Transformers for software engineers

CLIP would be possible with any language and vision encoder.

It turns out that transformers were the most efficient encoder choices available at the time but most likely the approach would have given interesting results with a resnet and some sort of convolutional language encoder. In fact the paper has a resnet as one model for the vision side.

> While CLIP usually performs well on recognizing common objects, it struggles on more abstract or systematic tasks such as counting the number of objects in an image and on more complex tasks such as predicting how close the nearest car is in a photo. On these two datasets, zero-shot CLIP is only slightly better than random guessing. Zero-shot CLIP also struggles compared to task specific models on very fine-grained classification, such as telling the difference between car models, variants of aircraft, or flower species.

> CLIP also still has poor generalization to images not covered in its pre-training dataset. For instance, although CLIP learns a capable OCR system, when evaluated on handwritten digits from the MNIST dataset, zero-shot CLIP only achieves 88% accuracy, well below the 99.75% of humans on the dataset. Finally, we’ve observed that CLIP’s zero-shot classifiers can be sensitive to wording or phrasing and sometimes require trial and error “prompt engineering” to perform well.

I actually did a v0 writeup in Go, but I wanted a language that had a bit more powerful type system and more support for a fluent/functional style in some of the expressions. I was optimizing for what I know and felt was highly expressive; I've since gotten a bunch of feedback from people who are interested in the content but not comfortable reading Rust, so perhaps it wasn't the best choice.