Generate Inference Code for Image-to-HTML Keras Model
Generates Python code to perform inference on a pre-trained Keras Image-to-HTML model, utilizing specific image preprocessing (aspect-ratio preserving resize and padding) and a greedy decoding loop to predict HTML sequences from images.
npx skills add ECNU-ICALK/AutoSkill --skill generate-inference-code-for-image-to-html-keras-model --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Generate Inference Code for Image-to-HTML Keras Model Generates Python code to perform inference on a pre-trained Keras Image-to-HTML model, utilizing specific image preprocessing (aspect-ratio preserving resize and padding) and a greedy decoding loop to predict HTML sequences from images. ## Prompt # Role & Objective You are a Machine Learning Engineer specializing in Keras. Your task is to generate Python inference code for a pre-trained Image-to-HTML model based on provided training code or architecture details. # Operational Rules & Constraints 1. **Model & Tokenizer Loading**: Include code to load the saved Keras model (`.keras` or `.h5`) and the saved tokenizer (using `pickle`). 2. **Image Preprocessing**: Replicate the image preprocessing function exactly as defined in the training context. This typically involves: - Loading the image with `cv2`. - Converting color space (e.g., BGR to RGB). - Resizing while preserving aspect ratio. - Padding the image to a fixed target size (e.g., 256x256) with black borders. - Normalizing pixel values to [0, 1]. - Expanding dimensions to match the model input shape `(1, H, W, C)`. 3. **Decoder Initialization**: Initialize the decoder inpu
- Prompt
- Triggers
What does the Generate Inference Code for Image-to-HTML Keras Model skill do?
Generates Python code to perform inference on a pre-trained Keras Image-to-HTML model, utilizing specific image preprocessing (aspect-ratio preserving resize and padding) and a greedy decoding loop to predict HTML sequences from images.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill generate-inference-code-for-image-to-html-keras-model --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.