正在加载视频...

视频加载失败

We outgrew static gradients. So we rebuilt everything. Grainient V2 is live. What started as a gradient library is now something else entirely: • Animated gradient videos • Real-time gradient shader tool • Textured, mesh, and AI-crafted backgrounds From downloading assets → to actually create and control them. So,...

127,817 次观看 • 3 个月前 •via X (Twitter)

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

CSS Trick! 🤙 You can create gradient borders on translucent elements using mask-clip and mask-composite with a pseudo-element 🔥 .gradient-border::after { mask-clip: padding-box, border-box; mask-composite: intersect; mask: linear-gradient(transparent, transparent), linear-gradient(white, white); } It's the same "Transparent border trick" from before. But, now you apply it to a pseudo-element 😎 The trick is to create a pseudo-element with a gradient background and then mask it so we only see the part we want, the border ✨ mask-clip defines the area affected by a mask. Similar to how you can define background-size. Using padding-box and border-box constrains the two masks. mask-composite is the magic part ✨ It defines a compositing operation for stacked mask layers. Using intersect means that the parts that overlap get replaced. And this seems to work in all browsers 🙌 As for the rest of the styles... – Make sure you set pointer-events: none on the pseudo-element – Make sure it fills the parent element. You can use position: absolute and inset: 0 – Make sure the background fills the space including the border-width. You can use calc to achieve that: --bg-size: calc(100% + (2px * var(--border))); background: var(--gradient) center center / var(--bg-size) var(--bg-size); That's it! 🚀 Gradient borders on translucent elements. You can set all the backdrop-filter: blur() you like! 😅 CodePen.IO link below! 👇

jhey ʕ•ᴥ•ʔ

269,847 次观看 • 2 年前

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!

Tom Yeh

952,815 次观看 • 12 天前