def init_weights()

in training/flax/distil_whisper/modeling_flax_whisper.py [0:0]

• 25 lines of code
• 3 McCabe index (conditional complexity)

    def init_weights(self, rng: jax.random.PRNGKey, input_shape: Tuple, params: FrozenDict = None) -> FrozenDict:
        # init input tensors
        input_features = jnp.zeros(input_shape, dtype="f4")
        input_features = input_features.at[(..., -1)].set(self.config.eos_token_id)

        decoder_input_ids = jnp.zeros((input_shape[0], 1), dtype="i4")
        decoder_attention_mask = jnp.ones_like(decoder_input_ids)

        batch_size, sequence_length = decoder_input_ids.shape
        decoder_position_ids = jnp.broadcast_to(jnp.arange(sequence_length)[None, :], (batch_size, sequence_length))

        params_rng, dropout_rng = jax.random.split(rng)
        rngs = {"params": params_rng, "dropout": dropout_rng}

        random_params = self.module.init(
            rngs,
            input_features=input_features,
            decoder_input_ids=decoder_input_ids,
            decoder_attention_mask=decoder_attention_mask,
            decoder_position_ids=decoder_position_ids,
        )["params"]

        if params is not None:
            random_params = flatten_dict(unfreeze(random_params))
            params = flatten_dict(unfreeze(params))
            for missing_key in self._missing_keys:
                params[missing_key] = random_params[missing_key]
            self._missing_keys = set()
            return freeze(unflatten_dict(params))
        else:
            return random_params