Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,8 @@ A [microsoft/Florence-2-base](https://huggingface.co/microsoft/Florence-2-base)
|
|
| 21 |
|
| 22 |
This is a very early version as I have a limited number of training images and the variety of images is lacking. Basically all images used were *high quality* so captioning *low quality* images may perform poorly.
|
| 23 |
|
|
|
|
|
|
|
| 24 |
## Model Evaluation
|
| 25 |
|
| 26 |
| Source Image | Ground Truth | Original Model Prediction | Fine-tuned Model Prediction |
|
|
|
|
| 21 |
|
| 22 |
This is a very early version as I have a limited number of training images and the variety of images is lacking. Basically all images used were *high quality* so captioning *low quality* images may perform poorly.
|
| 23 |
|
| 24 |
+
Uses `<CAPTION>` task prompt. Training on `<DETAILED_CAPTION>` or `<MORE_DETAILED_CAPTION>` did not seem to make a difference in quality compared to `<CAPTION>`.
|
| 25 |
+
|
| 26 |
## Model Evaluation
|
| 27 |
|
| 28 |
| Source Image | Ground Truth | Original Model Prediction | Fine-tuned Model Prediction |
|