-
Hi all,
I want to translate caffemodel to caffe2 model following the guide using the command line:
| python -m caffe2.python.caffe_translator deploy.prototxt pretrained.caffemodel
-- | --
…
-
-
I train faster rcnn based on ResNet-101-FPN and use pre-trained on my dataset. NUM_GPUS=4.
CUDA_VISIBLE_DEVICES=0,1,2,3 python3 -u tools/train_net.py --cfg configs/getting_started/oid_faster_r…
-
## Issue description
I was trying to read my onnx model via caffe and deployed it onto AWS lambda.
The complete deployment seems to be working fine in my local but on AWS lambda we are getting thi…
-
The error occurred while compiling on the resc-v schema
make[2]: *** [caffe2/CMakeFiles/kernel_lambda_legacy_test.dir/build.make:101: bin/kernel_lambda_legacy_test] Error 1
make[1]: *** [CMakeFiles/…
-
## 🐛 Bug
Building pytorch master HEAD under Mac OS X 10.13.16 with CC3.0 Nvidia GT 750M CUDA 10.0 and cuDNN 7.4.2 failed with error: identifier "__ldg" is undefined because __ldg is only support …
-
## 🐛 Bug
## To Reproduce
Steps to reproduce the behavior:
1.
1.
1.
## Expected behavior
## Environment
Please copy and paste the output from our
[environment collectio…
-
Hey guys,
I am trying to convert mobilenet model from TensorFlow to Caffe2, now it can work perfectly without batch norm. I got trouble in filling parameters into spatial_bn operator of Caffe2, whi…
-
i want to implement fast neural style, but find caffe2 don't have "resize" method, is it true?
-
I have a simple CNN. When I send data as a = np.random.rand(1,2,3,3), I want to obtain one output of shape (1, 9, 2), in which the SoftMax is taken along axis = -1. So, in this way np.sum(out) = 9, an…