-
http://caffe2.ai/docs/tutorial-loading-pre-trained-models.html
`with open("init_net.pb") as f:`
` init_net = f.read()`
`with open("predict_net.pb") as f:`
` predict_net = f.read()`
`print…
-
I get the following error while trying to build the package on ubuntu 16.04:
cc1plus: warning: unrecognized command line option '-Wno-unknown-warning-option'
cc1plus: warning: unrecognized command…
-
All I did was converted a standard vgg16 prototxt and standard vgg caffemodel from caffe and then converted it to onnx using mmdnn and then tried to convert it to caffe2, but got following error while…
-
See https://app.circleci.com/pipelines/github/pytorch/pytorch/148057/workflows/df15651f-11ba-4459-8687-cd11a2a13b15/jobs/4987650
```
unning "C:\Users\circleci\project\build\win_tmp\build\torch\test…
-
2019-07-11 10:01:27,073 maskrcnn_benchmark.utils.checkpoint INFO: Loading checkpoint from catalog://ImageNetPretrained/MSRA/R-50
2019-07-11 10:01:27,075 maskrcnn_benchmark.utils.checkpoint INFO: cata…
-
## 🐛 Bug
When compiling on Docker for L4T with CUDA 10.2 installed, torch doesn't compile with due to not finding CUDA.
## To Reproduce
Clone the [Torch Samples](https://github.com/pytorch/ex…
-
My machine has cuda install at: /usr/local/cuda; it's fine when I build with cuda. However, if I don't want to build it with cuda
```cmake .. -DNO_CUDA=1```
I get following errors:
```
[ 74%…
-
I directly run the apk build by this project without any change on my own android device.
However, it seems that the outputs(top5 labels) do not make any sense, I also tried to use a better model, t…
-
Hi,
Thanks for the demo. it is really amazing. I build and run the app in windows environment, its working fine. I am new on caffe2 as well as on android. The question is how can i improve the predic…
-
Hello,
I can't compile any model that includes scatter or scatter min from torch_scatter.
For example in this beautiful script
```
import torch
import torch_geometric
from torch_scatter imp…