keras / dfine_medium_obj2coco

This is a DFine model uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends. This model is related to a ObjectDetector task.

Model config:

• name: d_fine_backbone
• trainable: True
• backbone: {'module': 'keras_hub.src.models.hgnetv2.hgnetv2_backbone', 'class_name': 'HGNetV2Backbone', 'config': {'name': 'hg_net_v2_backbone', 'trainable': True, 'depths': [3, 4, 6, 3], 'embedding_size': 32, 'hidden_sizes': [192, 384, 768, 1536], 'stem_channels': [3, 24, 32], 'hidden_act': 'relu', 'use_learnable_affine_block': True, 'stackwise_stage_filters': [[32, 32, 96, 1, 4, 3], [96, 64, 384, 1, 4, 3], [384, 128, 768, 3, 4, 5], [768, 256, 1536, 1, 4, 5]], 'apply_downsample': [False, True, True, True], 'use_lightweight_conv_block': [False, False, True, True], 'image_shape': [None, None, 3], 'out_features': ['stage2', 'stage3', 'stage4'], 'data_format': 'channels_last'}, 'registered_name': 'keras_hub>HGNetV2Backbone'}
• decoder_in_channels: [256, 256, 256]
• encoder_hidden_dim: 256
• num_labels: 80
• num_denoising: 100
• learn_initial_query: False
• num_queries: 300
• anchor_image_size: [640, 640]
• feat_strides: [8, 16, 32]
• num_feature_levels: 3
• hidden_dim: 256
• encoder_in_channels: [384, 768, 1536]
• encode_proj_layers: [2]
• num_attention_heads: 8
• encoder_ffn_dim: 1024
• num_encoder_layers: 1
• hidden_expansion: 1.0
• depth_multiplier: 0.67
• eval_idx: -1
• box_noise_scale: 1.0
• label_noise_ratio: 0.5
• labels: None
• num_decoder_layers: 4
• decoder_attention_heads: 8
• decoder_ffn_dim: 1024
• decoder_method: default
• decoder_n_points: [3, 6, 3]
• lqe_hidden_dim: 64
• num_lqe_layers: 2
• seed: 0
• image_shape: [None, None, 3]
• data_format: channels_last
• out_features: ['stage2', 'stage3', 'stage4']

This model card has been generated automatically and should be completed by the model author. See Model Cards documentation for more information.