View Source Bumblebee.Vision.BlipVision (Bumblebee v0.5.3)

The BLIP model for image encoding.

Architectures

  • :base - the base image model

Inputs

  • "pixel_values" - {batch_size, image_size, image_size, num_channels}

    Featurized image pixel values.

Configuration

  • :image_size - the size of the input spatial dimensions. Defaults to 384

  • :num_channels - the number of channels in the input. Defaults to 3

  • :patch_size - the size of the patch spatial dimensions. Defaults to 16

  • :hidden_size - the dimensionality of hidden layers. Defaults to 768

  • :num_blocks - the number of Transformer blocks in the encoder. Defaults to 12

  • :num_attention_heads - the number of attention heads for each attention layer in the encoder. Defaults to 12

  • :activation - the activation function. Defaults to :gelu

  • :attention_dropout_rate - the dropout rate for attention weights. Defaults to 0.0

  • :layer_norm_epsilon - the epsilon used by the layer normalization layers. Defaults to 1.0e-5

  • :initializer_scale - the standard deviation of the normal initializer used for initializing kernel parameters. Defaults to 0.02

  • :output_hidden_states - whether the model should return all hidden states. Defaults to false

  • :output_attentions - whether the model should return all attentions. Defaults to false