Training in progress, epoch 1

config.json

@@ -0,0 +1,111 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "silu",
+  "architectures": [
+    "LwDetrForObjectDetection"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "auxiliary_loss": true,
+  "backbone": null,
+  "backbone_config": {
+    "cae_init_values": 0.1,
+    "dropout_prob": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 192,
+    "image_size": 1024,
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-06,
+    "mlp_ratio": 4,
+    "model_type": "lw_detr_vit",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 6,
+    "num_windows": 16,
+    "num_windows_side": 4,
+    "out_features": [
+      "stage2",
+      "stage4",
+      "stage6"
+    ],
+    "out_indices": [
+      2,
+      4,
+      6
+    ],
+    "patch_size": 16,
+    "pretrain_image_size": 224,
+    "qkv_bias": true,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4",
+      "stage5",
+      "stage6"
+    ],
+    "use_absolute_position_embeddings": true,
+    "window_block_indices": [
+      0,
+      2,
+      4
+    ]
+  },
+  "batch_norm_eps": 1e-05,
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "c2f_num_blocks": 3,
+  "class_cost": 2,
+  "d_model": 256,
+  "decoder_activation_function": "relu",
+  "decoder_cross_attention_heads": 16,
+  "decoder_ffn_dim": 2048,
+  "decoder_layers": 3,
+  "decoder_n_points": 2,
+  "decoder_self_attention_heads": 8,
+  "dice_loss_coefficient": 1,
+  "disable_custom_kernels": true,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "eos_coefficient": 0.1,
+  "focal_alpha": 0.25,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "group_detr": 13,
+  "hidden_expansion": 0.5,
+  "id2label": {
+    "0": "Tray",
+    "1": "Cart"
+  },
+  "init_std": 0.02,
+  "keys_to_ignore_at_inference": [
+    "loss_dict",
+    "auxiliary_outputs",
+    "last_hidden_state",
+    "intermediate_hidden_states",
+    "intermediate_logits",
+    "intermediate_reference_points",
+    "encoder_last_hidden_state",
+    "init_reference_points",
+    "enc_outputs_class",
+    "enc_outputs_coord_logits"
+  ],
+  "label2id": {
+    "Cart": 1,
+    "Tray": 0
+  },
+  "model_type": "lw_detr",
+  "num_feature_levels": 1,
+  "num_queries": 100,
+  "projector_in_channels": [
+    256
+  ],
+  "projector_out_channels": 256,
+  "projector_scale_factors": [
+    1.0
+  ],
+  "transformers_version": "5.2.0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f07e99b09c70381b31af3112484b40404fdd603a17b63c3e814c8c3e7ef8602
+size 46985608

preprocessor_config.json

@@ -0,0 +1,30 @@
+{
+  "data_format": "channels_first",
+  "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": "DeformableDetrImageProcessorFast",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "pad_size": {
+    "height": 640,
+    "width": 640
+  },
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_height": 640,
+    "max_width": 640
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb8c668ede040d7f4b3f52b9ffd794934672153a7263bbd1e0c91d1bcaa1844
+size 5329