Spaces:
Running
on
Zero
Running
on
Zero
derektan
commited on
Commit
·
182d7df
1
Parent(s):
0b72cc5
Update examples
Browse files
app.py
CHANGED
|
@@ -159,23 +159,23 @@ model.eval()
|
|
| 159 |
examples_in_domain = [
|
| 160 |
[
|
| 161 |
"./imgs/examples/Animalia_Chordata_Aves_Charadriiformes_Laridae_Larus_marinus/80645_39.76079_-74.10316.jpg",
|
| 162 |
-
"Where can I find the shore birds (
|
| 163 |
],
|
| 164 |
[
|
| 165 |
"./imgs/examples/Animalia_Chordata_Mammalia_Rodentia_Caviidae_Hydrochoerus_hydrochaeris/28871_-12.80255_-69.29999.jpg",
|
| 166 |
-
"Where can I find the capybaras (
|
| 167 |
],
|
| 168 |
[
|
| 169 |
"./imgs/examples/Animalia_Arthropoda_Malacostraca_Decapoda_Ocypodidae_Ocypode_quadrata/277303_38.72364_-75.07749.jpg",
|
| 170 |
-
"Where can I find the crabs (
|
| 171 |
],
|
| 172 |
[
|
| 173 |
"./imgs/examples/Animalia_Chordata_Mammalia_Rodentia_Sciuridae_Marmota_marmota/388246_45.49036_7.14796.jpg",
|
| 174 |
-
"Where can I find the marmots (
|
| 175 |
],
|
| 176 |
[
|
| 177 |
"./imgs/examples/Animalia_Chordata_Reptilia_Squamata_Varanidae_Varanus_salvator/410613_5.35573_100.28948.jpg",
|
| 178 |
-
"Where can I find monitor lizard (
|
| 179 |
],
|
| 180 |
|
| 181 |
]
|
|
@@ -186,12 +186,12 @@ examples_out_domain = [
|
|
| 186 |
"Where can I find the seals (Animalia Chordata Mammalia Carnivora Phocidae Mirounga angustirostris) in this image? Please output segmentation mask and explain why.",
|
| 187 |
],
|
| 188 |
[
|
| 189 |
-
"./imgs/examples/
|
| 190 |
-
"Where can I find the
|
| 191 |
],
|
| 192 |
[
|
| 193 |
-
"./imgs/examples/
|
| 194 |
-
"Where can I find the
|
| 195 |
],
|
| 196 |
]
|
| 197 |
output_labels = ["Segmentation Output"]
|
|
@@ -203,9 +203,9 @@ description = """
|
|
| 203 |
This is an adapted version of the online demo for <a href='https://github.com/dvlab-research/LISA' target='_blank'>LISA</a>, where we finetune from scratch the LISA model (7B) with data from <a href='https://search-tta.github.io/' target='_blank'>AVS-Bench (Search-TTA)</a>. \n
|
| 204 |
**Note**: Different prompts can lead to significantly varied results. Please **standardize** your input text prompts to **avoid ambiguity**, and pay attention to whether the **punctuations** of the input are correct. \n
|
| 205 |
**Usage**: <br>
|
| 206 |
-
 (1) To let LISA-AVS **segment something**, input prompt like: "Where can I find the <em>Common Name</em> (<em>
|
| 207 |
-
 (2) To let LISA-AVS **output an explanation**, input prompt like: "Where can I find the <em>Common Name</em> (<em>
|
| 208 |
-
 (3) To obtain **solely language output**, you can input like what you should do in current multi-modal LLM (e.g., LLaVA), like: "Where can I find the <em>Common Name</em> (<em>
|
| 209 |
|
| 210 |
</font>
|
| 211 |
"""
|
|
|
|
| 159 |
examples_in_domain = [
|
| 160 |
[
|
| 161 |
"./imgs/examples/Animalia_Chordata_Aves_Charadriiformes_Laridae_Larus_marinus/80645_39.76079_-74.10316.jpg",
|
| 162 |
+
"Where can I find the shore birds (Larus marinus) in this image? Please output segmentation mask.",
|
| 163 |
],
|
| 164 |
[
|
| 165 |
"./imgs/examples/Animalia_Chordata_Mammalia_Rodentia_Caviidae_Hydrochoerus_hydrochaeris/28871_-12.80255_-69.29999.jpg",
|
| 166 |
+
"Where can I find the capybaras (Hydrochoerus hydrochaeris) in this image? Please output segmentation mask and explain why.",
|
| 167 |
],
|
| 168 |
[
|
| 169 |
"./imgs/examples/Animalia_Arthropoda_Malacostraca_Decapoda_Ocypodidae_Ocypode_quadrata/277303_38.72364_-75.07749.jpg",
|
| 170 |
+
"Where can I find the crabs (Ocypode quadrata) in this image? Please output segmentation mask.",
|
| 171 |
],
|
| 172 |
[
|
| 173 |
"./imgs/examples/Animalia_Chordata_Mammalia_Rodentia_Sciuridae_Marmota_marmota/388246_45.49036_7.14796.jpg",
|
| 174 |
+
"Where can I find the marmots (Marmota marmota) in this image? Please output segmentation mask and explain why.",
|
| 175 |
],
|
| 176 |
[
|
| 177 |
"./imgs/examples/Animalia_Chordata_Reptilia_Squamata_Varanidae_Varanus_salvator/410613_5.35573_100.28948.jpg",
|
| 178 |
+
"Where can I find monitor lizard (Varanus salvator) in this image? Please output segmentation mask.",
|
| 179 |
],
|
| 180 |
|
| 181 |
]
|
|
|
|
| 186 |
"Where can I find the seals (Animalia Chordata Mammalia Carnivora Phocidae Mirounga angustirostris) in this image? Please output segmentation mask and explain why.",
|
| 187 |
],
|
| 188 |
[
|
| 189 |
+
"./imgs/examples/Animalia_Chordata_Mammalia_Carnivora_Canidae_Urocyon_littoralis/304160_34.0144_-119.54417.jpg",
|
| 190 |
+
"Where can I find the raccoons (Animalia Chordata Mammalia Carnivora Canidae Urocyon littoralis) in this image? Please output segmentation mask.",
|
| 191 |
],
|
| 192 |
[
|
| 193 |
+
"./imgs/examples/Animalia_Chordata_Mammalia_Carnivora_Canidae_Canis_aureus/1528408_13.00422_80.23033.jpg",
|
| 194 |
+
"Where can I find the wolves (Animalia Chordata Mammalia Carnivora Canidae Canis aureus) in this image? Please output segmentation mask and explain why.",
|
| 195 |
],
|
| 196 |
]
|
| 197 |
output_labels = ["Segmentation Output"]
|
|
|
|
| 203 |
This is an adapted version of the online demo for <a href='https://github.com/dvlab-research/LISA' target='_blank'>LISA</a>, where we finetune from scratch the LISA model (7B) with data from <a href='https://search-tta.github.io/' target='_blank'>AVS-Bench (Search-TTA)</a>. \n
|
| 204 |
**Note**: Different prompts can lead to significantly varied results. Please **standardize** your input text prompts to **avoid ambiguity**, and pay attention to whether the **punctuations** of the input are correct. \n
|
| 205 |
**Usage**: <br>
|
| 206 |
+
 (1) To let LISA-AVS **segment something**, input prompt like: "Where can I find the <em>Common Name</em> (<em>Taxonomy Name</em>) in this image? Please output segmentation mask."; <br>
|
| 207 |
+
 (2) To let LISA-AVS **output an explanation**, input prompt like: "Where can I find the <em>Common Name</em> (<em>Taxonomy Name</em>) in this image? Please output segmentation mask and explain why."; <br>
|
| 208 |
+
 (3) To obtain **solely language output**, you can input like what you should do in current multi-modal LLM (e.g., LLaVA), like: "Where can I find the <em>Common Name</em> (<em>Taxonomy Name</em>) in this image?" <br>
|
| 209 |
|
| 210 |
</font>
|
| 211 |
"""
|