AI說書 - 從0開始 - 501 | CLIP 程式之推論部分

我想要一天分享一點「LLM從底層堆疊的技術」，並且每篇文章長度控制在三分鐘以內，讓大家不會壓力太大，但是又能夠每天成長一點。

with torch.no_grad():
	image_features = model.encode_image(image_input)
	text_features = model.encode_text(text_inputs)

進行推論之相似度計算：

image_features /= image_features.norm(dim = -1, keepdim = True)
text_features /= text_features.norm(dim = -1, keepdim = True)
similarity = (100.0 * image_features @ text_features.T).softmax(dim = -1)
values, indices = similarity[0].topk(5)

print("\nTop predictions:\n")
for value, index in zip(values, indices):
	print(f"{cifar100.classes[index]:>16s}: {100 * value.item():.2f}%")

結果為：