maxtext.multimodal package

Submodules

• maxtext.multimodal.processor module
  • preprocess_mm_data()
  • preprocess_image_for_training()
  • get_image_offsets()
  • reformat_prompt()
  • reformat_response()
  • prepare_text_for_image_fusion()
  • get_dummy_image_shape_for_init()
  • get_dummy_audio_shape_for_init()
  • get_bidirectional_mask_vision()
  • get_bidirectional_mask_audio()
• maxtext.multimodal.processor_gemma3 module
  • Gemma3PreprocessorOutput
    • Gemma3PreprocessorOutput.num_images
    • Gemma3PreprocessorOutput.pixel_values
    • Gemma3PreprocessorOutput.pixel_mask
  • preprocess_mm_data_gemma3()
  • get_image_offsets_gemma3()
  • reformat_prompt_gemma3()
  • insert_sequence()
  • add_extra_tokens_for_images_gemma3()
  • get_dummy_image_shape_for_init_gemma3()
• maxtext.multimodal.processor_gemma4 module
  • Gemma4PreprocessorOutput
    • Gemma4PreprocessorOutput.num_images
    • Gemma4PreprocessorOutput.pixel_values
    • Gemma4PreprocessorOutput.pixel_mask
    • Gemma4PreprocessorOutput.positions_xy
  • preprocess_mm_data_gemma4()
  • get_image_offsets_gemma4()
  • reformat_prompt_gemma4()
  • insert_sequence()
  • add_extra_tokens_for_images_gemma4()
  • get_dummy_image_shape_for_init_gemma4()
• maxtext.multimodal.processor_llama4 module
  • Llama4PreprocessorOutput
    • Llama4PreprocessorOutput.num_images
    • Llama4PreprocessorOutput.pixel_values
    • Llama4PreprocessorOutput.pixel_mask
    • Llama4PreprocessorOutput.aspect_ratios
  • get_factors()
  • find_supported_resolutions()
  • get_best_resolution()
  • pad_to_best_fit_jax()
  • pad_to_max_tiles()
  • split_to_tiles()
  • preprocess_mm_data_llama4()
  • get_num_tokens_for_this_image()
  • get_image_offsets_llama4()
  • reformat_prompt_llama4()
  • get_tokens_for_this_image()
  • add_extra_tokens_for_images_llama4()
  • get_dummy_image_shape_for_init_llama4()
• maxtext.multimodal.processor_qwen3_omni module
  • Qwen3OmniPreprocessorOutput
    • Qwen3OmniPreprocessorOutput.num_images
    • Qwen3OmniPreprocessorOutput.pixel_values
    • Qwen3OmniPreprocessorOutput.pixel_grid_thw
    • Qwen3OmniPreprocessorOutput.num_videos
    • Qwen3OmniPreprocessorOutput.video_values
    • Qwen3OmniPreprocessorOutput.video_grid_thw
    • Qwen3OmniPreprocessorOutput.video_second_per_grid
    • Qwen3OmniPreprocessorOutput.num_audios
    • Qwen3OmniPreprocessorOutput.audio_values
    • Qwen3OmniPreprocessorOutput.audio_mask
    • Qwen3OmniPreprocessorOutput.audio_lengths
  • smart_resize()
  • pre_process_qwen3_image()
  • calculate_video_frame_range()
  • smart_nframes()
  • preprocess_video()
  • pre_process_audio_qwen3_omni()
  • preprocess_mm_data_qwen3_omni()
  • add_extra_tokens_for_qwen3_omni()
  • get_dummy_image_shape_for_init_qwen3_omni()
  • get_dummy_audio_shape_for_init_qwen3_omni()
  • get_llm_pos_ids_for_vision()
  • get_chunked_index()
  • get_rope_index()
  • reformat_prompt_qwen3_omni()
  • get_mm_offsets_qwen3_omni()
• maxtext.multimodal.utils module
  • PreprocessorOutput
    • PreprocessorOutput.pixel_values
    • PreprocessorOutput.pixel_mask
    • PreprocessorOutput.aspect_ratios
    • PreprocessorOutput.num_images
    • PreprocessorOutput.audio_values
    • PreprocessorOutput.audio_mask
  • convert_to_RGB()
  • load_image_from_path()
  • normalize_images()
  • merge_mm_embeddings()
  • amplitude_to_db()
  • power_to_db()
  • spectrogram()
  • hertz_to_mel()
  • mel_to_hertz()
  • mel_filter_bank()
  • window_function()
  • load_audio()