Pinned
Check out some of our learnings and how workflows progressed when it comes to computer vision in the wild!
Podcast with @Trust_in_soda
Alexander Hirner
@cybertreiber
Vienna, Austria
Joined January 2013
- Typical problems of rust devs: * ext4 driver is only twice as fast, what to do? * ES2.0 implementation passes all conformance tests - how to remove last two .clone()? * Found undefined behavior in the DNS spec after modelling it with TypeStates
- I'd be very interested in hearing @ezyang opinion on the best serialization steps without wielding python for candle: github.com/huggingface/ca… (and candle in general) 🔥
- A good tokenizer is all you need.this is wild — kNN using a gzip-based distance metric outperforms BERT and other neural methods for OOD sentence classification intuition: 2 texts similar if cat-ing one to the other barely increases gzip size no training, no tuning, no params — this is the entire algorithm:
![for (x1, _) in test_set:
Cx1 = len(gzip.compress(x1.encode()))
distance_from_x1 = []
for (x2, _) in training_set:
Cx2 = len(gzip.compress(x2. encode())
x1x2 = " ".join([x1, x2])
Cx1x2 = len(gzip.compress(x1x2. encode())
ncd = (Cx1x2 - min(Cx1,Cx2)) / max(Cx1, Cx2)
distance_from_x1.append(ncd)
sorted_idx = np.argsort(np.array(distance_from_x1))
top_k_class = training_set[sorted_idx[:k], 1]
predict_class = max(set(top_k_class), key=top_k_class.count)](https://pbs.twimg.com/media/F05HxqsWwAAHRCI?format=webp&name=medium)
