Upload 3 files
Browse files- config.json +70 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "relu",
|
| 4 |
+
"angle_loss_coefficient": 1,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"MonoDETRForMultiObjectDetection"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"auxiliary_loss": true,
|
| 10 |
+
"backbone": "resnet50",
|
| 11 |
+
"backbone_config": null,
|
| 12 |
+
"bbox_cost": 5,
|
| 13 |
+
"bbox_loss_coefficient": 5,
|
| 14 |
+
"center3d_cost": 10,
|
| 15 |
+
"center3d_loss_coefficient": 10,
|
| 16 |
+
"class_cost": 2,
|
| 17 |
+
"cls_loss_coefficient": 2,
|
| 18 |
+
"d_model": 256,
|
| 19 |
+
"decoder_attention_heads": 8,
|
| 20 |
+
"decoder_depth_residual": true,
|
| 21 |
+
"decoder_ffn_dim": 256,
|
| 22 |
+
"decoder_layers": 3,
|
| 23 |
+
"decoder_n_points": 4,
|
| 24 |
+
"decoder_self_attn": true,
|
| 25 |
+
"depth_loss_coefficient": 1,
|
| 26 |
+
"depth_map_loss_coefficient": 1,
|
| 27 |
+
"depth_max": 60.0,
|
| 28 |
+
"depth_min": 0.001,
|
| 29 |
+
"dim_loss_coefficient": 1,
|
| 30 |
+
"disable_custom_kernels": false,
|
| 31 |
+
"dropout": 0.1,
|
| 32 |
+
"encoder_attention_heads": 8,
|
| 33 |
+
"encoder_ffn_dim": 256,
|
| 34 |
+
"encoder_layers": 3,
|
| 35 |
+
"encoder_n_points": 4,
|
| 36 |
+
"focal_alpha": 0.25,
|
| 37 |
+
"freeze_backbone": true,
|
| 38 |
+
"giou_cost": 2,
|
| 39 |
+
"giou_loss_coefficient": 2,
|
| 40 |
+
"group_num": 11,
|
| 41 |
+
"id2label": {
|
| 42 |
+
"0": "Pedestrian",
|
| 43 |
+
"1": "Car",
|
| 44 |
+
"2": "Cyclist"
|
| 45 |
+
},
|
| 46 |
+
"init_box": false,
|
| 47 |
+
"init_std": 0.02,
|
| 48 |
+
"init_xavier_std": 1.0,
|
| 49 |
+
"is_encoder_decoder": true,
|
| 50 |
+
"label2id": {
|
| 51 |
+
"Car": 1,
|
| 52 |
+
"Cyclist": 2,
|
| 53 |
+
"Pedestrian": 0
|
| 54 |
+
},
|
| 55 |
+
"model_type": "mono3dvgv2",
|
| 56 |
+
"num_channels": 3,
|
| 57 |
+
"num_depth_bins": 80,
|
| 58 |
+
"num_feature_levels": 4,
|
| 59 |
+
"num_queries": 50,
|
| 60 |
+
"position_embedding_type": "sine",
|
| 61 |
+
"pretrained_backbone_path": "pretrained-models/resnet50/model.safetensors",
|
| 62 |
+
"region_loss_coefficient": 1,
|
| 63 |
+
"torch_dtype": "float32",
|
| 64 |
+
"transformers_version": "4.46.3",
|
| 65 |
+
"two_stage": false,
|
| 66 |
+
"use_pretrained_backbone": true,
|
| 67 |
+
"use_timm_backbone": true,
|
| 68 |
+
"use_torchvision_backbone": false,
|
| 69 |
+
"with_box_refine": true
|
| 70 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.485,
|
| 7 |
+
0.456,
|
| 8 |
+
0.406
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "MonoDETRImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.229,
|
| 13 |
+
0.224,
|
| 14 |
+
0.225
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 384,
|
| 20 |
+
"width": 1280
|
| 21 |
+
}
|
| 22 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2108718904cf4c0ed6c3dd805279bc7cb8a8349fbfcb3338e66c66420bde95a
|
| 3 |
+
size 150522118
|