Training in progress, epoch 1
Browse files
config.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "silu",
|
| 4 |
+
"anchor_image_size": null,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"RTDetrV2ForObjectDetection"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"auxiliary_loss": true,
|
| 10 |
+
"backbone": null,
|
| 11 |
+
"backbone_config": {
|
| 12 |
+
"depths": [
|
| 13 |
+
2,
|
| 14 |
+
2,
|
| 15 |
+
2,
|
| 16 |
+
2
|
| 17 |
+
],
|
| 18 |
+
"downsample_in_bottleneck": false,
|
| 19 |
+
"downsample_in_first_stage": false,
|
| 20 |
+
"dtype": "float32",
|
| 21 |
+
"embedding_size": 64,
|
| 22 |
+
"hidden_act": "relu",
|
| 23 |
+
"hidden_sizes": [
|
| 24 |
+
64,
|
| 25 |
+
128,
|
| 26 |
+
256,
|
| 27 |
+
512
|
| 28 |
+
],
|
| 29 |
+
"layer_type": "basic",
|
| 30 |
+
"model_type": "rt_detr_resnet",
|
| 31 |
+
"num_channels": 3,
|
| 32 |
+
"out_features": [
|
| 33 |
+
"stage2",
|
| 34 |
+
"stage3",
|
| 35 |
+
"stage4"
|
| 36 |
+
],
|
| 37 |
+
"out_indices": [
|
| 38 |
+
2,
|
| 39 |
+
3,
|
| 40 |
+
4
|
| 41 |
+
],
|
| 42 |
+
"stage_names": [
|
| 43 |
+
"stem",
|
| 44 |
+
"stage1",
|
| 45 |
+
"stage2",
|
| 46 |
+
"stage3",
|
| 47 |
+
"stage4"
|
| 48 |
+
]
|
| 49 |
+
},
|
| 50 |
+
"backbone_kwargs": null,
|
| 51 |
+
"batch_norm_eps": 1e-05,
|
| 52 |
+
"box_noise_scale": 1.0,
|
| 53 |
+
"d_model": 256,
|
| 54 |
+
"decoder_activation_function": "relu",
|
| 55 |
+
"decoder_attention_heads": 8,
|
| 56 |
+
"decoder_ffn_dim": 1024,
|
| 57 |
+
"decoder_in_channels": [
|
| 58 |
+
256,
|
| 59 |
+
256,
|
| 60 |
+
256
|
| 61 |
+
],
|
| 62 |
+
"decoder_layers": 3,
|
| 63 |
+
"decoder_method": "default",
|
| 64 |
+
"decoder_n_levels": 3,
|
| 65 |
+
"decoder_n_points": 4,
|
| 66 |
+
"decoder_offset_scale": 0.5,
|
| 67 |
+
"disable_custom_kernels": true,
|
| 68 |
+
"dropout": 0.0,
|
| 69 |
+
"dtype": "float32",
|
| 70 |
+
"encode_proj_layers": [
|
| 71 |
+
2
|
| 72 |
+
],
|
| 73 |
+
"encoder_activation_function": "gelu",
|
| 74 |
+
"encoder_attention_heads": 8,
|
| 75 |
+
"encoder_ffn_dim": 1024,
|
| 76 |
+
"encoder_hidden_dim": 256,
|
| 77 |
+
"encoder_in_channels": [
|
| 78 |
+
128,
|
| 79 |
+
256,
|
| 80 |
+
512
|
| 81 |
+
],
|
| 82 |
+
"encoder_layers": 1,
|
| 83 |
+
"eos_coefficient": 0.0001,
|
| 84 |
+
"eval_size": null,
|
| 85 |
+
"feat_strides": [
|
| 86 |
+
8,
|
| 87 |
+
16,
|
| 88 |
+
32
|
| 89 |
+
],
|
| 90 |
+
"focal_loss_alpha": 0.75,
|
| 91 |
+
"focal_loss_gamma": 2.0,
|
| 92 |
+
"freeze_backbone_batch_norms": true,
|
| 93 |
+
"hidden_expansion": 0.5,
|
| 94 |
+
"id2label": {
|
| 95 |
+
"0": "barcode"
|
| 96 |
+
},
|
| 97 |
+
"initializer_bias_prior_prob": null,
|
| 98 |
+
"initializer_range": 0.01,
|
| 99 |
+
"is_encoder_decoder": true,
|
| 100 |
+
"label2id": {
|
| 101 |
+
"barcode": 0
|
| 102 |
+
},
|
| 103 |
+
"label_noise_ratio": 0.5,
|
| 104 |
+
"layer_norm_eps": 1e-05,
|
| 105 |
+
"learn_initial_query": false,
|
| 106 |
+
"matcher_alpha": 0.25,
|
| 107 |
+
"matcher_bbox_cost": 5.0,
|
| 108 |
+
"matcher_class_cost": 2.0,
|
| 109 |
+
"matcher_gamma": 2.0,
|
| 110 |
+
"matcher_giou_cost": 2.0,
|
| 111 |
+
"model_type": "rt_detr_v2",
|
| 112 |
+
"normalize_before": false,
|
| 113 |
+
"num_denoising": 100,
|
| 114 |
+
"num_feature_levels": 3,
|
| 115 |
+
"num_queries": 300,
|
| 116 |
+
"positional_encoding_temperature": 10000,
|
| 117 |
+
"transformers_version": "4.57.3",
|
| 118 |
+
"use_focal_loss": true,
|
| 119 |
+
"use_pretrained_backbone": false,
|
| 120 |
+
"use_timm_backbone": false,
|
| 121 |
+
"weight_loss_bbox": 5.0,
|
| 122 |
+
"weight_loss_giou": 2.0,
|
| 123 |
+
"weight_loss_vfl": 1.0,
|
| 124 |
+
"with_box_refine": true
|
| 125 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ca0e79574b94b5eeb37515fa3a455741d2621d88bfbacd615409f9a2bac5d99
|
| 3 |
+
size 80498888
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": false,
|
| 5 |
+
"device": null,
|
| 6 |
+
"disable_grouping": null,
|
| 7 |
+
"do_center_crop": null,
|
| 8 |
+
"do_convert_annotations": true,
|
| 9 |
+
"do_convert_rgb": null,
|
| 10 |
+
"do_normalize": false,
|
| 11 |
+
"do_pad": false,
|
| 12 |
+
"do_rescale": true,
|
| 13 |
+
"do_resize": true,
|
| 14 |
+
"format": "coco_detection",
|
| 15 |
+
"image_mean": [
|
| 16 |
+
0.485,
|
| 17 |
+
0.456,
|
| 18 |
+
0.406
|
| 19 |
+
],
|
| 20 |
+
"image_processor_type": "RTDetrImageProcessorFast",
|
| 21 |
+
"image_std": [
|
| 22 |
+
0.229,
|
| 23 |
+
0.224,
|
| 24 |
+
0.225
|
| 25 |
+
],
|
| 26 |
+
"input_data_format": null,
|
| 27 |
+
"pad_size": null,
|
| 28 |
+
"resample": 2,
|
| 29 |
+
"rescale_factor": 0.00392156862745098,
|
| 30 |
+
"return_segmentation_masks": null,
|
| 31 |
+
"return_tensors": null,
|
| 32 |
+
"size": {
|
| 33 |
+
"height": 480,
|
| 34 |
+
"width": 480
|
| 35 |
+
}
|
| 36 |
+
}
|
runs/Jan09_02-26-01_c883a7217238/events.out.tfevents.1767925564.c883a7217238.2363.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:046cab562463e9749c204ff19341a3045b3fab6da1b395cfe9daf319cdd2d435
|
| 3 |
+
size 9016
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f165b8a0cfcc70dd1ef3b03d31d1c2e2989b0773b24fe1901a4e6993f1babe78
|
| 3 |
+
size 5905
|