With these pieces in place, the next step is to define a forward method that describes the flow of data.
29
And now instantiate the model to a GPU and pass it some input data.
30
This will automatically call its forward method for training and prediction.
31
Congratulations, you just built a neural network.
32
This has been PyTorch in 100 seconds.
33
Thanks for watching, and I will see you in the next one.

Télécharger l'application

Tout pour parler couramment

Prononciation IAChaque phrase notée
Phonétique (IPA)Maîtrisez chaque son
VocabulaireEnrichissez votre lexique
Jeu de vocabulaireApprenez en jouant
Scanner le QR
Scanner le QR
Download on theApp StoreGet it onGoogle Play

Même chaîne

The last real programmers are dying out...C1
1

The last real programmers are dying out...

Daily ConversationUniversity StudentsWorking Adults
PostgreSQL in 100 SecondsC1
1

PostgreSQL in 100 Seconds

Daily ConversationWorking Adults
Did Google just dethrone OpenAI and Anthropic?C1
2

Did Google just dethrone OpenAI and Anthropic?

Daily ConversationUniversity StudentsWorking Adults
A $6.3 billion open-weight model just got embarrassed by the French...C1
3

A $6.3 billion open-weight model just got embarrassed by the French...

Daily ConversationUniversity StudentsWorking Adults
Every app on Earth is now open source... whether it likes it or notC1
3

Every app on Earth is now open source... whether it likes it or not

Daily ConversationWorking Adults
OpenAI’s lead engineer was secretly a spy...C1
3

OpenAI’s lead engineer was secretly a spy...

Daily ConversationUniversity StudentsWorking Adults
Mind-bending new programming language for GPUs just dropped...C1
2

Mind-bending new programming language for GPUs just dropped...

Daily ConversationUniversity Students
Intel chips can’t possibly be this bad… 100% crash rate?B2
6

Intel chips can’t possibly be this bad… 100% crash rate?

American AccentBusiness EnglishUniversity StudentsWorking Adults
Godot in 100 SecondsC1
2

Godot in 100 Seconds

American AccentBusiness EnglishUniversity StudentsWorking Adults
Grok 4 pushes humanity closer to AGI… but there’s a problemB2
1

Grok 4 pushes humanity closer to AGI… but there’s a problem

American AccentBusiness EnglishUniversity StudentsWorking Adults
Array Map in 100 SecondsC1
3

Array Map in 100 Seconds

American AccentBusiness EnglishUniversity StudentsWorking Adults
Docker in 100 SecondsC1
30

Docker in 100 Seconds

American AccentBusiness EnglishUniversity StudentsWorking Adults
The most interesting "hack" in history...C1
7

The most interesting "hack" in history...

American AccentBusiness EnglishUniversity StudentsWorking Adults
OpenAI’s new browser feels familiar…B2
3

OpenAI’s new browser feels familiar…

American AccentBusiness EnglishUniversity StudentsWorking Adults
10 weird OSS projects you need right now...C1
12

10 weird OSS projects you need right now...

American AccentBusiness EnglishUniversity StudentsWorking Adults
Firefox and Tor hit with 9.8 critical level exploitB2
3

Firefox and Tor hit with 9.8 critical level exploit

American AccentBusiness EnglishUniversity StudentsWorking Adults
5 open source tools that replaced my $320/mo AI stack...B2
3

5 open source tools that replaced my $320/mo AI stack...

American AccentBusiness EnglishUniversity StudentsWorking Adults
C++ in 100 SecondsC1
2

C++ in 100 Seconds

American AccentBusiness EnglishUniversity StudentsWorking Adults
DHH has gone completely off the rails...C1
1

DHH has gone completely off the rails...

American AccentBusiness EnglishUniversity StudentsWorking Adults
Rust in 100 SecondsC1
2

Rust in 100 Seconds

American AccentBusiness EnglishUniversity StudentsWorking Adults
FOR YOU

Vidéo recommandée

Nvidia CUDA in 100 SecondsC1
16
37 phrases

Nvidia CUDA in 100 Seconds

American AccentBusiness EnglishUniversity StudentsWorking Adults
Transformers, the tech behind LLMs | Deep Learning Chapter 5C1
5
270 phrases

Transformers, the tech behind LLMs | Deep Learning Chapter 5

American AccentBusiness EnglishUniversity StudentsWorking Adults
My Secret Warehouse TourB2
3
163 phrases

My Secret Warehouse Tour

American AccentBusiness EnglishHigh School StudentsUniversity Students
You're Stuck In The Matrix, Here's How You EscapeC1
3
275 phrases

You're Stuck In The Matrix, Here's How You Escape

American AccentBusiness EnglishUniversity StudentsWorking Adults
mattpocock/skills: A complete AI Coding workflow, end-to-endC1
3
273 phrases

mattpocock/skills: A complete AI Coding workflow, end-to-end

British AccentBusiness EnglishUniversity StudentsWorking Adults
Google’s AI Course for Beginners (in 10 minutes)!C1
1
105 phrases

Google’s AI Course for Beginners (in 10 minutes)!

American AccentBusiness EnglishUniversity StudentsWorking Adults
Pixar in a Box: The Art of LightingB2
13
43 phrases

Pixar in a Box: The Art of Lighting

Business EnglishUniversity StudentsWorking Adults
Rapid Engineering With AIC1
1
12 phrases

Rapid Engineering With AI

Business EnglishUniversity StudentsWorking Adults
How I Would Learn Python FAST (if I could start over)C1
2
285 phrases

How I Would Learn Python FAST (if I could start over)

Business EnglishUniversity StudentsWorking Adults
Amazon Athena explained in 120 seconds💡C1
15
29 phrases

Amazon Athena explained in 120 seconds💡

Daily ConversationUniversity StudentsWorking Adults
Intro to Scrum in Under 10 MinutesC1
4
122 phrases

Intro to Scrum in Under 10 Minutes

Business EnglishUniversity StudentsWorking Adults

Vocabulaire et conseils d’expression pour cette leçon

Cette leçon d’expression orale de niveau C1 s’appuie sur la vidéo « PyTorch in 100 Seconds ». Les mots qui reviennent le plus souvent : layer, model, tensor, output, Pytorch. Cette vidéo contient 33 phrases et 540 mots à répéter en shadowing. La partie parlée dure 2:41. Le locuteur parle vite, environ 201 mots par minute : attendez-vous à des liaisons et à des sons réduits. Seuls 71 % des mots font partie des 3 000 mots les plus courants en anglais, le vocabulaire est donc exigeant.

Vocabulaire clé de cette vidéo

Les 15 mots les plus avancés de la vidéo, avec leur prononciation et leur sens :

MotPrononciationSens
neural adjectif/ˈnʊɹəl/neural
dimensional adjectif/daɪˈmɛn.ʃə.nəl/dimensionnel, de dimension
compute verbe/kəmˈpjuːt/computer, calculer
flatten verbe/ˈflæ.tən/aplatir
graph nom/ɡɹæf/graphique
acyclic adjectif/eɪˈsaɪklɪk/acyclique
classifier nom/ˈklæsɪfaɪɚ/classificateur
computation nom/ˌkɑmpjʊˈteɪʃn̩/calcul, comptage
instantiate verbe/ɪnˈstænʃieɪt/instancier
integer nom/ˈɪn.tɪ.d͡ʒə(ɹ)/entier, nombre entier
iteration nom/ˌɪt.əˈɹeɪ.ʃən/itération
multiply verbe/ˈmʌltɪplaɪ/multiplier
optimize verbe/ˈɑptɪmaɪz/agir en optimiste
usability nom/ˌjuːzəˈbɪlɪti/convivialité, ergonomie
derive verbe/dɪˈɹaɪv/tirer, trouver

La grammaire de cette vidéo

Les structures que le locuteur utilise le plus, avec les mots exacts de la vidéo :

StructureDans la vidéo
Voix passive be + participe passé — l’accent est mis sur ce qui arrive, pas sur qui le faitwas created · be optimized · is followed
Present perfect have/has + participe passé — une action passée qui compte encore maintenanthas been

Prononciation à surveiller

  • Les sons « sh » et « zh »: dimensional /daɪˈmɛn.ʃə.nəl/, computation /ˌkɑmpjʊˈteɪʃn̩/, instantiate /ɪnˈstænʃieɪt/, iteration /ˌɪt.əˈɹeɪ.ʃən/, optionally /ˈɑpʃənəli/
  • Mots longs — placez bien l’accent: dimensional /daɪˈmɛn.ʃə.nəl/, iteration /ˌɪt.əˈɹeɪ.ʃən/, optionally /ˈɑpʃənəli/, usability /ˌjuːzəˈbɪlɪti/, parameter /pəˈɹæm.ə.tɚ/

Les sons difficiles pour les francophones :

  • /tʃ/ et /dʒ/ — à ne pas adoucir en « ch » et « j »: integer /ˈɪn.tɪ.d͡ʒə(ɹ)/, algebra /ˈæl.d͡ʒɪ.bɹə/, generator /ˈdʒɛnəɹeɪtə(ɹ)/
  • /r/ anglais — langue recourbée, sans frotter la gorge: neural /ˈnʊɹəl/, graph /ɡɹæf/, integer /ˈɪn.tɪ.d͡ʒə(ɹ)/, iteration /ˌɪt.əˈɹeɪ.ʃən/, derive /dɪˈɹaɪv/

Comment s’entraîner avec cette vidéo

  1. Écoutez la vidéo en entier une fois sans parler et notez les mots que vous ne connaissez pas.
  2. Commencez à la vitesse 0,75×, répétez phrase par phrase, puis revenez à la vitesse normale quand cela devient facile.
  3. Enregistrez-vous et comparez avec l’original, en faisant attention à des mots comme neural, dimensional, compute.

Qu'est-ce que la technique du Shadowing ?

Le Shadowing est une technique d'apprentissage des langues fondée sur la science, développée à l'origine pour la formation des interprètes professionnels. Le principe est simple mais puissant : vous écoutez de l'anglais natif et le répétez immédiatement à voix haute — comme une ombre suivant le locuteur avec un décalage de 1 à 2 secondes. Les recherches montrent une amélioration significative de la précision de la prononciation, de l'intonation, du rythme, des liaisons, de la compréhension orale et de la fluidité.

Technique du shadowing : lire le guide complet étape par étape →