|
|
--- |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
# Shot Type |
|
|
|
|
|
This model predicts an image's cinematic shot type [clean single, double, group, over the shoulder, insert, establishing]. The model is a DinoV2 with registers backbone (initiated with `facebook/dinov2-with-registers-large` weights) and trained on a diverse set of five thousand human-annotated images. |
|
|
|
|
|
## How to use: |
|
|
```python |
|
|
|
|
|
import torch |
|
|
from PIL import Image |
|
|
from transformers import AutoImageProcessor |
|
|
from transformers import AutoModelForImageClassification |
|
|
|
|
|
image_processor = AutoImageProcessor.from_pretrained("facebook/dinov2-with-registers-large") |
|
|
model = AutoModelForImageClassification.from_pretrained('aslakey/depth_of_field') |
|
|
model.eval() |
|
|
|
|
|
# Model labels: [clean_single, double, group, over_the_shoulder, insert, establishing] |
|
|
image = Image.open('cinematic_shot.jpg') |
|
|
inputs = image_processor(image, return_tensors="pt") |
|
|
with torch.no_grad(): |
|
|
outputs = model(**inputs) |
|
|
|
|
|
predicted_label = outputs.logits.argmax(-1).item() |
|
|
print(model.config.id2label[predicted_label]) |
|
|
``` |
|
|
|
|
|
## Performance: |
|
|
|
|
|
|
|
|
| Category | Precision | Recall | |
|
|
|----------|-----------|--------| |
|
|
| clean_single | 81% | 89% | |
|
|
| double | 80% | 72% | |
|
|
| group | 91% | 74% | |
|
|
| over the shoulder | 60% | 67% | |
|
|
| establishing | 91% | 77% | |
|
|
|
