Training in progress, epoch 1

config.json

@@ -1,148 +1,69 @@
 {
-  "_name_or_path": "facebook/detr-resnet-50",
+  "_name_or_path": "microsoft/conditional-detr-resnet-50",
   "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
-    "DetrForObjectDetection"
+    "ConditionalDetrForObjectDetection"
   ],
   "attention_dropout": 0.0,
   "auxiliary_loss": false,
-  "backbone": null,
-  "backbone_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "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": [
-      3,
-      4,
-      6,
-      3
-    ],
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "downsample_in_bottleneck": false,
-    "downsample_in_first_stage": false,
-    "early_stopping": false,
-    "embedding_size": 64,
-    "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": "relu",
-    "hidden_sizes": [
-      256,
-      512,
-      1024,
-      2048
-    ],
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_type": "bottleneck",
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "resnet",
-    "no_repeat_ngram_size": 0,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_channels": 3,
-    "num_return_sequences": 1,
-    "out_features": [
-      "stage4"
-    ],
+  "backbone": "resnet50",
+  "backbone_config": null,
+  "backbone_kwargs": {
+    "in_chans": 3,
     "out_indices": [
+      1,
+      2,
+      3,
       4
-    ],
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "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,
-    "typical_p": 1.0,
-    "use_bfloat16": false
+    ]
   },
-  "backbone_kwargs": null,
   "bbox_cost": 5,
   "bbox_loss_coefficient": 5,
-  "class_cost": 1,
+  "class_cost": 2,
+  "cls_loss_coefficient": 2,
   "d_model": 256,
   "decoder_attention_heads": 8,
   "decoder_ffn_dim": 2048,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 6,
   "dice_loss_coefficient": 1,
-  "dilation": null,
+  "dilation": false,
   "dropout": 0.1,
   "encoder_attention_heads": 8,
   "encoder_ffn_dim": 2048,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
-  "eos_coefficient": 0.1,
+  "focal_alpha": 0.25,
   "giou_cost": 2,
   "giou_loss_coefficient": 2,
   "id2label": {
-    "1": "Blackspot",
-    "2": "Canker",
-    "3": "Greening"
+    "0": "Coverall",
+    "1": "Face_Shield",
+    "2": "Gloves",
+    "3": "Goggles",
+    "4": "Mask"
   },
   "init_std": 0.02,
   "init_xavier_std": 1.0,
   "is_encoder_decoder": true,
   "label2id": {
-    "Blackspot": 1,
-    "Canker": 2,
-    "Greening": 3
+    "Coverall": 0,
+    "Face_Shield": 1,
+    "Gloves": 2,
+    "Goggles": 3,
+    "Mask": 4
   },
   "mask_loss_coefficient": 1,
-  "model_type": "detr",
+  "max_position_embeddings": 1024,
+  "model_type": "conditional_detr",
   "num_channels": 3,
   "num_hidden_layers": 6,
-  "num_queries": 100,
+  "num_queries": 300,
   "position_embedding_type": "sine",
   "scale_embedding": false,
   "torch_dtype": "float32",
   "transformers_version": "4.42.4",
-  "use_pretrained_backbone": null,
-  "use_timm_backbone": false
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1119d7f332806a2b0839b4b9a1a19c59497165fe169400705588a9aa97cbc393
-size 166505784
+oid sha256:2651a4913fec7f5ce2d2983a792afcd2bb32553a1a07e8870f1450252ea653c4
+size 174079796

preprocessor_config.json

@@ -10,17 +10,20 @@
     0.456,
     0.406
   ],
-  "image_processor_type": "DetrImageProcessor",
+  "image_processor_type": "ConditionalDetrImageProcessor",
   "image_std": [
     0.229,
     0.224,
     0.225
   ],
-  "pad_size": null,
+  "pad_size": {
+    "height": 480,
+    "width": 480
+  },
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "longest_edge": 1333,
-    "shortest_edge": 800
+    "max_height": 480,
+    "max_width": 480
   }
 }

runs/Aug14_14-16-40_12ac50f0b3d9/events.out.tfevents.1723645072.12ac50f0b3d9.266.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c80193a7cc98d0383620e3d54525046fdf2db5b6ee9e6f78faecd04bfc7434
+size 7191

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a67994656ca5bd1b546c9c5fde70c7557ff9444977bdb493f78c5c5d4fec92e7
+oid sha256:c3a09941984b9e00b0d3621b93dcdfe879cb41cb0a4b49d38832fff10ce2b512
 size 5112