|
|
--- |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
# Camera Level |
|
|
|
|
|
This model predicts an image's cinematic camera level [ground, hip, shoulder, eye, aerial]. 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/camera_level') |
|
|
model.eval() |
|
|
|
|
|
# Model labels: [ground, hip, shoulder, eye, aerial] |
|
|
image = Image.open('cinematic_shot.jpg') |
|
|
inputs = image_processor(image, return_tensors="pt") |
|
|
with torch.no_grad(): |
|
|
outputs = model(**inputs) |
|
|
|
|
|
# technically multi-label training, but argmax works too! |
|
|
predicted_label = outputs.logits.argmax(-1).item() |
|
|
print(model.config.id2label[predicted_label]) |
|
|
``` |
|
|
|
|
|
## Performance: |
|
|
|
|
|
|
|
|
| Category | Precision | Recall | |
|
|
|----------|-----------|--------| |
|
|
| ground | 65% | 51% | |
|
|
| hip | 69% | 62% | |
|
|
| shoulder | 68% | 74% | |
|
|
| eye | 51% | 39% | |
|
|
| aerial | 89% | 76% | |
