Training in progress, epoch 1

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/maskformer-swin-tiny-coco",
+  "architectures": [
+    "MaskFormerForInstanceSegmentation"
+  ],
+  "backbone": null,
+  "backbone_config": {
+    "depths": [
+      2,
+      2,
+      6,
+      2
+    ],
+    "drop_path_rate": 0.3,
+    "embed_dim": 96,
+    "encoder_stride": 32,
+    "hidden_size": 768,
+    "image_size": 224,
+    "in_channels": 3,
+    "model_type": "maskformer-swin",
+    "num_heads": [
+      3,
+      6,
+      12,
+      24
+    ],
+    "out_features": [
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ],
+    "path_norm": true,
+    "pretrain_img_size": 224,
+    "window_size": 7
+  },
+  "backbone_kwargs": null,
+  "ce_weight": 1.0,
+  "cross_entropy_weight": 1.0,
+  "decoder_config": {
+    "max_position_embeddings": 1024,
+    "model_type": "detr",
+    "scale_embedding": false
+  },
+  "dice_weight": 1.0,
+  "fpn_feature_size": 256,
+  "id2label": {
+    "0": "person",
+    "1": "car"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "label2id": {
+    "car": 1,
+    "person": 0
+  },
+  "mask_feature_size": 256,
+  "mask_weight": 20.0,
+  "model_type": "maskformer",
+  "no_object_weight": 0.1,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "num_queries": 100,
+  "output_auxiliary_logits": null,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "use_auxiliary_loss": false,
+  "use_pretrained_backbone": false,
+  "use_timm_backbone": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a386ce688a2c7e1a32f875af96e60c6006d81dc667b1ef170a0441aa6ba6eb2f
+size 167175760

preprocessor_config.json

@@ -0,0 +1,45 @@
+{
+  "_max_size": 1333,
+  "_valid_processor_keys": [
+    "images",
+    "segmentation_maps",
+    "instance_id_to_semantic_id",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "ignore_index",
+    "do_reduce_labels",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_reduce_labels": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "ignore_index": 255,
+  "image_mean": [
+    0.48500001430511475,
+    0.4560000002384186,
+    0.4059999883174896
+  ],
+  "image_processor_type": "MaskFormerImageProcessor",
+  "image_std": [
+    0.2290000021457672,
+    0.2239999920129776,
+    0.22499999403953552
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 256,
+    "width": 256
+  },
+  "size_divisor": 32
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:249970984043353f51543f29ce552123fae7b976355e1483fbbc96c9e4ae0356
+size 4731