Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

the essentials pt.2 is here Buffbunny Collection 😍 Here is the direct link to shop! Outfits I’m wearing in the reel: Corset bodysuit in baked blue (size m) Airbrush pocket legging in lipstick red (size m) Phantom hip jacket in lipstick red (size m) Aurora tank in onyx black...

13,470 Aufrufe • vor 7 Monaten •via X (Twitter)

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

MLP in PyTorch by hand ✍️ ~ 7 steps walkthrough below Goal: fill in every blank in the PyTorch code to build a multi-layer perceptron. 1. Given Let us start with a code template on the left and the network it is supposed to build on the right. Every blank in the code can be worked out from the picture. 2. Linear layer We count: 3 features in, 4 features out. So the weight matrix is 4 by 3. There is an extra column for the biases, which means bias = T. 3. ReLU Let us apply the activation. ReLU crosses out the negatives, so -1 becomes 0. 4. Linear layer The input size is 4, because that is what the previous layer put out. The output size is 2. A 2 by 4 weight matrix, and this time no extra column, so bias = F. 5. ReLU We cross out the negatives again. 6. Linear layer Two features in, five out. A 5 by 2 weight matrix, with a bias column, so bias = T. 7. Sigmoid Let us finish. Sigmoid squashes the raw scores (3, 0, -2, 5, -5) into probabilities between 0 and 1. You have just implemented a three-layer deep neural network by hand. ✍️ == Story == Three years ago I gave this exercise to my students, to connect the code to the math. They found it odd. Every other AI course they were taking lived inside a Jupyter notebook, and here I was handing out paper. Three years later, my colleagues are the ones rushing to move their materials to paper. The exercise has not changed. Paper still asks the one thing a notebook lets you skip: do you actually understand what the code is doing? If you can tell me why the weight matrix is 4 by 3, and why bias is F on the second layer, you understand nn.Linear better than someone who has been copy-pasting it for a year. 💾 Save this post! #AIbyHand #PyTorch #DeepLearning

Tom Yeh

13,318 Aufrufe • vor 2 Monaten

🚨⚠️ M&S RE-ORG!! ⚠️🚨 ** MEN IN MY LOCAL M&S NOW HAVE TO WALK THROUGH THE LINGERIE SECTION TO GET TO MENSWEAR ** Ok, so I checked in again today, and it’s even worse. I don’t think this is fair on most men (decent men) either. To be clear, I raised the issue of sex discrimination with the store manager and M&S HQ back in March 2026. Nothing has changed. Except one thing HAS changed. Very recently. In their infinite wisdom, M&S has now jumbled the Lingerie section pretty much in with the Menswear. 2 videos of my (1) walk round, cut up as I don’t have the tools to obscure faces and a large fella walked straight between me and the lingerie midway through, looking straight at camera. You can also see how isolated the Lingerie fitting rooms are here (also cut at end as a man was sitting on a seat inside the entrance to the Lingerie fitting rooms). There was a staff member at the fitting rooms today, but it’s Saturday, peak time. There are not always staff members present, more often than not in my experience. No till points on this floor either. They took those out last year/year before (they were in the Menswear section adjacent to the Men’s fitting rooms). Before this month (it’s very recent), the Lingerie and Menswear sections were divided by the escalators and men did not have to walk through the Lingerie section to get to Menswear. It’s like a male knicker fetishist is in charge of store layout at M&S HQ. I can’t work out otherwise why they would think this is a good idea! 😬 #BringBackSafeguarding #BringBackCommonSense Sex Matters™ Maya Forstater 💚🤍💜#Your Mums a TERF 🦕Restore UK Bring Back Safeguarding Jean Hatchet Please feel free to tag anyone else who might wanna know.

Alicia

355,118 Aufrufe • vor 3 Monaten

OFFICIAL: DG-2 TESSIE UPGRADE GUIDE: 1. Using abomination beams, destroy one of the purple plant-like things in the fog. It will drop a ton of salvage and an item. 2. Grab spore jar from the Blackwater kitchen and put it on the dead horse infront of the Vandorn Farm. Wait three rounds. Grab the mushroom from its corpse. 3. Use the saw trap on a Ravager to get its eyes. 4. Kill a bear with the abomination beams to get its limb. 5. There's a mirror that damages you in Ashwood. Use a wisp to activate it then use necrofluid gauntlet to smash it to get powder 6. In the Vandorn Farm, use a tomahawk on a hanging corpses foot to get the foot. 6. Interact with the powder on the table in Yuri's Lab in the Cosmodrome. It will start smoking. There will also be a cipher on the wall. -When it turns grey, that means you can choose an order to put the ingredients in. When it's black, that means you are out of attempts. 7. Decode the cipher using this key (first two "letters" of each code): CL = eye L(upside down L) = tentacle C J = foot 8. Click on each ingredient in order (top to bottom) and then interact with the flask to give your blood. A lockdown sequence will start. 9. You will now need to grab three glowing keys using the WW and bring them to the floating red pyramid thing in the Rabbit Alley in ashwood. Note: the keys can be incredibly hard to spot sometimes. Spawns: Ship (glowing green key): -One is on the top of the ship in a window -One is in the corner of a blue shipping container -One is underneath on one side of the ship between two barrels Crashed Rocket (glowing yellow key): -In the crashed pylon -To the right of a car crash on the cliffside (near the Ashwood gate) -On the corner ontop of one of the array buildings Orda Graveyard (glowing red key): -In the mouth of the top T-Rex -Back of the skull of the bottom T-Rex -Next to the back of a Janus Towers car Once all keys are in, a cutscene will play and the DG2 will spawn. Last three images are examples of key locations

COD: Zombies News

441,629 Aufrufe • vor 10 Monaten

Vector Database by Hand ✍️ Vector databases are revolutionizing how we search and analyze complex data. They have become the backbone of Retrieval Augmented Generation (#RAG). How do vector databases work? [1] Given ↳ A dataset of three sentences, each has 3 words (or tokens) ↳ In practice, a dataset may contain millions or billions of sentences. The max number of tokens may be tens of thousands (e.g., 32,768 mistral-7b). Process "how are you" [2] 🟨 Word Embeddings ↳ For each word, look up corresponding word embedding vector from a table of 22 vectors, where 22 is the vocabulary size. ↳ In practice, the vocabulary size can be tens of thousands. The word embedding dimensions are in the thousands (e.g., 1024, 4096) [3] 🟩 Encoding ↳ Feed the sequence of word embeddings to an encoder to obtain a sequence of feature vectors, one per word. ↳ Here, the encoder is a simple one layer perceptron (linear layer + ReLU) ↳ In practice, the encoder is a transformer or one of its many variants. [4] 🟩 Mean Pooling ↳ Merge the sequence of feature vectors into a single vector using "mean pooling" which is to average across the columns. ↳ The result is a single vector. We often call it "text embeddings" or "sentence embeddings." ↳ Other pooling techniques are possible, such as CLS. But mean pooling is the most common. [5] 🟦 Indexing ↳ Reduce the dimensions of the text embedding vector by a projection matrix. The reduction rate is 50% (4->2). ↳ In practice, the values in this projection matrix is much more random. ↳ The purpose is similar to that of hashing, which is to obtain a short representation to allow faster comparison and retrieval. ↳ The resulting dimension-reduced index vector is saved in the vector storage. [6] Process "who are you" ↳ Repeat [2]-[5] [7] Process "who am I" ↳ Repeat [2]-[5] Now we have indexed our dataset in the vector database. [8] 🟥 Query: "am I you" ↳ Repeat [2]-[5] ↳ The result is a 2-d query vector. [9] 🟥 Dot Products ↳ Take dot product between the query vector and database vectors. They are all 2-d. ↳ The purpose is to use dot product to estimate similarity. ↳ By transposing the query vector, this step becomes a matrix multiplication. [10] 🟥 Nearest Neighbor ↳ Find the largest dot product by linear scan. ↳ The sentence with the highest dot product is "who am I" ↳ In practice, because scanning billions of vectors is slow, we use an Approximate Nearest Neighbor (ANN) algorithm like the Hierarchical Navigable Small Worlds (HNSW).

Tom Yeh

192,022 Aufrufe • vor 2 Jahren