Training in progress, step 500

config.json

@@ -0,0 +1,323 @@
+{
+  "_name_or_path": "facebook/detr-resnet-50",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "resnet50",
+  "backbone_config": null,
+  "backbone_kwargs": {
+    "in_chans": 3,
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ]
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "classifier_dropout": 0.0,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dice_loss_coefficient": 1,
+  "dilation": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_coefficient": 0.1,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "1": 53,
+    "2": 98,
+    "3": 99,
+    "4": 47,
+    "5": 48,
+    "6": 28,
+    "7": 29,
+    "8": 51,
+    "9": 97,
+    "10": 98,
+    "11": 99,
+    "12": 14,
+    "13": 16,
+    "14": 50,
+    "15": 76,
+    "16": 77,
+    "17": 32,
+    "18": 33,
+    "19": 74,
+    "20": 83,
+    "21": 67,
+    "22": 101,
+    "23": 100,
+    "24": 102,
+    "25": 31,
+    "26": 4,
+    "27": 87,
+    "28": 89,
+    "29": 15,
+    "30": 12,
+    "31": 7,
+    "32": 92,
+    "33": 3,
+    "34": 52,
+    "35": 20,
+    "36": 19,
+    "37": 57,
+    "38": 58,
+    "39": 35,
+    "40": 34,
+    "41": 39,
+    "42": 40,
+    "43": 49,
+    "44": 20,
+    "45": 19,
+    "46": 85,
+    "47": 86,
+    "48": 74,
+    "49": 75,
+    "50": 61,
+    "51": 62,
+    "52": 18,
+    "53": 14,
+    "54": 35,
+    "55": 34,
+    "56": 1,
+    "57": 28,
+    "58": 30,
+    "59": 10,
+    "60": 53,
+    "61": 22,
+    "62": 20,
+    "63": 19,
+    "64": 74,
+    "65": 101,
+    "66": 100,
+    "67": 102,
+    "68": 72,
+    "69": 73,
+    "70": 21,
+    "71": 57,
+    "72": 58,
+    "73": 36,
+    "74": 37,
+    "75": 38,
+    "76": 63,
+    "77": 53,
+    "78": 90,
+    "79": 91,
+    "80": 7,
+    "81": 9,
+    "82": 97,
+    "83": 98,
+    "84": 99,
+    "85": 26,
+    "86": 27,
+    "87": 92,
+    "88": 93,
+    "89": 66,
+    "90": 61,
+    "91": 62,
+    "92": 94,
+    "93": 92,
+    "94": 87,
+    "95": 81,
+    "96": 80,
+    "97": 78,
+    "98": 79,
+    "99": 51,
+    "100": 68,
+    "101": 54,
+    "102": 55,
+    "103": 56,
+    "104": 69,
+    "105": 8,
+    "106": 103,
+    "107": 104,
+    "108": 105,
+    "109": 25,
+    "110": 23,
+    "111": 24,
+    "112": 72,
+    "113": 95,
+    "114": 96,
+    "115": 41,
+    "116": 42,
+    "117": 6,
+    "118": 70,
+    "119": 71,
+    "120": 44,
+    "121": 45,
+    "122": 46,
+    "123": 15,
+    "124": 12,
+    "125": 87,
+    "126": 88,
+    "127": 28,
+    "128": 29,
+    "129": 82,
+    "130": 83,
+    "131": 106,
+    "132": 107,
+    "133": 2,
+    "134": 42,
+    "135": 43,
+    "136": 81,
+    "137": 80,
+    "138": 78,
+    "139": 67,
+    "140": 8,
+    "141": 26,
+    "142": 32,
+    "143": 11,
+    "144": 13,
+    "145": 17,
+    "146": 23,
+    "147": 24,
+    "148": 63,
+    "149": 63,
+    "150": 70,
+    "151": 84,
+    "152": 106,
+    "153": 107,
+    "154": 2,
+    "155": 59,
+    "156": 60,
+    "157": 10,
+    "158": 63,
+    "159": 64
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "1": 56,
+    "2": 154,
+    "3": 33,
+    "4": 26,
+    "6": 117,
+    "7": 80,
+    "8": 140,
+    "9": 81,
+    "10": 157,
+    "11": 143,
+    "12": 124,
+    "13": 144,
+    "14": 53,
+    "15": 123,
+    "16": 13,
+    "17": 145,
+    "18": 52,
+    "19": 63,
+    "20": 62,
+    "21": 70,
+    "22": 61,
+    "23": 146,
+    "24": 147,
+    "25": 109,
+    "26": 141,
+    "27": 86,
+    "28": 127,
+    "29": 128,
+    "30": 58,
+    "31": 25,
+    "32": 142,
+    "33": 18,
+    "34": 55,
+    "35": 54,
+    "36": 73,
+    "37": 74,
+    "38": 75,
+    "39": 41,
+    "40": 42,
+    "41": 115,
+    "42": 134,
+    "43": 135,
+    "44": 120,
+    "45": 121,
+    "46": 122,
+    "47": 4,
+    "48": 5,
+    "49": 43,
+    "50": 14,
+    "51": 99,
+    "52": 34,
+    "53": 77,
+    "54": 101,
+    "55": 102,
+    "56": 103,
+    "57": 71,
+    "58": 72,
+    "59": 155,
+    "60": 156,
+    "61": 90,
+    "62": 91,
+    "63": 158,
+    "64": 159,
+    "66": 89,
+    "67": 139,
+    "68": 100,
+    "69": 104,
+    "70": 150,
+    "71": 119,
+    "72": 112,
+    "73": 69,
+    "74": 64,
+    "75": 49,
+    "76": 15,
+    "77": 16,
+    "78": 138,
+    "79": 98,
+    "80": 137,
+    "81": 136,
+    "82": 129,
+    "83": 130,
+    "84": 151,
+    "85": 46,
+    "86": 47,
+    "87": 125,
+    "88": 126,
+    "89": 28,
+    "90": 78,
+    "91": 79,
+    "92": 93,
+    "93": 88,
+    "94": 92,
+    "95": 113,
+    "96": 114,
+    "97": 82,
+    "98": 83,
+    "99": 84,
+    "100": 66,
+    "101": 65,
+    "102": 67,
+    "103": 106,
+    "104": 107,
+    "105": 108,
+    "106": 152,
+    "107": 153
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "detr",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 100,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daae49c4d5bdc952b3d0e5525b4c806df450001f3c30c268b5e81d14f06c006d
+size 166657288

preprocessor_config.json

@@ -0,0 +1,45 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "annotations",
+    "return_segmentation_masks",
+    "masks_path",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "do_convert_annotations",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "format",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_convert_annotations": true,
+  "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": "DetrImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1333,
+    "shortest_edge": 800
+  }
+}

runs/Jun05_01-32-32_11ac20b3c004/events.out.tfevents.1717551327.11ac20b3c004.22399.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:255b0f5362841ad9098ea6fb09ce595eec9dad07dcae9bdfbf8c0bc401a36976
+size 9742

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac81d2581e05534daa45b3e6be4822a1fc67ce47f27b9faf521433cafe4dff29
+size 5112