Hugging Face's logo

keras
/
dfine_xlarge_obj365

KerasHub
Model card Files
xet
Community
dfine_xlarge_obj365
File size: 4,100 Bytes 
5ffee4f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
 
{
    "module": "keras_hub.src.models.d_fine.d_fine_backbone",
    "class_name": "DFineBackbone",
    "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": [
                    256,
                    512,
                    1024,
                    2048
                ],
                "stem_channels": [
                    3,
                    32,
                    64
                ],
                "hidden_act": "relu",
                "use_learnable_affine_block": false,
                "stackwise_stage_filters": [
                    [
                        64,
                        64,
                        128,
                        1,
                        6,
                        3
                    ],
                    [
                        128,
                        128,
                        512,
                        2,
                        6,
                        3
                    ],
                    [
                        512,
                        256,
                        1024,
                        5,
                        6,
                        5
                    ],
                    [
                        1024,
                        512,
                        2048,
                        2,
                        6,
                        5
                    ]
                ],
                "apply_downsample": [
                    false,
                    true,
                    true,
                    true
                ],
                "use_lightweight_conv_block": [
                    false,
                    false,
                    true,
                    true
                ],
                "image_shape": [
                    null,
                    null,
                    3
                ],
                "out_features": [
                    "stage2",
                    "stage3",
                    "stage4"
                ],
                "data_format": "channels_last"
            },
            "registered_name": "keras_hub>HGNetV2Backbone"
        },
        "decoder_in_channels": [
            384,
            384,
            384
        ],
        "encoder_hidden_dim": 384,
        "num_labels": 366,
        "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": [
            512,
            1024,
            2048
        ],
        "encode_proj_layers": [
            2
        ],
        "num_attention_heads": 8,
        "encoder_ffn_dim": 2048,
        "num_encoder_layers": 1,
        "hidden_expansion": 1.0,
        "depth_multiplier": 1.0,
        "eval_idx": -1,
        "box_noise_scale": 1.0,
        "label_noise_ratio": 0.5,
        "labels": null,
        "num_decoder_layers": 6,
        "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": [
            null,
            null,
            3
        ],
        "data_format": "channels_last",
        "out_features": [
            "stage2",
            "stage3",
            "stage4"
        ]
    },
    "registered_name": "keras_hub>DFineBackbone"
}