Training in progress, epoch 1
Browse files- config.json +28 -85
- model.safetensors +2 -2
- preprocessor_config.json +5 -5
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,98 +1,41 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
-
"activation_dropout": 0.0,
|
| 4 |
-
"activation_function": "silu",
|
| 5 |
-
"anchor_image_size": null,
|
| 6 |
"architectures": [
|
| 7 |
-
"
|
| 8 |
],
|
| 9 |
-
"
|
| 10 |
-
"auxiliary_loss":
|
| 11 |
-
"
|
| 12 |
-
"
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
2,
|
| 21 |
-
3,
|
| 22 |
-
4
|
| 23 |
-
]
|
| 24 |
-
},
|
| 25 |
-
"backbone_kwargs": null,
|
| 26 |
-
"batch_norm_eps": 1e-05,
|
| 27 |
-
"box_noise_scale": 1.0,
|
| 28 |
-
"d_model": 256,
|
| 29 |
-
"decoder_activation_function": "relu",
|
| 30 |
-
"decoder_attention_heads": 8,
|
| 31 |
-
"decoder_ffn_dim": 1024,
|
| 32 |
-
"decoder_in_channels": [
|
| 33 |
-
256,
|
| 34 |
-
256,
|
| 35 |
-
256
|
| 36 |
-
],
|
| 37 |
-
"decoder_layers": 6,
|
| 38 |
-
"decoder_n_points": 4,
|
| 39 |
-
"disable_custom_kernels": true,
|
| 40 |
-
"dropout": 0.0,
|
| 41 |
-
"encode_proj_layers": [
|
| 42 |
-
2
|
| 43 |
-
],
|
| 44 |
-
"encoder_activation_function": "gelu",
|
| 45 |
-
"encoder_attention_heads": 8,
|
| 46 |
-
"encoder_ffn_dim": 1024,
|
| 47 |
-
"encoder_hidden_dim": 256,
|
| 48 |
-
"encoder_in_channels": [
|
| 49 |
-
512,
|
| 50 |
-
1024,
|
| 51 |
-
2048
|
| 52 |
-
],
|
| 53 |
-
"encoder_layers": 1,
|
| 54 |
-
"eos_coefficient": 0.0001,
|
| 55 |
-
"eval_size": null,
|
| 56 |
-
"feat_strides": [
|
| 57 |
-
8,
|
| 58 |
-
16,
|
| 59 |
-
32
|
| 60 |
-
],
|
| 61 |
-
"focal_loss_alpha": 0.75,
|
| 62 |
-
"focal_loss_gamma": 2.0,
|
| 63 |
-
"freeze_backbone_batch_norms": true,
|
| 64 |
-
"hidden_expansion": 1.0,
|
| 65 |
"id2label": {
|
| 66 |
"0": "logos",
|
| 67 |
"1": "logos"
|
| 68 |
},
|
| 69 |
-
"
|
| 70 |
-
|
| 71 |
-
|
|
|
|
|
|
|
|
|
|
| 72 |
"label2id": {
|
| 73 |
"logos": 1
|
| 74 |
},
|
| 75 |
-
"
|
| 76 |
-
"
|
| 77 |
-
"
|
| 78 |
-
"
|
| 79 |
-
"
|
| 80 |
-
"
|
| 81 |
-
"
|
| 82 |
-
"
|
| 83 |
-
"model_type": "rt_detr",
|
| 84 |
-
"normalize_before": false,
|
| 85 |
-
"num_denoising": 100,
|
| 86 |
-
"num_feature_levels": 3,
|
| 87 |
-
"num_queries": 100,
|
| 88 |
-
"positional_encoding_temperature": 10000,
|
| 89 |
"torch_dtype": "float32",
|
| 90 |
"transformers_version": "4.49.0.dev0",
|
| 91 |
-
"
|
| 92 |
-
"use_pretrained_backbone": false,
|
| 93 |
-
"use_timm_backbone": false,
|
| 94 |
-
"weight_loss_bbox": 5.0,
|
| 95 |
-
"weight_loss_giou": 2.0,
|
| 96 |
-
"weight_loss_vfl": 1.0,
|
| 97 |
-
"with_box_refine": true
|
| 98 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "hustvl/yolos-small",
|
|
|
|
|
|
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
+
"YolosForObjectDetection"
|
| 5 |
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"auxiliary_loss": false,
|
| 8 |
+
"bbox_cost": 5,
|
| 9 |
+
"bbox_loss_coefficient": 5,
|
| 10 |
+
"class_cost": 1,
|
| 11 |
+
"eos_coefficient": 0.1,
|
| 12 |
+
"giou_cost": 2,
|
| 13 |
+
"giou_loss_coefficient": 2,
|
| 14 |
+
"hidden_act": "gelu",
|
| 15 |
+
"hidden_dropout_prob": 0.0,
|
| 16 |
+
"hidden_size": 384,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"id2label": {
|
| 18 |
"0": "logos",
|
| 19 |
"1": "logos"
|
| 20 |
},
|
| 21 |
+
"image_size": [
|
| 22 |
+
512,
|
| 23 |
+
864
|
| 24 |
+
],
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 1536,
|
| 27 |
"label2id": {
|
| 28 |
"logos": 1
|
| 29 |
},
|
| 30 |
+
"layer_norm_eps": 1e-12,
|
| 31 |
+
"model_type": "yolos",
|
| 32 |
+
"num_attention_heads": 6,
|
| 33 |
+
"num_channels": 3,
|
| 34 |
+
"num_detection_tokens": 100,
|
| 35 |
+
"num_hidden_layers": 12,
|
| 36 |
+
"patch_size": 16,
|
| 37 |
+
"qkv_bias": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
"torch_dtype": "float32",
|
| 39 |
"transformers_version": "4.49.0.dev0",
|
| 40 |
+
"use_mid_position_embeddings": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b4ace90714f68c1152bd750bf67837715f561ef54ce6d7046a6e8bd7c9688d9
|
| 3 |
+
size 122626212
|
preprocessor_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"do_convert_annotations": true,
|
| 3 |
-
"do_normalize":
|
| 4 |
-
"do_pad":
|
| 5 |
"do_rescale": true,
|
| 6 |
"do_resize": true,
|
| 7 |
"format": "coco_detection",
|
|
@@ -10,7 +10,7 @@
|
|
| 10 |
0.456,
|
| 11 |
0.406
|
| 12 |
],
|
| 13 |
-
"image_processor_type": "
|
| 14 |
"image_std": [
|
| 15 |
0.229,
|
| 16 |
0.224,
|
|
@@ -20,7 +20,7 @@
|
|
| 20 |
"resample": 2,
|
| 21 |
"rescale_factor": 0.00392156862745098,
|
| 22 |
"size": {
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
}
|
| 26 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"do_convert_annotations": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pad": true,
|
| 5 |
"do_rescale": true,
|
| 6 |
"do_resize": true,
|
| 7 |
"format": "coco_detection",
|
|
|
|
| 10 |
0.456,
|
| 11 |
0.406
|
| 12 |
],
|
| 13 |
+
"image_processor_type": "YolosImageProcessor",
|
| 14 |
"image_std": [
|
| 15 |
0.229,
|
| 16 |
0.224,
|
|
|
|
| 20 |
"resample": 2,
|
| 21 |
"rescale_factor": 0.00392156862745098,
|
| 22 |
"size": {
|
| 23 |
+
"longest_edge": 1333,
|
| 24 |
+
"shortest_edge": 800
|
| 25 |
}
|
| 26 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1ea256e36e5887705954b5466860ad6f26877d8523a57b6721a0663ce8aa569
|
| 3 |
size 5368
|