Upload 3 files

config.json

@@ -0,0 +1,85 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "angle_loss_coefficient": 1,
+  "architectures": [
+    "Mono3DVGv2ForSingleObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "swin_large_patch4_window7_224",
+  "backbone_config": null,
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "center3d_cost": 10,
+  "center3d_loss_coefficient": 10,
+  "class_cost": 2,
+  "cls_loss_coefficient": 2,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_depth_residual": false,
+  "decoder_ffn_dim": 256,
+  "decoder_layers": 1,
+  "decoder_n_points": 4,
+  "decoder_self_attn": false,
+  "decoder_text_residual": false,
+  "depth_loss_coefficient": 1,
+  "depth_map_loss_coefficient": 1,
+  "depth_max": 60.0,
+  "depth_min": 0.001,
+  "dim_loss_coefficient": 1,
+  "disable_custom_kernels": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 256,
+  "encoder_layers": 3,
+  "encoder_n_points": 4,
+  "focal_alpha": 0.25,
+  "freeze_backbone": true,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "pedestrian",
+    "1": "car",
+    "2": "cyclist",
+    "3": "van",
+    "4": "truck",
+    "5": "tram",
+    "6": "bus",
+    "7": "person_sitting",
+    "8": "motorcyclist"
+  },
+  "init_box": false,
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "bus": 6,
+    "car": 1,
+    "cyclist": 2,
+    "motorcyclist": 8,
+    "pedestrian": 0,
+    "person_sitting": 7,
+    "tram": 5,
+    "truck": 4,
+    "van": 3
+  },
+  "model_type": "mono3dvgv2",
+  "num_channels": 3,
+  "num_depth_bins": 80,
+  "num_feature_levels": 4,
+  "num_queries": 1,
+  "num_text_output_layers": 1,
+  "position_embedding_type": "sine",
+  "pretrained_backbone_path": "pretrained-models/swin_large_patch4_window7_224/model.safetensors",
+  "text_encoder_type": "pretrained-models/roberta-base",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "two_stage": false,
+  "use_dab": true,
+  "use_pretrained_backbone": true,
+  "use_text_guided_adapter": true,
+  "use_timm_backbone": true,
+  "vl_encoder_type": "fusion",
+  "with_box_refine": true
+}

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "Mono3DVGImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 1280
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeae527ec76a06e746b913e8e4b4a984107567a03d67494cacdae822835aba3b
+size 1324513302