Spaces:
Runtime error
Runtime error
modify markdown
Browse files
app.py
CHANGED
@@ -158,13 +158,10 @@ with demo:
|
|
158 |
<h2>Overview</h2>
|
159 |
|
160 |
BigDL-Nano is a library in [BigDL 2.0](https://github.com/intel-analytics/BigDL) that allows the users to transparently accelerate their deep learning pipelines (including data processing, training and inference) by automatically integrating optimized libraries, best-known configurations, and software optimizations. </p>
|
161 |
-
The
|
162 |
''')
|
163 |
with gr.Column():
|
164 |
gr.Video(value="data/training_api.mp4")
|
165 |
-
gr.Markdown('''
|
166 |
-
The below animation shows how the user can easily enable acceleration and quantization using BigDL-Nano with just a couple of lines of code; you may refer to our [CVPR 2022 demo paper](https://arxiv.org/abs/2204.01715) for more details.
|
167 |
-
''')
|
168 |
with gr.Row().style(equal_height=True):
|
169 |
with gr.Column():
|
170 |
gr.Video(value="data/openvino_api.mp4")
|
@@ -173,7 +170,7 @@ with demo:
|
|
173 |
gr.Markdown('''
|
174 |
<h2>Demo</h2>
|
175 |
|
176 |
-
This section
|
177 |
This inference demo is adapted from the original [FSPBT-Image-Translation code](https://github.com/rnwzd/FSPBT-Image-Translation),
|
178 |
and the default image is from [the COCO dataset](https://cocodataset.org/#home).
|
179 |
''')
|
|
|
158 |
<h2>Overview</h2>
|
159 |
|
160 |
BigDL-Nano is a library in [BigDL 2.0](https://github.com/intel-analytics/BigDL) that allows the users to transparently accelerate their deep learning pipelines (including data processing, training and inference) by automatically integrating optimized libraries, best-known configurations, and software optimizations. </p>
|
161 |
+
The video on the right shows how the user can easily accelerate their training and inference (including tracing and quantization) pipelines using BigDL-Nano with just a couple of lines of code; you may refer to our [CVPR 2022 demo paper](https://arxiv.org/abs/2204.01715) for more details.
|
162 |
''')
|
163 |
with gr.Column():
|
164 |
gr.Video(value="data/training_api.mp4")
|
|
|
|
|
|
|
165 |
with gr.Row().style(equal_height=True):
|
166 |
with gr.Column():
|
167 |
gr.Video(value="data/openvino_api.mp4")
|
|
|
170 |
gr.Markdown('''
|
171 |
<h2>Demo</h2>
|
172 |
|
173 |
+
This section uses an image stylization example to demonstrate the speedup of an inference pipeline using quantization in BigDL-Nano (about 2~3x inference time speedup).
|
174 |
This inference demo is adapted from the original [FSPBT-Image-Translation code](https://github.com/rnwzd/FSPBT-Image-Translation),
|
175 |
and the default image is from [the COCO dataset](https://cocodataset.org/#home).
|
176 |
''')
|