Instructions to use aayushgs/Salesforce-blip-image-captioning-large-custom-handler with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aayushgs/Salesforce-blip-image-captioning-large-custom-handler with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="aayushgs/Salesforce-blip-image-captioning-large-custom-handler")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("aayushgs/Salesforce-blip-image-captioning-large-custom-handler") model = AutoModelForImageTextToText.from_pretrained("aayushgs/Salesforce-blip-image-captioning-large-custom-handler") - Notebooks
- Google Colab
- Kaggle
slight changes
Browse files- handler.py +1 -1
handler.py
CHANGED
|
@@ -26,7 +26,7 @@ class EndpointHandler:
|
|
| 26 |
if not encoded_images:
|
| 27 |
return {"captions": [], "error": "No images provided"}
|
| 28 |
|
| 29 |
-
texts = input_data.get("texts", ["
|
| 30 |
|
| 31 |
try:
|
| 32 |
raw_images = [
|
|
|
|
| 26 |
if not encoded_images:
|
| 27 |
return {"captions": [], "error": "No images provided"}
|
| 28 |
|
| 29 |
+
texts = input_data.get("texts", [""] * len(encoded_images))
|
| 30 |
|
| 31 |
try:
|
| 32 |
raw_images = [
|