End of training
Browse files- README.md +65 -0
- config.json +150 -0
- model.safetensors +3 -0
- preprocessor_config.json +25 -0
- runs/Apr21_11-49-02_8e9a95c1cbc0/events.out.tfevents.1713700143.8e9a95c1cbc0.1293.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/detr-resnet-50
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: detr
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# detr
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.9448
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.0001
|
38 |
+
- train_batch_size: 64
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 3
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 2.6853 | 0.32 | 50 | 1.8717 |
|
50 |
+
| 1.6419 | 0.64 | 100 | 1.4752 |
|
51 |
+
| 1.4029 | 0.96 | 150 | 1.2728 |
|
52 |
+
| 1.2596 | 1.27 | 200 | 1.1683 |
|
53 |
+
| 1.1761 | 1.59 | 250 | 1.0847 |
|
54 |
+
| 1.106 | 1.91 | 300 | 1.0396 |
|
55 |
+
| 1.0586 | 2.23 | 350 | 0.9886 |
|
56 |
+
| 1.0258 | 2.55 | 400 | 0.9653 |
|
57 |
+
| 1.0151 | 2.87 | 450 | 0.9448 |
|
58 |
+
|
59 |
+
|
60 |
+
### Framework versions
|
61 |
+
|
62 |
+
- Transformers 4.38.2
|
63 |
+
- Pytorch 2.2.1+cu121
|
64 |
+
- Datasets 2.19.0
|
65 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/detr-resnet-50",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"DetrForObjectDetection"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"auxiliary_loss": false,
|
10 |
+
"backbone": null,
|
11 |
+
"backbone_config": {
|
12 |
+
"_name_or_path": "",
|
13 |
+
"add_cross_attention": false,
|
14 |
+
"architectures": null,
|
15 |
+
"bad_words_ids": null,
|
16 |
+
"begin_suppress_tokens": null,
|
17 |
+
"bos_token_id": null,
|
18 |
+
"chunk_size_feed_forward": 0,
|
19 |
+
"cross_attention_hidden_size": null,
|
20 |
+
"decoder_start_token_id": null,
|
21 |
+
"depths": [
|
22 |
+
3,
|
23 |
+
4,
|
24 |
+
6,
|
25 |
+
3
|
26 |
+
],
|
27 |
+
"diversity_penalty": 0.0,
|
28 |
+
"do_sample": false,
|
29 |
+
"downsample_in_bottleneck": false,
|
30 |
+
"downsample_in_first_stage": false,
|
31 |
+
"early_stopping": false,
|
32 |
+
"embedding_size": 64,
|
33 |
+
"encoder_no_repeat_ngram_size": 0,
|
34 |
+
"eos_token_id": null,
|
35 |
+
"exponential_decay_length_penalty": null,
|
36 |
+
"finetuning_task": null,
|
37 |
+
"forced_bos_token_id": null,
|
38 |
+
"forced_eos_token_id": null,
|
39 |
+
"hidden_act": "relu",
|
40 |
+
"hidden_sizes": [
|
41 |
+
256,
|
42 |
+
512,
|
43 |
+
1024,
|
44 |
+
2048
|
45 |
+
],
|
46 |
+
"id2label": {
|
47 |
+
"0": "LABEL_0",
|
48 |
+
"1": "LABEL_1"
|
49 |
+
},
|
50 |
+
"is_decoder": false,
|
51 |
+
"is_encoder_decoder": false,
|
52 |
+
"label2id": {
|
53 |
+
"LABEL_0": 0,
|
54 |
+
"LABEL_1": 1
|
55 |
+
},
|
56 |
+
"layer_type": "bottleneck",
|
57 |
+
"length_penalty": 1.0,
|
58 |
+
"max_length": 20,
|
59 |
+
"min_length": 0,
|
60 |
+
"model_type": "resnet",
|
61 |
+
"no_repeat_ngram_size": 0,
|
62 |
+
"num_beam_groups": 1,
|
63 |
+
"num_beams": 1,
|
64 |
+
"num_channels": 3,
|
65 |
+
"num_return_sequences": 1,
|
66 |
+
"out_features": [
|
67 |
+
"stage4"
|
68 |
+
],
|
69 |
+
"out_indices": [
|
70 |
+
4
|
71 |
+
],
|
72 |
+
"output_attentions": false,
|
73 |
+
"output_hidden_states": false,
|
74 |
+
"output_scores": false,
|
75 |
+
"pad_token_id": null,
|
76 |
+
"prefix": null,
|
77 |
+
"problem_type": null,
|
78 |
+
"pruned_heads": {},
|
79 |
+
"remove_invalid_values": false,
|
80 |
+
"repetition_penalty": 1.0,
|
81 |
+
"return_dict": true,
|
82 |
+
"return_dict_in_generate": false,
|
83 |
+
"sep_token_id": null,
|
84 |
+
"stage_names": [
|
85 |
+
"stem",
|
86 |
+
"stage1",
|
87 |
+
"stage2",
|
88 |
+
"stage3",
|
89 |
+
"stage4"
|
90 |
+
],
|
91 |
+
"suppress_tokens": null,
|
92 |
+
"task_specific_params": null,
|
93 |
+
"temperature": 1.0,
|
94 |
+
"tf_legacy_loss": false,
|
95 |
+
"tie_encoder_decoder": false,
|
96 |
+
"tie_word_embeddings": true,
|
97 |
+
"tokenizer_class": null,
|
98 |
+
"top_k": 50,
|
99 |
+
"top_p": 1.0,
|
100 |
+
"torch_dtype": null,
|
101 |
+
"torchscript": false,
|
102 |
+
"typical_p": 1.0,
|
103 |
+
"use_bfloat16": false
|
104 |
+
},
|
105 |
+
"backbone_kwargs": null,
|
106 |
+
"bbox_cost": 5,
|
107 |
+
"bbox_loss_coefficient": 5,
|
108 |
+
"class_cost": 1,
|
109 |
+
"d_model": 256,
|
110 |
+
"decoder_attention_heads": 8,
|
111 |
+
"decoder_ffn_dim": 2048,
|
112 |
+
"decoder_layerdrop": 0.0,
|
113 |
+
"decoder_layers": 6,
|
114 |
+
"dice_loss_coefficient": 1,
|
115 |
+
"dilation": null,
|
116 |
+
"dropout": 0.1,
|
117 |
+
"encoder_attention_heads": 8,
|
118 |
+
"encoder_ffn_dim": 2048,
|
119 |
+
"encoder_layerdrop": 0.0,
|
120 |
+
"encoder_layers": 6,
|
121 |
+
"eos_coefficient": 0.1,
|
122 |
+
"giou_cost": 2,
|
123 |
+
"giou_loss_coefficient": 2,
|
124 |
+
"id2label": {
|
125 |
+
"0": "clothing",
|
126 |
+
"1": "shoes",
|
127 |
+
"2": "bags",
|
128 |
+
"3": "accessories"
|
129 |
+
},
|
130 |
+
"init_std": 0.02,
|
131 |
+
"init_xavier_std": 1.0,
|
132 |
+
"is_encoder_decoder": true,
|
133 |
+
"label2id": {
|
134 |
+
"accessories": 3,
|
135 |
+
"bags": 2,
|
136 |
+
"clothing": 0,
|
137 |
+
"shoes": 1
|
138 |
+
},
|
139 |
+
"mask_loss_coefficient": 1,
|
140 |
+
"model_type": "detr",
|
141 |
+
"num_channels": 3,
|
142 |
+
"num_hidden_layers": 6,
|
143 |
+
"num_queries": 100,
|
144 |
+
"position_embedding_type": "sine",
|
145 |
+
"scale_embedding": false,
|
146 |
+
"torch_dtype": "float32",
|
147 |
+
"transformers_version": "4.38.2",
|
148 |
+
"use_pretrained_backbone": null,
|
149 |
+
"use_timm_backbone": false
|
150 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2face0da1a7edad34659d8f2ecb45f6cf718a830b00291f56401da52f4fcdada
|
3 |
+
size 166506812
|
preprocessor_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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",
|
8 |
+
"image_mean": [
|
9 |
+
0.485,
|
10 |
+
0.456,
|
11 |
+
0.406
|
12 |
+
],
|
13 |
+
"image_processor_type": "DetrImageProcessor",
|
14 |
+
"image_std": [
|
15 |
+
0.229,
|
16 |
+
0.224,
|
17 |
+
0.225
|
18 |
+
],
|
19 |
+
"resample": 2,
|
20 |
+
"rescale_factor": 0.00392156862745098,
|
21 |
+
"size": {
|
22 |
+
"longest_edge": 1333,
|
23 |
+
"shortest_edge": 800
|
24 |
+
}
|
25 |
+
}
|
runs/Apr21_11-49-02_8e9a95c1cbc0/events.out.tfevents.1713700143.8e9a95c1cbc0.1293.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b99bac8807e9c8b16a465fdafd1e724b54c33c0d223a9c3b72e02e4a40a3d8ad
|
3 |
+
size 12052
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2438f1bace1bb955af03e445f3b3eae802c11c43b460828b67124b47c7fe26c2
|
3 |
+
size 4856
|