View Source Bumblebee.Vision.ResNet (Bumblebee v0.5.3)
ResNet model family.
Architectures
:base
- plain ResNet without any head on top:for_image_classification
- ResNet with a classification head. The head consists of a single dense layer on top of the pooled features and it returns logits corresponding to possible classes
Inputs
"pixel_values"
- {batch_size, height, width, num_channels}Featurized image pixel values (224x224).
Configuration
:num_channels
- the number of channels in the input. Defaults to3
:embedding_size
- the dimensionality of the embedding layer. Defaults to64
:hidden_sizes
- the dimensionality of hidden layers at each stage. Defaults to[256, 512, 1024, 2048]
:depths
- the depth (number of residual blocks) at each stage. Defaults to[3, 4, 6, 3]
:residual_block_type
- the residual block to use, either:basic
(used for smaller models, like ResNet-18 or ResNet-34) or:bottleneck
(used for larger models like ResNet-50 and above) . Defaults to:bottleneck
:activation
- the activation function. Defaults to:relu
:downsample_in_first_stage
- whether the first stage should downsample the inputs using a stride of 2. Defaults tofalse
:output_hidden_states
- whether the model should return all hidden states. Defaults tofalse
:num_labels
- the number of labels to use in the last layer for the classification task. Defaults to2
:id_to_label
- a map from class index to label. Defaults to%{}