Upload Mask2FormerForUniversalSegmentation

config.json

@@ -0,0 +1,237 @@
+{
+  "_commit_hash": null,
+  "activation_function": "relu",
+  "architectures": [
+    "Mask2FormerForUniversalSegmentation"
+  ],
+  "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": 0.3,
+    "early_stopping": false,
+    "embed_dim": 128,
+    "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": 1024,
+    "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": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_layers": 4,
+    "num_return_sequences": 1,
+    "out_features": [
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 4,
+    "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": "4.28.0.dev0",
+    "typical_p": 1.0,
+    "use_absolute_embeddings": false,
+    "use_bfloat16": false,
+    "window_size": 12
+  },
+  "class_weight": 2.0,
+  "common_stride": 4,
+  "decoder_layers": 10,
+  "dice_weight": 5.0,
+  "dim_feedforward": 2048,
+  "dropout": 0.0,
+  "encoder_feedforward_dim": 1024,
+  "encoder_layers": 6,
+  "enforce_input_proj": false,
+  "enforce_input_projection": false,
+  "feature_size": 256,
+  "feature_strides": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "frame_range": 20,
+  "frame_shuffle": false,
+  "hidden_dim": 256,
+  "id2label": {
+    "0": "person",
+    "1": "giant_panda",
+    "2": "lizard",
+    "3": "parrot",
+    "4": "skateboard",
+    "5": "sedan",
+    "6": "ape",
+    "7": "dog",
+    "8": "snake",
+    "9": "monkey",
+    "10": "hand",
+    "11": "rabbit",
+    "12": "duck",
+    "13": "cat",
+    "14": "cow",
+    "15": "fish",
+    "16": "train",
+    "17": "horse",
+    "18": "turtle",
+    "19": "bear",
+    "20": "motorbike",
+    "21": "giraffe",
+    "22": "leopard",
+    "23": "fox",
+    "24": "deer",
+    "25": "owl",
+    "26": "surfboard",
+    "27": "airplane",
+    "28": "truck",
+    "29": "zebra",
+    "30": "tiger",
+    "31": "elephant",
+    "32": "snowboard",
+    "33": "boat",
+    "34": "shark",
+    "35": "mouse",
+    "36": "frog",
+    "37": "eagle",
+    "38": "earless_seal",
+    "39": "tennis_racket"
+  },
+  "ignore_value": 255,
+  "importance_sample_ratio": 0.75,
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_video": true,
+  "label2id": {
+    "airplane": 27,
+    "ape": 6,
+    "bear": 19,
+    "boat": 33,
+    "cat": 13,
+    "cow": 14,
+    "deer": 24,
+    "dog": 7,
+    "duck": 12,
+    "eagle": 37,
+    "earless_seal": 38,
+    "elephant": 31,
+    "fish": 15,
+    "fox": 23,
+    "frog": 36,
+    "giant_panda": 1,
+    "giraffe": 21,
+    "hand": 10,
+    "horse": 17,
+    "leopard": 22,
+    "lizard": 2,
+    "monkey": 9,
+    "motorbike": 20,
+    "mouse": 35,
+    "owl": 25,
+    "parrot": 3,
+    "person": 0,
+    "rabbit": 11,
+    "sedan": 5,
+    "shark": 34,
+    "skateboard": 4,
+    "snake": 8,
+    "snowboard": 32,
+    "surfboard": 26,
+    "tennis_racket": 39,
+    "tiger": 30,
+    "train": 16,
+    "truck": 28,
+    "turtle": 18,
+    "zebra": 29
+  },
+  "mask_feature_size": 256,
+  "mask_weight": 5.0,
+  "model_type": "mask2former",
+  "no_object_weight": 0.1,
+  "num_attention_heads": 8,
+  "num_frames": 2,
+  "num_hidden_layers": 10,
+  "num_queries": 100,
+  "output_auxiliary_logits": null,
+  "oversample_ratio": 3.0,
+  "pre_norm": false,
+  "torch_dtype": "float32",
+  "train_num_points": 12544,
+  "transformers_version": null,
+  "use_auxiliary_loss": true
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ec7bed770fb1d097b25913b589950875207f8f2fe591baa04bf6b30460f46a
+size 431837253