This is a HGNetV2 model uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
This model is related to a ImageClassifier task.
Model config:
- name: hg_net_v2_backbone_1
- trainable: True
- depths: [2, 3, 6, 3]
- embedding_size: 96
- hidden_sizes: [192, 512, 1024, 2048]
- stem_channels: [3, 48, 96]
- hidden_act: relu
- use_learnable_affine_block: False
- stackwise_stage_filters: [[96, 96, 192, 2, 6, 3], [192, 192, 512, 3, 6, 3], [512, 384, 1024, 6, 6, 5], [1024, 768, 2048, 3, 6, 5]]
- apply_downsample: [False, True, True, True]
- use_lightweight_conv_block: [False, False, True, True]
- image_shape: [224, 224, 3]
- out_features: ['stem', 'stage1', 'stage2', 'stage3', 'stage4']
- data_format: channels_last
This model card has been generated automatically and should be completed by the model author. See Model Cards documentation for more information.
- Downloads last month
- 11
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support