SCET Berkeley

SCET Berkeley

Welcome to the official UC Berkeley SCET KZread Channel!
scet.berkeley.edu/

Пікірлер

  • @upsidedownChad
    @upsidedownChad20 күн бұрын

    First

  • @Bigtakes
    @Bigtakes2 ай бұрын

    Hate this guy ong

  • @ahmednserel_din2786
    @ahmednserel_din27862 ай бұрын

    can you share slides

  • @noelyong6843
    @noelyong68434 ай бұрын

    Where is Mr Lam🤨

  • @theuncoverfacts582
    @theuncoverfacts5824 ай бұрын

    😊😊 1:07:14 1:07:16 1:07:17 1:07:17

  • @science.20246
    @science.202464 ай бұрын

    bad quakity audio

  • @pacifiquebusiness
    @pacifiquebusiness5 ай бұрын

    So interesting

  • @hedleyfurio
    @hedleyfurio5 ай бұрын

    What a super flight plan for any young person wanting to add value - be humble , work with teams of competent people , if you see a process defect jump in and own it , and solve it

  • @wandersquares
    @wandersquares5 ай бұрын

    This might be the most insightful video on all of youtube😉 Hope you enjoy this hastily drawn peek into the future!

  • @nicholask1039
    @nicholask10396 ай бұрын

    *promo sm* ⭐

  • @BillionMoonshots
    @BillionMoonshots7 ай бұрын

    great work

  • @andrewashmore8000
    @andrewashmore80008 ай бұрын

    One clever smart answer by Lars , allowed his career to continue. His answer was " 3 days " probably saved his career. Cool story.

  • @andrewashmore8000
    @andrewashmore80008 ай бұрын

    The story from Lars about 3/4 way in about automating wheel alignment in the production line is a great example of a engineer with conviction acing there job. Story or answer was really impressive.

  • @andrewashmore8000
    @andrewashmore80008 ай бұрын

    Standout impression for me about Lars is deep integrity.

  • @andrewashmore8000
    @andrewashmore80008 ай бұрын

    Super interesting formation story on outlook from a very young age. Super committed from a young age to make cars. A bit like Adrian Newey , Super committed to building fast cars so knew he needed to study aerodynamics. Lars knew he needed to study manufacturing engineering , cos he knew he wanted to build cars.

  • @breaktherules6035
    @breaktherules60358 ай бұрын

    EXCELLENT insights! THANK YOU so much for your generosity and for sharing!

  • @dorasnaranjit82
    @dorasnaranjit829 ай бұрын

    A part from the IoU (not UoI) these explanations are great! Thank you :-)

  • @luzdominguezdominguez9700
    @luzdominguezdominguez970010 ай бұрын

    Magnífica y clara, precisa y preciosa explicación, incluso para una "mujer de Letras.

  • @fatanehsadeghi5723
    @fatanehsadeghi572310 ай бұрын

    explanation is really great. thank you for fluently and simple explanation.just the audio wasn't great as much. thank you so much

  • @rodghani6692
    @rodghani6692 Жыл бұрын

    Super good review. THANK YOU

  • @charliehunt1470
    @charliehunt1470 Жыл бұрын

    The Y Scraper is genius🤣

  • @neotodsoltani5902
    @neotodsoltani5902 Жыл бұрын

    why the instructor says UoI thought the whole course?? isn't it IoU? (as the formula shows, Intersection over Union)

  • @9891676610
    @9891676610 Жыл бұрын

    At 11.08 output should be (S, S, No of Bounding Box x (5 + No of Total Classes)) and not (S, S, (5X no of bounding boxes + No of Classes))

  • @zukofire6424
    @zukofire6424 Жыл бұрын

    no you're wrong, read the paper is says that for each cell you get B*5+C values as output

  • @tweaze9002
    @tweaze9002 Жыл бұрын

    Very good vid

  • @adamkasprowicz
    @adamkasprowicz Жыл бұрын

    "you can't be too smart" :D that's the greatest advice for me so far. I'm kinda old, I know too much. It's better to be in your 20s and still naive. Too much knowledge can paralyse you.

  • @shirinzu-pe7hw
    @shirinzu-pe7hw Жыл бұрын

    where can I find this code ?

  • @zachhoy
    @zachhoy Жыл бұрын

    Alvin, positive and dedicated as always, very glad the world has you working on solutions to the VR problem (i.e. there's not enough VR adoption yet)! Thanks for sharing so much with us, very insightful. My condolences for your father.

  • @ClarkPotter
    @ClarkPotter Жыл бұрын

    Great presentation and product. I'm an investor of yours on Republic. I'm no startup expert like your audience, but I have a good feeling about you. Keep up the great work.

  • @salmakhaled2397
    @salmakhaled2397 Жыл бұрын

    Thank you 🙏🏻

  • @eduardomusic8560
    @eduardomusic8560 Жыл бұрын

    I liked this video and interview! Great quality in audio, congratulations for this work. Greetings from Sonora, México.

  • @NadidLinchestein
    @NadidLinchestein Жыл бұрын

    Great interview.

  • @ataucei
    @ataucei Жыл бұрын

    This was a really good interview! It was really nice to hear their experience talking about how they found out what they wanted to do in their career

  • @ChosenByGod1111
    @ChosenByGod1111 Жыл бұрын

    How do you trust people to write down everything they think you can improve on without telling them the idea, or does this happen after the patent is paid for? I really want peoples opinion but worried they would steal or tell my idea to others before patent is paid for.

  • @samc6368
    @samc6368 Жыл бұрын

    at 11:00 isnt it better label with S x S X (5 (B+C))

  • @samc6368
    @samc6368 Жыл бұрын

    Excellent overview, thanks, one more clarification at 15:00 is it UoI or IoU ?

  • @roberto759
    @roberto759 Жыл бұрын

    🅿🆁🅾🅼🅾🆂🅼

  • @pathikghugare
    @pathikghugare Жыл бұрын

    Such a clear explaination ! but I want to make sure that what I understood is correct so here's my understanding and doubts: 1. we divide image into S x S grid 2. In each grid, we try to predict probability that the bounding box(which we are predicting from our model) contains an object or not 3. With 2, we try to predict the coordinates of the bounding box and the respctive conditional probabilities of classes 4. Step 2,3 is I suppose the output of the model w.r.t each grid but I am still confused that if B is no of bounding boxes which we want to predict then why do we need 5B+C vectors?

  • @marcospiotto9755
    @marcospiotto97556 ай бұрын

    i think 5B+C is the lenght of the y vector, so if B = 2 then the y vector needs 5 elements for p,x,y,h,w of the first bounding box, then p,x,y,h,w for the second bounding box and lastly C elements for the probability of each class, 5*2 + C

  • @baconlatte
    @baconlatte Жыл бұрын

    Globalist psychopath wants to save humanity by replacing health-promoting, nutrient-dense animal foods with... genetically-modified, heavily-processed, disease-promoting, malnourishing, fake-food excrement. At least it’s “plant-based”!

  • @charleenlozi4775
    @charleenlozi4775 Жыл бұрын

    12:20 I thought yolo has no pooling layer?

  • @312pato
    @312pato Жыл бұрын

    U forgot that u know satoshi ….. mr pool

  • @312pato
    @312pato Жыл бұрын

    Hex Richard heart ❤️

  • @s2ms10ik5
    @s2ms10ik5 Жыл бұрын

    thank god for the subtitles

  • @eliaslouw6400
    @eliaslouw6400 Жыл бұрын

    Hi michael thank you for a excellent leaning experience

  • @miko1335
    @miko1335 Жыл бұрын

    Amazing teacher ! Thank you

  • @nmaajidkhan
    @nmaajidkhan Жыл бұрын

    Pro Tip before you begin the video: Use subtitles to relate with the audio

  • @umarmuhammadi429
    @umarmuhammadi4292 жыл бұрын

    Nice video 👍 Can you share the slides

  • @fukui307
    @fukui3072 жыл бұрын

    should it be 5(B+C)?

  • @lakshaydulani
    @lakshaydulani2 жыл бұрын

    really nice video! do we call the Bounding boxes at 5:29 as "Anchor boxes"?

  • @GARUDA1992152
    @GARUDA1992152 Жыл бұрын

    Anchor boxes are nothing but initial guesses of the bounding boxes, calculated using the aspect ratios and sizes of bounding boxes in the training dataset

  • @varunkoshal15
    @varunkoshal152 жыл бұрын

    Berkley is incredible

  • @kushagrakirtiman3292
    @kushagrakirtiman32923 ай бұрын

    chup