EmbeddingGemma2VideoConverter classkeras_hub.layers.EmbeddingGemma2VideoConverter(
patch_size=16, max_soft_tokens=70, pooling_kernel_size=3, max_frames=32, **kwargs
)
Video converter for EmbeddingGemma2.
This layer handles video inputs by sampling frames and delegating to
EmbeddingGemma2ImageConverter for frame-level processing.
Unlike Gemma4VideoConverter which always samples exactly num_frames,
this converter keeps all frames up to max_frames. If the video exceeds
max_frames, it uniformly samples max_frames frames.
This converter does not sample by frame rate. The Hugging Face processor
first samples one frame per second when the video has fps metadata. To
get the same frames, decode the video at 1 frame per second before calling
this layer.
from_preset methodEmbeddingGemma2VideoConverter.from_preset(preset, **kwargs)
Instantiate a keras_hub.layers.VideoConverter from a model preset.
A preset is a directory of configs, weights and other file assets used
to save and load a pre-trained model. The preset can be passed as
one of:
'gemma4_2b_it''kaggle://user/gemma4/keras/gemma4_2b_it''hf://google/gemma-4-2b-it''./gemma4_2b_it'You can run cls.presets.keys() to list all built-in presets available
on the class.
This constructor can be called in one of two ways. Either from the base
class like keras_hub.models.VideoConverter.from_preset(), or from a
model class like keras_hub.models.Gemma4VideoConverter.from_preset().
If calling from the base class, the subclass of the returning object
will be inferred from the config in the preset directory.
Arguments
Examples
# Load a video converter from a preset.
converter = keras_hub.layers.VideoConverter.from_preset(
"hf://google/gemma-4-2b-it"
)
| Preset | Parameters | Description |
|---|---|---|
| embedding_gemma2 | 744.37M | EmbeddingGemma 2: 744M-parameter, 24-layer multimodal embedding model built on Gemma 4. Embeds text, images, video and audio into a 768-dimensional space. |