Upload config.json with huggingface_hub
Browse files- config.json +75 -0
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/conditional-detr-resnet-50",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "relu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"ConditionalDetrForObjectDetection"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"auxiliary_loss": false,
|
| 10 |
+
"backbone": "resnet50",
|
| 11 |
+
"backbone_config": null,
|
| 12 |
+
"backbone_kwargs": {
|
| 13 |
+
"in_chans": 3,
|
| 14 |
+
"out_indices": [
|
| 15 |
+
1,
|
| 16 |
+
2,
|
| 17 |
+
3,
|
| 18 |
+
4
|
| 19 |
+
]
|
| 20 |
+
},
|
| 21 |
+
"bbox_cost": 5,
|
| 22 |
+
"bbox_loss_coefficient": 5,
|
| 23 |
+
"class_cost": 2,
|
| 24 |
+
"cls_loss_coefficient": 2,
|
| 25 |
+
"d_model": 256,
|
| 26 |
+
"decoder_attention_heads": 8,
|
| 27 |
+
"decoder_ffn_dim": 2048,
|
| 28 |
+
"decoder_layerdrop": 0.0,
|
| 29 |
+
"decoder_layers": 6,
|
| 30 |
+
"dice_loss_coefficient": 1,
|
| 31 |
+
"dilation": false,
|
| 32 |
+
"dropout": 0.1,
|
| 33 |
+
"encoder_attention_heads": 8,
|
| 34 |
+
"encoder_ffn_dim": 2048,
|
| 35 |
+
"encoder_layerdrop": 0.0,
|
| 36 |
+
"encoder_layers": 6,
|
| 37 |
+
"focal_alpha": 0.25,
|
| 38 |
+
"giou_cost": 2,
|
| 39 |
+
"giou_loss_coefficient": 2,
|
| 40 |
+
"id2label": {
|
| 41 |
+
"0": "bag",
|
| 42 |
+
"1": "bottom",
|
| 43 |
+
"2": "dress",
|
| 44 |
+
"3": "hat",
|
| 45 |
+
"4": "outer",
|
| 46 |
+
"5": "shoes",
|
| 47 |
+
"6": "top",
|
| 48 |
+
"7": "accessory"
|
| 49 |
+
},
|
| 50 |
+
"init_std": 0.02,
|
| 51 |
+
"init_xavier_std": 1.0,
|
| 52 |
+
"is_encoder_decoder": true,
|
| 53 |
+
"label2id": {
|
| 54 |
+
"accessory": 7,
|
| 55 |
+
"bag": 0,
|
| 56 |
+
"bottom": 1,
|
| 57 |
+
"dress": 2,
|
| 58 |
+
"hat": 3,
|
| 59 |
+
"outer": 4,
|
| 60 |
+
"shoes": 5,
|
| 61 |
+
"top": 6
|
| 62 |
+
},
|
| 63 |
+
"mask_loss_coefficient": 1,
|
| 64 |
+
"max_position_embeddings": 1024,
|
| 65 |
+
"model_type": "conditional_detr",
|
| 66 |
+
"num_channels": 3,
|
| 67 |
+
"num_hidden_layers": 6,
|
| 68 |
+
"num_queries": 300,
|
| 69 |
+
"position_embedding_type": "sine",
|
| 70 |
+
"scale_embedding": false,
|
| 71 |
+
"torch_dtype": "float32",
|
| 72 |
+
"transformers_version": "4.46.0",
|
| 73 |
+
"use_pretrained_backbone": true,
|
| 74 |
+
"use_timm_backbone": true
|
| 75 |
+
}
|