Commit
•
8baa378
1
Parent(s):
22bf6a9
Upload 8 files
Browse files- README.md +63 -0
- config.json +172 -0
- preprocessor_config.json +17 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,3 +1,66 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- image-captioning
|
5 |
+
languages:
|
6 |
+
- en
|
7 |
+
pipeline_tag: image-to-text
|
8 |
+
datasets:
|
9 |
+
- michelecafagna26/hl
|
10 |
+
language:
|
11 |
+
- en
|
12 |
+
metrics:
|
13 |
+
- sacrebleu
|
14 |
+
- rouge
|
15 |
+
library_name: transformers
|
16 |
---
|
17 |
+
## BLIP-base fine-tuned for Narrative Image Captioning
|
18 |
+
|
19 |
+
[BLIP](https://arxiv.org/abs/2201.12086) base trained on the [HL Narratives](https://huggingface.co/datasets/michelecafagna26/hl-narratives) for **high-level narrative descriptions generation**
|
20 |
+
|
21 |
+
## Model fine-tuning 🏋️
|
22 |
+
|
23 |
+
- Trained for a 3 epochs using a
|
24 |
+
- lr: 5e−5
|
25 |
+
- Adam optimizer
|
26 |
+
- half-precision (fp16)
|
27 |
+
|
28 |
+
## Test set metrics 🧾
|
29 |
+
|
30 |
+
| Cider | SacreBLEU | Rouge-L|
|
31 |
+
|--------|------------|--------|
|
32 |
+
| 79.39 | 11.70 | 26.17 |
|
33 |
+
|
34 |
+
## Model in Action 🚀
|
35 |
+
|
36 |
+
```python
|
37 |
+
import requests
|
38 |
+
from PIL import Image
|
39 |
+
from transformers import BlipProcessor, BlipForConditionalGeneration
|
40 |
+
|
41 |
+
processor = BlipProcessor.from_pretrained("blip-base-captioning-ft-hl-narratives")
|
42 |
+
model = BlipForConditionalGeneration.from_pretrained("blip-base-captioning-ft-hl-narratives").to("cuda")
|
43 |
+
|
44 |
+
img_url = 'https://datasets-server.huggingface.co/assets/michelecafagna26/hl/--/default/train/0/image/image.jpg'
|
45 |
+
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
|
46 |
+
|
47 |
+
|
48 |
+
inputs = processor(raw_image, return_tensors="pt").to("cuda")
|
49 |
+
pixel_values = inputs.pixel_values
|
50 |
+
|
51 |
+
generated_ids = model.generate(pixel_values=pixel_values, max_length=50,
|
52 |
+
do_sample=True,
|
53 |
+
top_k=120,
|
54 |
+
top_p=0.9,
|
55 |
+
early_stopping=True,
|
56 |
+
num_return_sequences=1)
|
57 |
+
|
58 |
+
processor.batch_decode(generated_ids, skip_special_tokens=True)
|
59 |
+
|
60 |
+
>>>
|
61 |
+
```
|
62 |
+
|
63 |
+
## BibTex and citation info
|
64 |
+
|
65 |
+
```BibTeX
|
66 |
+
```
|
config.json
ADDED
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": "637f179f73831e02cf6140cd1c7c5d34035a4387",
|
3 |
+
"_name_or_path": "Salesforce/blip-image-captioning-base",
|
4 |
+
"architectures": [
|
5 |
+
"BlipForConditionalGeneration"
|
6 |
+
],
|
7 |
+
"image_text_hidden_size": 256,
|
8 |
+
"initializer_factor": 1.0,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"logit_scale_init_value": 2.6592,
|
11 |
+
"model_type": "blip",
|
12 |
+
"projection_dim": 512,
|
13 |
+
"text_config": {
|
14 |
+
"_name_or_path": "",
|
15 |
+
"add_cross_attention": false,
|
16 |
+
"architectures": null,
|
17 |
+
"attention_probs_dropout_prob": 0.0,
|
18 |
+
"bad_words_ids": null,
|
19 |
+
"begin_suppress_tokens": null,
|
20 |
+
"bos_token_id": 30522,
|
21 |
+
"chunk_size_feed_forward": 0,
|
22 |
+
"cross_attention_hidden_size": null,
|
23 |
+
"decoder_start_token_id": null,
|
24 |
+
"diversity_penalty": 0.0,
|
25 |
+
"do_sample": false,
|
26 |
+
"early_stopping": false,
|
27 |
+
"encoder_hidden_size": 768,
|
28 |
+
"encoder_no_repeat_ngram_size": 0,
|
29 |
+
"eos_token_id": 2,
|
30 |
+
"exponential_decay_length_penalty": null,
|
31 |
+
"finetuning_task": null,
|
32 |
+
"forced_bos_token_id": null,
|
33 |
+
"forced_eos_token_id": null,
|
34 |
+
"hidden_act": "gelu",
|
35 |
+
"hidden_dropout_prob": 0.0,
|
36 |
+
"hidden_size": 768,
|
37 |
+
"id2label": {
|
38 |
+
"0": "LABEL_0",
|
39 |
+
"1": "LABEL_1"
|
40 |
+
},
|
41 |
+
"initializer_factor": 1.0,
|
42 |
+
"initializer_range": 0.02,
|
43 |
+
"intermediate_size": 3072,
|
44 |
+
"is_decoder": true,
|
45 |
+
"is_encoder_decoder": false,
|
46 |
+
"label2id": {
|
47 |
+
"LABEL_0": 0,
|
48 |
+
"LABEL_1": 1
|
49 |
+
},
|
50 |
+
"layer_norm_eps": 1e-12,
|
51 |
+
"length_penalty": 1.0,
|
52 |
+
"max_length": 20,
|
53 |
+
"max_position_embeddings": 512,
|
54 |
+
"min_length": 0,
|
55 |
+
"model_type": "blip_text_model",
|
56 |
+
"no_repeat_ngram_size": 0,
|
57 |
+
"num_attention_heads": 12,
|
58 |
+
"num_beam_groups": 1,
|
59 |
+
"num_beams": 1,
|
60 |
+
"num_hidden_layers": 12,
|
61 |
+
"num_return_sequences": 1,
|
62 |
+
"output_attentions": false,
|
63 |
+
"output_hidden_states": false,
|
64 |
+
"output_scores": false,
|
65 |
+
"pad_token_id": 0,
|
66 |
+
"prefix": null,
|
67 |
+
"problem_type": null,
|
68 |
+
"projection_dim": 768,
|
69 |
+
"pruned_heads": {},
|
70 |
+
"remove_invalid_values": false,
|
71 |
+
"repetition_penalty": 1.0,
|
72 |
+
"return_dict": true,
|
73 |
+
"return_dict_in_generate": false,
|
74 |
+
"sep_token_id": 102,
|
75 |
+
"suppress_tokens": null,
|
76 |
+
"task_specific_params": null,
|
77 |
+
"temperature": 1.0,
|
78 |
+
"tf_legacy_loss": false,
|
79 |
+
"tie_encoder_decoder": false,
|
80 |
+
"tie_word_embeddings": true,
|
81 |
+
"tokenizer_class": null,
|
82 |
+
"top_k": 50,
|
83 |
+
"top_p": 1.0,
|
84 |
+
"torch_dtype": null,
|
85 |
+
"torchscript": false,
|
86 |
+
"transformers_version": "4.30.0.dev0",
|
87 |
+
"typical_p": 1.0,
|
88 |
+
"use_bfloat16": false,
|
89 |
+
"use_cache": true,
|
90 |
+
"vocab_size": 30524
|
91 |
+
},
|
92 |
+
"torch_dtype": "float32",
|
93 |
+
"transformers_version": null,
|
94 |
+
"vision_config": {
|
95 |
+
"_name_or_path": "",
|
96 |
+
"add_cross_attention": false,
|
97 |
+
"architectures": null,
|
98 |
+
"attention_dropout": 0.0,
|
99 |
+
"bad_words_ids": null,
|
100 |
+
"begin_suppress_tokens": null,
|
101 |
+
"bos_token_id": null,
|
102 |
+
"chunk_size_feed_forward": 0,
|
103 |
+
"cross_attention_hidden_size": null,
|
104 |
+
"decoder_start_token_id": null,
|
105 |
+
"diversity_penalty": 0.0,
|
106 |
+
"do_sample": false,
|
107 |
+
"dropout": 0.0,
|
108 |
+
"early_stopping": false,
|
109 |
+
"encoder_no_repeat_ngram_size": 0,
|
110 |
+
"eos_token_id": null,
|
111 |
+
"exponential_decay_length_penalty": null,
|
112 |
+
"finetuning_task": null,
|
113 |
+
"forced_bos_token_id": null,
|
114 |
+
"forced_eos_token_id": null,
|
115 |
+
"hidden_act": "gelu",
|
116 |
+
"hidden_size": 768,
|
117 |
+
"id2label": {
|
118 |
+
"0": "LABEL_0",
|
119 |
+
"1": "LABEL_1"
|
120 |
+
},
|
121 |
+
"image_size": 384,
|
122 |
+
"initializer_factor": 1.0,
|
123 |
+
"initializer_range": 0.02,
|
124 |
+
"intermediate_size": 3072,
|
125 |
+
"is_decoder": false,
|
126 |
+
"is_encoder_decoder": false,
|
127 |
+
"label2id": {
|
128 |
+
"LABEL_0": 0,
|
129 |
+
"LABEL_1": 1
|
130 |
+
},
|
131 |
+
"layer_norm_eps": 1e-05,
|
132 |
+
"length_penalty": 1.0,
|
133 |
+
"max_length": 20,
|
134 |
+
"min_length": 0,
|
135 |
+
"model_type": "blip_vision_model",
|
136 |
+
"no_repeat_ngram_size": 0,
|
137 |
+
"num_attention_heads": 12,
|
138 |
+
"num_beam_groups": 1,
|
139 |
+
"num_beams": 1,
|
140 |
+
"num_channels": 3,
|
141 |
+
"num_hidden_layers": 12,
|
142 |
+
"num_return_sequences": 1,
|
143 |
+
"output_attentions": false,
|
144 |
+
"output_hidden_states": false,
|
145 |
+
"output_scores": false,
|
146 |
+
"pad_token_id": null,
|
147 |
+
"patch_size": 16,
|
148 |
+
"prefix": null,
|
149 |
+
"problem_type": null,
|
150 |
+
"projection_dim": 512,
|
151 |
+
"pruned_heads": {},
|
152 |
+
"remove_invalid_values": false,
|
153 |
+
"repetition_penalty": 1.0,
|
154 |
+
"return_dict": true,
|
155 |
+
"return_dict_in_generate": false,
|
156 |
+
"sep_token_id": null,
|
157 |
+
"suppress_tokens": null,
|
158 |
+
"task_specific_params": null,
|
159 |
+
"temperature": 1.0,
|
160 |
+
"tf_legacy_loss": false,
|
161 |
+
"tie_encoder_decoder": false,
|
162 |
+
"tie_word_embeddings": true,
|
163 |
+
"tokenizer_class": null,
|
164 |
+
"top_k": 50,
|
165 |
+
"top_p": 1.0,
|
166 |
+
"torch_dtype": null,
|
167 |
+
"torchscript": false,
|
168 |
+
"transformers_version": "4.30.0.dev0",
|
169 |
+
"typical_p": 1.0,
|
170 |
+
"use_bfloat16": false
|
171 |
+
}
|
172 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_resize": true,
|
4 |
+
"image_mean": [
|
5 |
+
0.48145466,
|
6 |
+
0.4578275,
|
7 |
+
0.40821073
|
8 |
+
],
|
9 |
+
"image_processor_type": "BlipImageProcessor",
|
10 |
+
"image_std": [
|
11 |
+
0.26862954,
|
12 |
+
0.26130258,
|
13 |
+
0.27577711
|
14 |
+
],
|
15 |
+
"processor_class": "BlipProcessor",
|
16 |
+
"size": 384
|
17 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9846aa27f2554ddac64c51266e09b36fb7cd4720639417d1d822b43dc95a827b
|
3 |
+
size 989827505
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"name_or_path": "bert-base-uncased",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"processor_class": "BlipProcessor",
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "BertTokenizer",
|
16 |
+
"unk_token": "[UNK]",
|
17 |
+
"model_input_names": [
|
18 |
+
"input_ids",
|
19 |
+
"attention_mask"
|
20 |
+
]
|
21 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|