Spaces:
Runtime error
Runtime error
Jingkang Yang
commited on
Commit
·
9a023ed
1
Parent(s):
4855376
update: app
Browse files
app.py
CHANGED
@@ -210,96 +210,96 @@ def greet_scannet(rgb_input, depth_map_input, class_candidates):
|
|
210 |
RGB_Semantic_SAM_Mask_gif = 'outputs/RGB_3D_All.mp4'
|
211 |
return RGB_Semantic_SAM_2D, RGB_Semantic_SAM_Mask_gif, Depth_map, Depth_Semantic_SAM_2D, Depth_Semantic_SAM_Mask_gif
|
212 |
|
|
|
|
|
|
|
|
|
|
|
|
|
213 |
|
214 |
with gr.Blocks(analytics_enabled=False) as segrgbd_iface:
|
215 |
-
|
216 |
-
|
217 |
-
|
218 |
-
|
219 |
-
|
220 |
-
|
221 |
-
|
222 |
-
|
223 |
-
|
224 |
-
|
225 |
-
|
226 |
-
|
227 |
-
|
228 |
-
|
229 |
-
|
230 |
-
|
231 |
-
|
232 |
-
|
233 |
-
|
234 |
-
|
235 |
-
|
236 |
-
|
237 |
-
|
238 |
-
|
239 |
-
|
240 |
-
|
241 |
-
|
242 |
-
|
243 |
-
|
244 |
-
|
245 |
-
|
246 |
-
|
247 |
-
|
248 |
-
|
249 |
-
|
250 |
-
|
251 |
-
|
252 |
-
[
|
253 |
-
|
254 |
-
|
255 |
-
|
256 |
-
|
257 |
-
|
258 |
-
|
259 |
-
|
260 |
-
|
261 |
-
|
262 |
-
|
263 |
-
|
264 |
-
|
265 |
-
|
266 |
-
|
267 |
-
|
268 |
-
|
269 |
-
|
270 |
-
|
271 |
-
|
272 |
-
|
273 |
-
|
274 |
-
|
275 |
-
|
276 |
-
|
277 |
-
|
278 |
-
|
279 |
-
|
280 |
-
|
281 |
-
|
282 |
-
|
283 |
-
|
284 |
-
|
285 |
-
|
286 |
-
|
287 |
-
|
288 |
-
|
289 |
-
|
290 |
-
|
291 |
-
],
|
292 |
-
[
|
293 |
-
|
294 |
-
|
295 |
-
|
296 |
-
|
297 |
-
inputs=[Input_RGB_Component, Depth_Map_Input_Component, Class_Candidates_Component],
|
298 |
-
outputs=[RGB_Semantic_SAM_Mask_Component, RGB_Semantic_SAM_Mask_3D_Component, Depth_Map_Output_Component, Depth_Semantic_SAM_Mask_Component, Depth_Semantic_SAM_Mask_3D_Component],
|
299 |
-
fn=greet_scannet)
|
300 |
-
vc_end_btn.click(inputs=[Input_RGB_Component, Depth_Map_Input_Component, Class_Candidates_Component],
|
301 |
-
outputs=[RGB_Semantic_SAM_Mask_Component, RGB_Semantic_SAM_Mask_3D_Component, Depth_Map_Output_Component, Depth_Semantic_SAM_Mask_Component, Depth_Semantic_SAM_Mask_3D_Component],
|
302 |
-
fn=greet_scannet)
|
303 |
|
304 |
demo = segrgbd_iface
|
305 |
demo.launch()
|
|
|
210 |
RGB_Semantic_SAM_Mask_gif = 'outputs/RGB_3D_All.mp4'
|
211 |
return RGB_Semantic_SAM_2D, RGB_Semantic_SAM_Mask_gif, Depth_map, Depth_Semantic_SAM_2D, Depth_Semantic_SAM_Mask_gif
|
212 |
|
213 |
+
SHARED_UI_WARNING = f'''### [NOTE] It may be very slow in this shared UI.
|
214 |
+
You can duplicate and use it with a paid private GPU.
|
215 |
+
<a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/mmlab-ntu/Segment-Any-RGBD?duplicate=true"><img style="margin-top:0;margin-bottom:0" src="https://huggingface.co/datasets/huggingface/badges/raw/main/duplicate-this-space-xl-dark.svg" alt="Duplicate Space"></a>
|
216 |
+
Alternatively, you can also use the Colab demo on our project page.
|
217 |
+
<a style="display:inline-block" href="https://github.com/Jun-CEN/SegmentAnyRGBD/"><img style="margin-top:0;margin-bottom:0" src="https://img.shields.io/badge/Project%20Page-online-brightgreen"></a>
|
218 |
+
'''
|
219 |
|
220 |
with gr.Blocks(analytics_enabled=False) as segrgbd_iface:
|
221 |
+
#######t2v#######
|
222 |
+
with gr.Tab(label="Dataset: Sailvos3D"):
|
223 |
+
with gr.Column():
|
224 |
+
with gr.Row():
|
225 |
+
# with gr.Tab(label='input'):
|
226 |
+
with gr.Column():
|
227 |
+
with gr.Row():
|
228 |
+
Input_RGB_Component = gr.Image(label = 'RGB_Input', type = 'filepath').style(width=320, height=200)
|
229 |
+
Depth_Map_Output_Component = gr.Image(label = "Vis_Depth_Map").style(width=320, height=200)
|
230 |
+
with gr.Row():
|
231 |
+
Depth_Map_Input_Component = gr.File(label = 'input_Depth_map')
|
232 |
+
Component_2D_to_3D_Projection_Parameters = gr.File(label = '2D_to_3D_Projection_Parameters')
|
233 |
+
with gr.Row():
|
234 |
+
Class_Candidates_Component = gr.Text(label = 'Class_Candidates')
|
235 |
+
vc_end_btn = gr.Button("Send")
|
236 |
+
with gr.Tab(label='Result'):
|
237 |
+
with gr.Row():
|
238 |
+
RGB_Semantic_SAM_Mask_Component = gr.Video(label = "RGB_Semantic_SAM_Mask").style(width=320, height=200)
|
239 |
+
RGB_Semantic_SAM_Mask_3D_Component = gr.Video(label = "Video_3D_RGB_Semantic_SAM_Mask").style(width=320, height=200)
|
240 |
+
with gr.Row():
|
241 |
+
Depth_Semantic_SAM_Mask_Component = gr.Video(label = "Depth_Semantic_SAM_Mask").style(width=320, height=200)
|
242 |
+
Depth_Semantic_SAM_Mask_3D_Component = gr.Video(label = "Video_3D_Depth_Semantic_SAM_Mask").style(width=320, height=200)
|
243 |
+
with gr.Row():
|
244 |
+
gr.Markdown("<b> It takes around 2 to 5 minutes to get the final results. The framework initialization, SAM segmentation, zero-shot semantic segmentation and 3D results rendering take long time.</b>")
|
245 |
+
gr.Examples(examples=[
|
246 |
+
[
|
247 |
+
'UI/sailvos3d/ex1/inputs/rgb_000160.bmp',
|
248 |
+
'UI/sailvos3d/ex1/inputs/depth_000160.npy',
|
249 |
+
'UI/sailvos3d/ex1/inputs/rage_matrices_000160.npz',
|
250 |
+
'person, car, motorcycle, truck, bird, dog, handbag, suitcase, bottle, cup, bowl, chair, potted plant, bed, dining table, tv, laptop, cell phone, bag, bin, box, door, road barrier, stick, lamp, floor, wall',
|
251 |
+
],
|
252 |
+
[
|
253 |
+
'UI/sailvos3d/ex2/inputs/rgb_000540.bmp',
|
254 |
+
'UI/sailvos3d/ex2/inputs/depth_000540.npy',
|
255 |
+
'UI/sailvos3d/ex2/inputs/rage_matrices_000540.npz',
|
256 |
+
'person, car, motorcycle, truck, bird, dog, handbag, suitcase, bottle, cup, bowl, chair, potted plant, bed, dining table, tv, laptop, cell phone, bag, bin, box, door, road barrier, stick, lamp, floor, wall',
|
257 |
+
]],
|
258 |
+
inputs=[Input_RGB_Component, Depth_Map_Input_Component, Component_2D_to_3D_Projection_Parameters, Class_Candidates_Component],
|
259 |
+
outputs=[RGB_Semantic_SAM_Mask_Component, RGB_Semantic_SAM_Mask_3D_Component, Depth_Map_Output_Component, Depth_Semantic_SAM_Mask_Component, Depth_Semantic_SAM_Mask_3D_Component],
|
260 |
+
fn=greet_sailvos3d)
|
261 |
+
vc_end_btn.click(inputs=[Input_RGB_Component, Depth_Map_Input_Component, Component_2D_to_3D_Projection_Parameters, Class_Candidates_Component],
|
262 |
+
outputs=[RGB_Semantic_SAM_Mask_Component, RGB_Semantic_SAM_Mask_3D_Component, Depth_Map_Output_Component, Depth_Semantic_SAM_Mask_Component, Depth_Semantic_SAM_Mask_3D_Component],
|
263 |
+
fn=greet_sailvos3d)
|
264 |
+
|
265 |
+
with gr.Tab(label="Dataset: Scannet"):
|
266 |
+
with gr.Column():
|
267 |
+
with gr.Row():
|
268 |
+
# with gr.Tab(label='input'):
|
269 |
+
with gr.Column():
|
270 |
+
with gr.Row():
|
271 |
+
Input_RGB_Component = gr.Image(label = 'RGB_Input', type = 'filepath').style(width=320, height=200)
|
272 |
+
Depth_Map_Output_Component = gr.Image(label = "Vis_Depth_Map").style(width=320, height=200)
|
273 |
+
with gr.Row():
|
274 |
+
Depth_Map_Input_Component = gr.File(label = "Input_Depth_Map")
|
275 |
+
Class_Candidates_Component = gr.Text(label = 'Class_Candidates')
|
276 |
+
vc_end_btn = gr.Button("Send")
|
277 |
+
with gr.Tab(label='Result'):
|
278 |
+
with gr.Row():
|
279 |
+
RGB_Semantic_SAM_Mask_Component = gr.Video(label = "RGB_Semantic_SAM_Mask").style(width=320, height=200)
|
280 |
+
RGB_Semantic_SAM_Mask_3D_Component = gr.Video(label = "Video_3D_RGB_Semantic_SAM_Mask").style(width=320, height=200)
|
281 |
+
with gr.Row():
|
282 |
+
Depth_Semantic_SAM_Mask_Component = gr.Video(label = "Depth_Semantic_SAM_Mask").style(width=320, height=200)
|
283 |
+
Depth_Semantic_SAM_Mask_3D_Component = gr.Video(label = "Video_3D_Depth_Semantic_SAM_Mask").style(width=320, height=200)
|
284 |
+
with gr.Row():
|
285 |
+
gr.Markdown("<b> It takes around 2 to 5 minutes to get the final results. The framework initialization, SAM segmentation, zero-shot semantic segmentation and 3D results rendering take long time.</b>")
|
286 |
+
gr.Examples(examples=[
|
287 |
+
[
|
288 |
+
'UI/scannetv2/examples/scene0000_00/color/1660.jpg',
|
289 |
+
'UI/scannetv2/examples/scene0000_00/depth/1660.png',
|
290 |
+
'wall, floor, cabinet, bed, chair, sofa, table, door, window, bookshelf, picture, counter, desk, curtain, refrigerator, shower curtain, toilet, sink, bathtub, other furniture',
|
291 |
+
],
|
292 |
+
[
|
293 |
+
'UI/scannetv2/examples/scene0000_00/color/5560.jpg',
|
294 |
+
'UI/scannetv2/examples/scene0000_00/depth/5560.png',
|
295 |
+
'wall, floor, cabinet, bed, chair, sofa, table, door, window, bookshelf, picture, counter, desk, curtain, refrigerator, shower curtain, toilet, sink, bathtub, other furniture',
|
296 |
+
]],
|
297 |
+
inputs=[Input_RGB_Component, Depth_Map_Input_Component, Class_Candidates_Component],
|
298 |
+
outputs=[RGB_Semantic_SAM_Mask_Component, RGB_Semantic_SAM_Mask_3D_Component, Depth_Map_Output_Component, Depth_Semantic_SAM_Mask_Component, Depth_Semantic_SAM_Mask_3D_Component],
|
299 |
+
fn=greet_scannet)
|
300 |
+
vc_end_btn.click(inputs=[Input_RGB_Component, Depth_Map_Input_Component, Class_Candidates_Component],
|
301 |
+
outputs=[RGB_Semantic_SAM_Mask_Component, RGB_Semantic_SAM_Mask_3D_Component, Depth_Map_Output_Component, Depth_Semantic_SAM_Mask_Component, Depth_Semantic_SAM_Mask_3D_Component],
|
302 |
+
fn=greet_scannet)
|
|
|
|
|
|
|
|
|
|
|
|
|
303 |
|
304 |
demo = segrgbd_iface
|
305 |
demo.launch()
|