@@ -20,7 +20,8 @@ versions.
2020
2121|  ` torch `             |  ` torchvision `       |  Python              | 
2222|  ------------------ |  ------------------ |  ------------------- | 
23- |  ` main `  / ` nightly `  |  ` main `  / ` nightly `  |  ` >=3.10 ` , ` <=3.13 `    | 
23+ |  ` main `  / ` nightly `  |  ` main `  / ` nightly `  |  ` >=3.10 ` , ` <=3.14 `   | 
24+ |  ` 2.9 `               |  ` 0.24 `              |  ` >=3.10 ` , ` <=3.14 `   | 
2425|  ` 2.8 `               |  ` 0.23 `              |  ` >=3.9 ` , ` <=3.13 `    | 
2526|  ` 2.7 `               |  ` 0.22 `              |  ` >=3.9 ` , ` <=3.13 `    | 
2627|  ` 2.6 `               |  ` 0.21 `              |  ` >=3.9 ` , ` <=3.12 `    | 
@@ -64,17 +65,6 @@ Torchvision currently supports the following image backends:
6465
6566Read more in in our [ docs] ( https://pytorch.org/vision/stable/transforms.html ) .
6667
67- # Using the models on C++  
68- 
69- Refer to [ example/cpp] ( https://github.com/pytorch/vision/tree/main/examples/cpp ) .
70- 
71- ** DISCLAIMER** : the ` libtorchvision `  library includes the torchvision
72- custom ops as well as most of the C++ torchvision APIs. Those APIs do not come
73- with any backward-compatibility guarantees and may change from one version to
74- the next. Only the Python APIs are stable and with backward-compatibility
75- guarantees. So, if you need stability within a C++ environment, your best bet is
76- to export the Python APIs via torchscript.
77- 
7868## Documentation  
7969
8070You can find the API documentation on the pytorch website: < https://pytorch.org/vision/stable/index.html > 
0 commit comments