Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- ru
|
5 |
+
metrics:
|
6 |
+
- bleu
|
7 |
+
pipeline_tag: image-to-text
|
8 |
+
---
|
9 |
+
# Model Card for Model ID
|
10 |
+
This model generate a description for movie posters ... mm, in principle, for any photo.
|
11 |
+
|
12 |
+
# Model Details
|
13 |
+
|
14 |
+
## Model Description
|
15 |
+
|
16 |
+
This is an encoder decoder model based on [VisionEncoderDecoderModel](https://huggingface.co/docs/transformers/model_doc/vision-encoder-decoder).
|
17 |
+
[Google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) was used as encoder, [DeepPavlov/rubert-base-cased](https://huggingface.co/DeepPavlov/rubert-base-cased) as decoder.
|
18 |
+
|
19 |
+
We refined the model on the dataset with descriptions and movie posters by russian app Kinoposk. Now the model generates descriptions on the jargon of blockbusters =).
|
20 |
+
|
21 |
+
## Model Sources
|
22 |
+
|
23 |
+
- **Repository:** [github.com/slivka83](https://github.com/slivka83/)
|
24 |
+
- **Demo [optional]:** [@MPC_project_bot](https://t.me/MPC_project_bot)
|
25 |
+
|
26 |
+
# Uses
|
27 |
+
|
28 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
29 |
+
|
30 |
+
## Direct Use
|
31 |
+
|
32 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
33 |
+
|
34 |
+
[More Information Needed]
|
35 |
+
|
36 |
+
## Out-of-Scope Use
|
37 |
+
|
38 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
39 |
+
|
40 |
+
[More Information Needed]
|
41 |
+
|
42 |
+
# Bias, Risks, and Limitations
|
43 |
+
|
44 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
45 |
+
|
46 |
+
[More Information Needed]
|
47 |
+
|
48 |
+
## Recommendations
|
49 |
+
|
50 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
51 |
+
|
52 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
53 |
+
|
54 |
+
# Training Details
|
55 |
+
|
56 |
+
## Training Data
|
57 |
+
|
58 |
+
We compiled a dataset from the open source of all Russian-language films for October 2022 - [kinopoisk](https://www.kinopoisk.ru/). Films with very short or very long descriptions were not included in the dataset, films with blank or very small images were excluded too.
|
59 |
+
|
60 |
+
### Preprocessing
|
61 |
+
|
62 |
+
The model was trained on 8 16 GB V100 for 90 hours.
|
63 |
+
|
64 |
+
# Evaluation
|
65 |
+
|
66 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
67 |
+
|
68 |
+
## Testing Data, Factors & Metrics
|
69 |
+
|
70 |
+
### Testing Data
|
71 |
+
|
72 |
+
<!-- This should link to a Data Card if possible. -->
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
### Factors
|
77 |
+
|
78 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
79 |
+
|
80 |
+
[More Information Needed]
|
81 |
+
|
82 |
+
### Metrics
|
83 |
+
|
84 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
85 |
+
|
86 |
+
[More Information Needed]
|
87 |
+
|
88 |
+
## Results
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
### Summary
|
93 |
+
|
94 |
+
|
95 |
+
|
96 |
+
# Model Examination [optional]
|
97 |
+
|
98 |
+
<!-- Relevant interpretability work for the model goes here -->
|
99 |
+
|
100 |
+
[More Information Needed]
|
101 |
+
|
102 |
+
# Environmental Impact
|
103 |
+
|
104 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
105 |
+
|
106 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
107 |
+
|
108 |
+
- **Hardware Type:** [More Information Needed]
|
109 |
+
- **Hours used:** [More Information Needed]
|
110 |
+
- **Cloud Provider:** [More Information Needed]
|
111 |
+
- **Compute Region:** [More Information Needed]
|
112 |
+
- **Carbon Emitted:** [More Information Needed]
|
113 |
+
|
114 |
+
# Technical Specifications [optional]
|
115 |
+
|
116 |
+
## Model Architecture and Objective
|
117 |
+
|
118 |
+
[More Information Needed]
|
119 |
+
|
120 |
+
## Compute Infrastructure
|
121 |
+
|
122 |
+
[More Information Needed]
|
123 |
+
|
124 |
+
### Hardware
|
125 |
+
|
126 |
+
[More Information Needed]
|
127 |
+
|
128 |
+
### Software
|
129 |
+
|
130 |
+
[More Information Needed]
|
131 |
+
|
132 |
+
# Citation [optional]
|
133 |
+
|
134 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
135 |
+
|
136 |
+
**BibTeX:**
|
137 |
+
|
138 |
+
[More Information Needed]
|
139 |
+
|
140 |
+
**APA:**
|
141 |
+
|
142 |
+
[More Information Needed]
|
143 |
+
|
144 |
+
# Glossary [optional]
|
145 |
+
|
146 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
147 |
+
|
148 |
+
[More Information Needed]
|
149 |
+
|
150 |
+
# More Information [optional]
|
151 |
+
|
152 |
+
[More Information Needed]
|
153 |
+
|
154 |
+
# Model Card Authors [optional]
|
155 |
+
|
156 |
+
[More Information Needed]
|
157 |
+
|
158 |
+
# Model Card Contact
|
159 |
+
|
160 |
+
[More Information Needed]
|
161 |
+
|
162 |
+
# How to Get Started with the Model
|
163 |
+
|
164 |
+
Use the code below to get started with the model.
|
165 |
+
|
166 |
+
<details>
|
167 |
+
<summary> Click to expand </summary>
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
</details>
|