Загрузка видео...
Не удалось загрузить видео
【📢】 One thing coming with the next VTube Studio update is the "layer group" editor ✨ After creating one, a layer group can be used to bulk-set layer screen/multiply color overlays (and more!) 🌈🎨🖌️ It'll be on the VTS beta branch soon if you wanna try it out early ⏰✨
230,237 просмотров • 1 год назад •via X (Twitter)
Комментарии: 35
FINALLYYYYY YESSSSSSSSSSSSS
YYYYEEEESSSSSSSSSS FINALLY
THIS IS WHAT IVE BEEN WAITING FORRRR YESSS
As always with layer recoloring, keep in mind that some artists may not want their art to be modified in any way... Always check with your artist first!! 💬🎨 🎵 Music by KODOMOi 🎵
ME AND MY 60 HAIR LAYERS ARE CLAPPING SO HARD RIGHT NOW
Vtube studio has so many amazing updates lately 😭
I WAS LITERALLY THINKING HOW BADLY I WANTED THIS LIKE 2 DAYS AGO THANK YOU
this is huge thank you so much
YES THANK YOU! I'VE BEEN ASKING FOR THIS FOR HALF A YEAR NOW ;-;
Ohhhh we don’t have to make sliders for customizable models!
GOD BLESS YOU
THANK YOUUUUUUU!!!
YESSSS!!! Coloring each hair layer one at a time was so def time consuming, this is nice, me like.
GOATED! Absolutely crazy good idea!!
PLEASEEEEE THIS WOULD SPEED THINGS UP SO MUCH
Huge W!
🙏🙏🙏
@ppslayer_vt omg!!!
LETS FUCKING GOOOOOOO
THANK YOU FOREVERRRRRR
Omg yessss pleaseee!
IM SO HYPED FOR THIS!! when will the update be?
marry me oh my god
YESS IVE BEEN ASKING FOR THIS IN THE DISCORD!
game changer
You guys are really cooking!!! Thank you so much for always considering our needs and improving the software like this <333
Denchi, I thank you. All 700 layers of my hair thanks you.
Revolutionary 🙏
YOU'RE SAVING MY TWO BRAINCELLS, THANK YOU!!!
Oh my god
THANK YOU MY GOAT 🙏😭
Thank you Vtube Studio!!
wait this is so big oh my god,,,
THANK GOD
omg
![Backpropagation by hand ✍️ ~ 11 steps walkthrough below Backpropagation is the algorithm that actually trains a neural network, and it is where most people stop following along. It is not calculus you cannot do. It is matrix multiplication, working backward, one layer at a time. So I drew and calculated one entirely by hand. Goal: push the loss gradient back through a 3-layer network and land on a new value for every weight and bias. = 1. Given = A 3-layer perceptron, an input X, predictions Ypred = [0.5, 0.5, 0], and the truth Ytarget = [0, 1, 0]. = 2. Backprop gradient cells = Let us draw empty cells for every gradient we are about to compute. The shape of the answer comes first. = 3. Layer 3 softmax = We get dL/dz3 straight from Ypred minus Ytarget = [0.5, -0.5, 0]. No chain rule needed, and that shortcut is the whole reason softmax and cross-entropy are paired. = 4. Layer 3 weights and biases = Let us multiply dL/dz3 by [a2 | 1]. One multiplication gives the gradient for W3 and b3 together. = 5. Layer 2 activations = We multiply dL/dz3 by W3 to get dL/da2. The gradient moves back across a layer the same way the signal moved forward. = 6. Layer 2 ReLU = Let us pass it through the gate: keep the gradient where the activation was positive, zero it everywhere else. = 7. Layer 2 weights and biases = We multiply dL/dz2 by [a1 | 1]. The same figure as step 4, one layer up. = 8. Layer 1 activations = Let us multiply dL/dz2 by W2. = 9. Layer 1 ReLU = We apply the same gate again, now on a1. = 10. Layer 1 weights and biases = Let us multiply dL/dz1 by [x | 1], and every weight in the network now has a gradient. = 11. Update = We subtract, and the network has learned. In practice a learning rate scales this step. The gradients: dL/dz3 = [0.5, -0.5, 0] dL/da1 = [1, -2, 2, -1] dL/dz1 = [0, -2, 2, -1] The takeaway: matrix multiplication is all you need. Just like the forward pass, backpropagation is matrix multiplications end to end. You can do every one by hand, slowly and imperfectly, which is exactly why a GPU's ability to do them fast mattered so much to deep learning. 💾 Save this post!](https://image.24vids.com/tw-2079208495094677511/ext_tw_video_thumb/2079208483669315584/pu/img/dDD0x6lHYHuV1POQ.jpg)
