Upload 6 files

README.md

@@ -1,3 +1,13 @@
 ---
-license: apache-2.0
+pipeline_tag: object-detection
+tags:
+- vision
 ---
+# Detection Transformers with Assignment
+
+By [Jeffrey Ouyang-Zhang](https://jozhang97.github.io/),  [Jang Hyun Cho](https://sites.google.com/view/janghyuncho/), [Xingyi Zhou](https://www.cs.utexas.edu/~zhouxy/), [Philipp Krähenbühl](http://www.philkr.net/)
+
+From the paper [NMS Strikes Back](https://arxiv.org/abs/2212.06137).
+
+
+**TL; DR.** **De**tection **T**ransformers with **A**ssignment (DETA) re-introduce IoU assignment and NMS for transformer-based detectors. DETA trains and tests comparibly as fast as Deformable-DETR and converges much faster (50.2 mAP in 12 epochs on COCO).

config.json

@@ -0,0 +1,328 @@
+{
+  "_commit_hash": null,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DetaForObjectDetection"
+  ],
+  "assign_first_stage": true,
+  "assign_second_stage": true,
+  "attention_dropout": 0.0,
+  "auxiliary_loss": true,
+  "backbone_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "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,
+      18,
+      2
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "early_stopping": false,
+    "embed_dim": 192,
+    "encoder_no_repeat_ngram_size": 0,
+    "encoder_stride": 32,
+    "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_size": 1536,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 4.0,
+    "model_type": "swin",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_heads": [
+      6,
+      12,
+      24,
+      48
+    ],
+    "num_layers": 4,
+    "num_return_sequences": 1,
+    "out_features": [
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 4,
+    "path_norm": true,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "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,
+    "transformers_version": "4.27.0.dev0",
+    "typical_p": 1.0,
+    "use_absolute_embeddings": false,
+    "use_bfloat16": false,
+    "window_size": 12
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_n_points": 4,
+  "dice_loss_coefficient": 1,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "encoder_n_points": 4,
+  "eos_coefficient": 0.1,
+  "focal_alpha": 0.25,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "N/A",
+    "1": "person",
+    "2": "bicycle",
+    "3": "car",
+    "4": "motorcycle",
+    "5": "airplane",
+    "6": "bus",
+    "7": "train",
+    "8": "truck",
+    "9": "boat",
+    "10": "traffic light",
+    "11": "fire hydrant",
+    "12": "N/A",
+    "13": "stop sign",
+    "14": "parking meter",
+    "15": "bench",
+    "16": "bird",
+    "17": "cat",
+    "18": "dog",
+    "19": "horse",
+    "20": "sheep",
+    "21": "cow",
+    "22": "elephant",
+    "23": "bear",
+    "24": "zebra",
+    "25": "giraffe",
+    "26": "N/A",
+    "27": "backpack",
+    "28": "umbrella",
+    "29": "N/A",
+    "30": "N/A",
+    "31": "handbag",
+    "32": "tie",
+    "33": "suitcase",
+    "34": "frisbee",
+    "35": "skis",
+    "36": "snowboard",
+    "37": "sports ball",
+    "38": "kite",
+    "39": "baseball bat",
+    "40": "baseball glove",
+    "41": "skateboard",
+    "42": "surfboard",
+    "43": "tennis racket",
+    "44": "bottle",
+    "45": "N/A",
+    "46": "wine glass",
+    "47": "cup",
+    "48": "fork",
+    "49": "knife",
+    "50": "spoon",
+    "51": "bowl",
+    "52": "banana",
+    "53": "apple",
+    "54": "sandwich",
+    "55": "orange",
+    "56": "broccoli",
+    "57": "carrot",
+    "58": "hot dog",
+    "59": "pizza",
+    "60": "donut",
+    "61": "cake",
+    "62": "chair",
+    "63": "couch",
+    "64": "potted plant",
+    "65": "bed",
+    "66": "N/A",
+    "67": "dining table",
+    "68": "N/A",
+    "69": "N/A",
+    "70": "toilet",
+    "71": "N/A",
+    "72": "tv",
+    "73": "laptop",
+    "74": "mouse",
+    "75": "remote",
+    "76": "keyboard",
+    "77": "cell phone",
+    "78": "microwave",
+    "79": "oven",
+    "80": "toaster",
+    "81": "sink",
+    "82": "refrigerator",
+    "83": "N/A",
+    "84": "book",
+    "85": "clock",
+    "86": "vase",
+    "87": "scissors",
+    "88": "teddy bear",
+    "89": "hair drier",
+    "90": "toothbrush"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "N/A": 83,
+    "airplane": 5,
+    "apple": 53,
+    "backpack": 27,
+    "banana": 52,
+    "baseball bat": 39,
+    "baseball glove": 40,
+    "bear": 23,
+    "bed": 65,
+    "bench": 15,
+    "bicycle": 2,
+    "bird": 16,
+    "boat": 9,
+    "book": 84,
+    "bottle": 44,
+    "bowl": 51,
+    "broccoli": 56,
+    "bus": 6,
+    "cake": 61,
+    "car": 3,
+    "carrot": 57,
+    "cat": 17,
+    "cell phone": 77,
+    "chair": 62,
+    "clock": 85,
+    "couch": 63,
+    "cow": 21,
+    "cup": 47,
+    "dining table": 67,
+    "dog": 18,
+    "donut": 60,
+    "elephant": 22,
+    "fire hydrant": 11,
+    "fork": 48,
+    "frisbee": 34,
+    "giraffe": 25,
+    "hair drier": 89,
+    "handbag": 31,
+    "horse": 19,
+    "hot dog": 58,
+    "keyboard": 76,
+    "kite": 38,
+    "knife": 49,
+    "laptop": 73,
+    "microwave": 78,
+    "motorcycle": 4,
+    "mouse": 74,
+    "orange": 55,
+    "oven": 79,
+    "parking meter": 14,
+    "person": 1,
+    "pizza": 59,
+    "potted plant": 64,
+    "refrigerator": 82,
+    "remote": 75,
+    "sandwich": 54,
+    "scissors": 87,
+    "sheep": 20,
+    "sink": 81,
+    "skateboard": 41,
+    "skis": 35,
+    "snowboard": 36,
+    "spoon": 50,
+    "sports ball": 37,
+    "stop sign": 13,
+    "suitcase": 33,
+    "surfboard": 42,
+    "teddy bear": 88,
+    "tennis racket": 43,
+    "tie": 32,
+    "toaster": 80,
+    "toilet": 70,
+    "toothbrush": 90,
+    "traffic light": 10,
+    "train": 7,
+    "truck": 8,
+    "tv": 72,
+    "umbrella": 28,
+    "vase": 86,
+    "wine glass": 46,
+    "zebra": 24
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 2048,
+  "model_type": "deta",
+  "num_feature_levels": 5,
+  "num_queries": 900,
+  "position_embedding_type": "sine",
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "two_stage": true,
+  "two_stage_num_proposals": 900,
+  "with_box_refine": true
+}

gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e2be6ab0cc12374e16adb7a51bd6e1e67342e63161477b197fca6c8606d473a
+size 879186588

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "DetaImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1333,
+    "shortest_edge": 800
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e8cd13b7ca76b06b7684534a8ac1e3c2628d57d58cb135ed438861938b5cf2
+size 879370285