Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -121,7 +121,7 @@ with gr.Blocks() as demo:
|
|
| 121 |
1. Enter list of labels separated by commas (or select one of the examples below)
|
| 122 |
2. Click **Get Random Image** to grab a random image from dataset
|
| 123 |
3. Click **Classify Image** to analyze current image against the labels (including after changing labels)
|
| 124 |
-
4. The dataset (<a href="https://github.com/unsplash/datasets" target="_blank">Unsplash Lite</a>) contains 25,000 nature-focused images
|
| 125 |
gr.Markdown(instructions)
|
| 126 |
with gr.Row(variant="compact"):
|
| 127 |
label_text = gr.Textbox(show_label=False, placeholder="Enter classification labels").style(container=False)
|
|
@@ -150,8 +150,8 @@ with gr.Blocks() as demo:
|
|
| 150 |
instructions = """## Instructions:
|
| 151 |
1. Click **Get Random Image** to grab a random image from dataset
|
| 152 |
1. Click **Create Caption** to generate a caption for the image
|
| 153 |
-
1. Different models can be selected: *COCO* generally produces more straight-forward captions, but it is a smaller dataset and therefore struggles to recognize certain objects; **Conceptual Captions** is a much larger dataset but
|
| 154 |
-
1. The dataset (<a href="https://github.com/unsplash/datasets" target="_blank">Unsplash Lite</a>) contains 25,000 nature-focused images
|
| 155 |
gr.Markdown(instructions)
|
| 156 |
with gr.Row():
|
| 157 |
with gr.Column(variant="panel"):
|
|
@@ -169,7 +169,7 @@ with gr.Blocks() as demo:
|
|
| 169 |
instructions = """## Instructions:
|
| 170 |
1. Enter a search query (or select one of the examples below)
|
| 171 |
2. Click **Find Images** to find images that match the query (top 5 are shown in order from left to right)
|
| 172 |
-
3. The dataset (<a href="https://github.com/unsplash/datasets" target="_blank">Unsplash Lite</a>) contains 25,000 nature-focused images
|
| 173 |
gr.Markdown(instructions)
|
| 174 |
with gr.Column(variant="panel"):
|
| 175 |
desc = gr.Textbox(show_label=False, placeholder="Enter description").style(container=False)
|
|
|
|
| 121 |
1. Enter list of labels separated by commas (or select one of the examples below)
|
| 122 |
2. Click **Get Random Image** to grab a random image from dataset
|
| 123 |
3. Click **Classify Image** to analyze current image against the labels (including after changing labels)
|
| 124 |
+
4. The dataset (<a href="https://github.com/unsplash/datasets" target="_blank">Unsplash Lite</a>) contains 25,000 nature-focused images"""
|
| 125 |
gr.Markdown(instructions)
|
| 126 |
with gr.Row(variant="compact"):
|
| 127 |
label_text = gr.Textbox(show_label=False, placeholder="Enter classification labels").style(container=False)
|
|
|
|
| 150 |
instructions = """## Instructions:
|
| 151 |
1. Click **Get Random Image** to grab a random image from dataset
|
| 152 |
1. Click **Create Caption** to generate a caption for the image
|
| 153 |
+
1. Different models can be selected: *COCO* generally produces more straight-forward captions, but it is a smaller dataset and therefore struggles to recognize certain objects; **Conceptual Captions** is a much larger dataset but sometimes produces overly...um...poetic results
|
| 154 |
+
1. The dataset (<a href="https://github.com/unsplash/datasets" target="_blank">Unsplash Lite</a>) contains 25,000 nature-focused images"""
|
| 155 |
gr.Markdown(instructions)
|
| 156 |
with gr.Row():
|
| 157 |
with gr.Column(variant="panel"):
|
|
|
|
| 169 |
instructions = """## Instructions:
|
| 170 |
1. Enter a search query (or select one of the examples below)
|
| 171 |
2. Click **Find Images** to find images that match the query (top 5 are shown in order from left to right)
|
| 172 |
+
3. The dataset (<a href="https://github.com/unsplash/datasets" target="_blank">Unsplash Lite</a>) contains 25,000 nature-focused images"""
|
| 173 |
gr.Markdown(instructions)
|
| 174 |
with gr.Column(variant="panel"):
|
| 175 |
desc = gr.Textbox(show_label=False, placeholder="Enter description").style(container=False)
|