upload config and model

config.json

@@ -0,0 +1,248 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "Multiformer"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "pvt_v2",
+  "backbone_config": {
+    "_name_or_path": "",
+    "_out_features": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3"
+    ],
+    "_out_indices": [
+      0,
+      1,
+      2,
+      3
+    ],
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "attn_reduce": "SR",
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      2,
+      2,
+      2,
+      2
+    ],
+    "diversity_penalty": 0.0,
+    "do_reduce_labels": true,
+    "do_sample": false,
+    "drop_path_rate": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_sizes": [
+      32,
+      64,
+      160,
+      256
+    ],
+    "id2label": {
+      "0": "unlabeled",
+      "1": "building",
+      "2": "fence",
+      "3": "other",
+      "4": "pedestrian",
+      "5": "pole",
+      "6": "road line",
+      "7": "road",
+      "8": "sidewalk",
+      "9": "vegetation",
+      "10": "vehicle",
+      "11": "wall",
+      "12": "traffic sign",
+      "13": "sky",
+      "14": "ground",
+      "15": "bridge",
+      "16": "rail track",
+      "17": "guard rail",
+      "18": "traffic light",
+      "19": "static",
+      "20": "dynamic",
+      "21": "water",
+      "22": "terrain"
+    },
+    "image_size": {
+      "height": 224,
+      "width": 224
+    },
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "bridge": 15,
+      "building": 1,
+      "dynamic": 20,
+      "fence": 2,
+      "ground": 14,
+      "guard rail": 17,
+      "other": 3,
+      "pedestrian": 4,
+      "pole": 5,
+      "rail track": 16,
+      "road": 7,
+      "road line": 6,
+      "sidewalk": 8,
+      "sky": 13,
+      "static": 19,
+      "terrain": 22,
+      "traffic light": 18,
+      "traffic sign": 12,
+      "unlabeled": 0,
+      "vegetation": 9,
+      "vehicle": 10,
+      "wall": 11,
+      "water": 21
+    },
+    "layer_norm_eps": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratios": [
+      4,
+      4,
+      4,
+      4
+    ],
+    "model_type": "pvt_v2",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": [
+      1,
+      2,
+      5,
+      8
+    ],
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_encoder_blocks": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": true,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_sizes": [
+      7,
+      3,
+      3,
+      3
+    ],
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "reshape_last_stage": true,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "sr_ratios": [
+      8,
+      4,
+      2,
+      1
+    ],
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "strides": [
+      4,
+      2,
+      2,
+      2
+    ],
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 256,
+  "decoder_layers": 3,
+  "decoder_n_points": 4,
+  "depth_decoder_dim": 64,
+  "dice_loss_coefficient": 1,
+  "dilation": false,
+  "disable_custom_kernels": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 256,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 3,
+  "encoder_n_points": 4,
+  "eos_coefficient": 0.1,
+  "focal_alpha": 0.25,
+  "frozen_batch_norm": false,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "head_in_index": -1,
+  "id2label": {
+    "0": "pedestrian",
+    "1": "car",
+    "2": "truck",
+    "3": "bus",
+    "4": "motorcycle",
+    "5": "bicycle",
+    "6": "no_box"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": null,
+  "mask_loss_coefficient": 1,
+  "max_depth": 10,
+  "max_position_embeddings": 1024,
+  "model_type": "multiformer",
+  "num_channels": 3,
+  "num_feature_levels": 4,
+  "num_queries": 300,
+  "position_embedding_type": "sine",
+  "semantic_classifier_dropout": 0.1,
+  "semantic_decoder_dim": 256,
+  "semantic_loss_ignore_index": 255,
+  "silog_lambda": 0.25,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0.dev0",
+  "two_stage": false,
+  "two_stage_num_proposals": 300,
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": false,
+  "with_box_refine": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2cda0bbe276c5f835ae40c74efa00b13c3014b8680ad34fc982b236d9b8872
+size 32310749