tags:
- autotrain
- vision
- image-classification
datasets:
- fsuarez/autotrain-data-logo-identifier
widget:
- src: >-
https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
example_title: Tiger
- src: >-
https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
example_title: Teapot
- src: >-
https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
example_title: Palace
co2_eq_emissions:
emissions: 0.060824697813101125
📒 logo-identifier-model
This model has been trained on a dataset called "LogoIdentifier" for multi-class classification of logos from 57 renowned brands and companies. These brands encompass a wide spectrum of industries and recognition, ranging from global giants like Coca-Cola, Coleman, Google, IBM, Nike, Pepsi, and many others. Each brand is thoughtfully organized into its designated subfolder, housing a comprehensive set of logo images for precise and accurate classification. Whether you're identifying iconic logos or exploring the branding diversity of these 57 famous names, this model is your go-to solution for logo recognition and classification.
🧪 Dataset Content
- The dataset includes logos from various brands and companies.
- The dataset is organized into subfolders, each corresponding to a specific brand or company.
- It contains a wide range of brand logos, including Acer, Acura, Adidas, Samsung, Lenovo, McDonald's, Java, and many more.
- Each brand or company in the dataset is associated with a numerical value, likely representing the number of images available for that brand.
The model has been trained to recognize and classify logos into their respective brand categories based on the images provided in the dataset.
| Company | Quantity of images |
|---|---|
| Acer | 67 |
| Acura | 74 |
| Addidas | 90 |
| Ades | 36 |
| Adio | 63 |
| Cadillac | 69 |
| CalvinKlein | 65 |
| Canon | 59 |
| Cocacola | 40 |
| CocaColaZero | 91 |
| Coleman | 57 |
| Converse | 60 |
| CornFlakes | 62 |
| DominossPizza | 99 |
| Excel | 88 |
| Gillette | 86 |
| GMC | 75 |
| 93 | |
| HardRockCafe | 93 |
| HBO | 103 |
| Heineken | 84 |
| HewlettPackard | 81 |
| Hp | 87 |
| Huawei | 84 |
| Hyundai | 84 |
| IBM | 84 |
| Java | 62 |
| KFC | 84 |
| Kia | 76 |
| Kingston | 79 |
| Lenovo | 82 |
| LG | 95 |
| Lipton | 94 |
| Mattel | 77 |
| McDonalds | 98 |
| MercedesBenz | 94 |
| Motorola | 86 |
| Nestle | 94 |
| Nickelodeon | 74 |
| Nike | 50 |
| Pennzoil | 82 |
| Pepsi | 93 |
| Peugeot | 60 |
| Porsche | 71 |
| Samsung | 96 |
| SchneiderElectric | 42 |
| Shell | 58 |
To use this model for brand logo identification, you can make use of the Hugging Face Transformers library and load the model using its model ID (90194144191). You can then input an image of a brand logo, and the model should be able to predict the brand it belongs to based on its training.
🤗 Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 90194144191
- CO2 Emissions (in grams): 0.0608
📐 Validation Metrics
- Loss: 0.300
- Accuracy: 0.924
- Macro F1: 0.924
- Micro F1: 0.924
- Weighted F1: 0.922
- Macro Precision: 0.930
- Micro Precision: 0.924
- Weighted Precision: 0.928
- Macro Recall: 0.924
- Micro Recall: 0.924
- Weighted Recall: 0.924