Gilsson commited on
Commit
ef8306e
·
verified ·
1 Parent(s): e3e5e38

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,67 +1,42 @@
1
  {
2
- "_name_or_path": "PekingU/rtdetr_r50vd_coco_o365",
3
  "activation_dropout": 0.0,
4
- "activation_function": "silu",
5
- "anchor_image_size": null,
6
  "architectures": [
7
- "RTDetrForObjectDetection"
8
  ],
9
  "attention_dropout": 0.0,
10
- "auxiliary_loss": true,
11
- "backbone": null,
12
- "backbone_config": {
13
- "model_type": "rt_detr_resnet",
14
- "out_features": [
15
- "stage2",
16
- "stage3",
17
- "stage4"
18
- ],
19
  "out_indices": [
 
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": "acrid",
67
  "1": "ancient wisp",
@@ -112,8 +87,8 @@
112
  "46": "wisp",
113
  "47": "young vagrant"
114
  },
115
- "initializer_bias_prior_prob": null,
116
- "initializer_range": 0.01,
117
  "is_encoder_decoder": true,
118
  "label2id": {
119
  "acrid": 0,
@@ -165,27 +140,16 @@
165
  "wisp": 46,
166
  "young vagrant": 47
167
  },
168
- "label_noise_ratio": 0.5,
169
- "layer_norm_eps": 1e-05,
170
- "learn_initial_query": false,
171
- "matcher_alpha": 0.25,
172
- "matcher_bbox_cost": 5.0,
173
- "matcher_class_cost": 2.0,
174
- "matcher_gamma": 2.0,
175
- "matcher_giou_cost": 2.0,
176
- "model_type": "rt_detr",
177
- "normalize_before": false,
178
- "num_denoising": 100,
179
- "num_feature_levels": 3,
180
  "num_queries": 300,
181
- "positional_encoding_temperature": 10000,
 
182
  "torch_dtype": "float32",
183
  "transformers_version": "4.46.1",
184
- "use_focal_loss": true,
185
- "use_pretrained_backbone": false,
186
- "use_timm_backbone": false,
187
- "weight_loss_bbox": 5.0,
188
- "weight_loss_giou": 2.0,
189
- "weight_loss_vfl": 1.0,
190
- "with_box_refine": true
191
  }
 
1
  {
2
+ "_name_or_path": "microsoft/conditional-detr-resnet-50",
3
  "activation_dropout": 0.0,
4
+ "activation_function": "relu",
 
5
  "architectures": [
6
+ "ConditionalDetrForObjectDetection"
7
  ],
8
  "attention_dropout": 0.0,
9
+ "auxiliary_loss": false,
10
+ "backbone": "resnet50",
11
+ "backbone_config": null,
12
+ "backbone_kwargs": {
13
+ "in_chans": 3,
 
 
 
 
14
  "out_indices": [
15
+ 1,
16
  2,
17
  3,
18
  4
19
  ]
20
  },
21
+ "bbox_cost": 5,
22
+ "bbox_loss_coefficient": 5,
23
+ "class_cost": 2,
24
+ "cls_loss_coefficient": 2,
25
  "d_model": 256,
 
26
  "decoder_attention_heads": 8,
27
+ "decoder_ffn_dim": 2048,
28
+ "decoder_layerdrop": 0.0,
 
 
 
 
29
  "decoder_layers": 6,
30
+ "dice_loss_coefficient": 1,
31
+ "dilation": false,
32
+ "dropout": 0.1,
 
 
 
 
33
  "encoder_attention_heads": 8,
34
+ "encoder_ffn_dim": 2048,
35
+ "encoder_layerdrop": 0.0,
36
+ "encoder_layers": 6,
37
+ "focal_alpha": 0.25,
38
+ "giou_cost": 2,
39
+ "giou_loss_coefficient": 2,
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  "id2label": {
41
  "0": "acrid",
42
  "1": "ancient wisp",
 
87
  "46": "wisp",
88
  "47": "young vagrant"
89
  },
90
+ "init_std": 0.02,
91
+ "init_xavier_std": 1.0,
92
  "is_encoder_decoder": true,
93
  "label2id": {
94
  "acrid": 0,
 
140
  "wisp": 46,
141
  "young vagrant": 47
142
  },
143
+ "mask_loss_coefficient": 1,
144
+ "max_position_embeddings": 1024,
145
+ "model_type": "conditional_detr",
146
+ "num_channels": 3,
147
+ "num_hidden_layers": 6,
 
 
 
 
 
 
 
148
  "num_queries": 300,
149
+ "position_embedding_type": "sine",
150
+ "scale_embedding": false,
151
  "torch_dtype": "float32",
152
  "transformers_version": "4.46.1",
153
+ "use_pretrained_backbone": true,
154
+ "use_timm_backbone": true
 
 
 
 
 
155
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57b37a8c940180e266c95181d9594d51f24f8966e17b9bb7f0009e3fadfc86ed
3
- size 171912816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f068eb36627e2159a747a0e5fe9f201dd1e2a546c600a4d704af136344cba41e
3
+ size 174124000
preprocessor_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "do_convert_annotations": true,
3
- "do_normalize": false,
4
- "do_pad": false,
5
  "do_rescale": true,
6
  "do_resize": true,
7
  "format": "coco_detection",
 
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",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b835d3156f018c42ef8524531e8c7759db3f56960fab4aaafee7c08484687ef8
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1196f04d8755b00d07cd99850502fb01bacacd58760e8acb7163628ec9b4a6eb
3
  size 5240