Training in progress, epoch 1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,157 @@
+{
+  "_commit_hash": null,
+  "_name_or_path": "jozhang97/deta-swin-large",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DetaForObjectDetection"
+  ],
+  "assign_first_stage": true,
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "swin-large",
+  "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_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": [
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      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,
+    "transformers_version": "4.28.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "bbox_cost": 5.0,
+  "bbox_loss_coefficient": 5.0,
+  "class_cost": 1.0,
+  "d_model": 256,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_n_points": 4,
+  "dice_loss_coefficient": 1,
+  "dilation": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "encoder_n_points": 4,
+  "eos_coefficient": 0.1,
+  "eos_loss_coefficient": 0.1,
+  "focal_alpha": 0.25,
+  "giou_cost": 2.0,
+  "giou_loss_coefficient": 2.0,
+  "id2label": {
+    "0": "leukocyte"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "leukocyte": 0
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 2048,
+  "model_type": "deta",
+  "num_classes": 1,
+  "num_feature_levels": 5,
+  "num_queries": 100,
+  "output_attentions": true,
+  "position_embedding_type": "sine",
+  "positional_embedding_type": "sine",
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "two_stage": true,
+  "two_stage_num_proposals": 300,
+  "use_pretrained_backbone": true,
+  "with_box_refine": true
+}

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "DetrFeatureExtractor",
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "DetrFeatureExtractor",
+  "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 sha256:1676c84e82bc132f9230fbb1317f483a307178d93e8b9b79e701b04c69fc913e
+size 171449333

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c455d74eacdb9259f4055d152e99035166f8d1948385a31c4010390a7b9482ff
+size 3579