|
|
--- |
|
|
tags: |
|
|
- image-classification |
|
|
- climate |
|
|
- biology |
|
|
base_model: microsoft/resnet-50 |
|
|
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 |
|
|
license: apache-2.0 |
|
|
metrics: |
|
|
- accuracy |
|
|
- bertscore |
|
|
pipeline_tag: image-classification |
|
|
library_name: transformers |
|
|
--- |
|
|
|
|
|
# Model Trained Using AutoTrain |
|
|
|
|
|
- Problem type: Image Classification |
|
|
|
|
|
<!-- ## Validation Metrics |
|
|
loss: 0.5462027192115784 |
|
|
|
|
|
f1_macro: 0.38996247906197656 |
|
|
|
|
|
f1_micro: 0.737093690248566 |
|
|
|
|
|
f1_weighted: 0.6627689294144399 |
|
|
|
|
|
precision_macro: 0.3467645553924699 |
|
|
|
|
|
precision_micro: 0.737093690248566 |
|
|
|
|
|
precision_weighted: 0.6320379754980795 |
|
|
|
|
|
recall_macro: 0.49719101123595505 |
|
|
|
|
|
recall_micro: 0.737093690248566 |
|
|
|
|
|
recall_weighted: 0.737093690248566 |
|
|
|
|
|
accuracy: 0.737093690248566 --> |
|
|
|
|
|
# Image Classification Model Results (AutoTrain) |
|
|
|
|
|
## Validation Metrics |
|
|
|
|
|
| Metric | Value | |
|
|
|--------|-------| |
|
|
| Loss | 0.5462 | |
|
|
| Accuracy | 0.7371 | |
|
|
|
|
|
### F1 Scores |
|
|
| Type | Value | |
|
|
|------|-------| |
|
|
| Macro | 0.3900 | |
|
|
| Micro | 0.7371 | |
|
|
| Weighted | 0.6628 | |
|
|
|
|
|
### Precision |
|
|
| Type | Value | |
|
|
|------|-------| |
|
|
| Macro | 0.3468 | |
|
|
| Micro | 0.7371 | |
|
|
| Weighted | 0.6320 | |
|
|
|
|
|
### Recall |
|
|
| Type | Value | |
|
|
|------|-------| |
|
|
| Macro | 0.4972 | |
|
|
| Micro | 0.7371 | |
|
|
| Weighted | 0.7371 | |
|
|
|
|
|
|
|
|
## How to use |
|
|
|
|
|
This model is designed for image classification. Here's how you can use it: |
|
|
|
|
|
```python |
|
|
from transformers import AutoImageProcessor, AutoModelForImageClassification |
|
|
import torch |
|
|
from PIL import Image |
|
|
|
|
|
model_name = "eligapris/v-mdd-2000" |
|
|
processor = AutoImageProcessor.from_pretrained(model_name) |
|
|
model = AutoModelForImageClassification.from_pretrained(model_name) |
|
|
|
|
|
image = Image.open("path_to_your_image.jpg") |
|
|
inputs = processor(images=image, return_tensors="pt") |
|
|
|
|
|
with torch.no_grad(): |
|
|
outputs = model(**inputs) |
|
|
|
|
|
logits = outputs.logits |
|
|
predicted_class_idx = logits.argmax(-1).item() |
|
|
print("Predicted class:", model.config.id2label[predicted_class_idx]) |
