diff --git a/README.md b/README.md index 1c02fea..4367176 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,7 @@ This operator extracts features for image or text with [CLIP](https://arxiv.org/ ## Code Example -Load an image from path './dog.jpg' to generate an image embedding. +Load an image from path './teddy.jpg' to generate an image embedding. Read the text 'a dog' to generate an text embedding. *Write the pipeline in simplified style*: @@ -34,7 +34,8 @@ towhee.dc(["a dog"]) \ .towhee.clip(name='ViT-B/32', modality='text') \ .show() ``` -result1 +result1 +result2 *Write a same pipeline with explicit inputs/outputs name specifications:* @@ -53,7 +54,7 @@ towhee.dc(["a dog"]) \ .select['data', 'vec']() \ .show() ``` -result2 +result1
@@ -82,8 +83,7 @@ Create the operator via the following factory method ## Interface -An image embedding operator takes a [towhee image](link/to/towhee/image/api/doc) as input. -It uses the pre-trained model specified by model name to generate an image embedding in ndarray. +An image-text embedding operator takes a [towhee image](link/to/towhee/image/api/doc) or string as input and generate an image embedding in ndarray. **Parameters:** diff --git a/tabular1.png b/tabular1.png new file mode 100644 index 0000000..fb3e917 Binary files /dev/null and b/tabular1.png differ diff --git a/vec1.png b/vec1.png new file mode 100644 index 0000000..5f60a86 Binary files /dev/null and b/vec1.png differ diff --git a/vec2.png b/vec2.png new file mode 100644 index 0000000..74d8257 Binary files /dev/null and b/vec2.png differ