-
Platform (like ubuntu 16.04/win10): win10
Python version: 3.6
Source framework with version (like Tensorflow 1.4.1 with GPU): Tensorflow 1.9
Destination framework with version (like CNTK 2.3 …
-
## 🐛 Bug
`caffe2::CudnnConvOp::RunOnDevice()` fails on Squeezenet
## To Reproduce
Steps to reproduce the behavior:
1. Unzip and copy [test_trt.zip](https://github.com/pytorch/pytorch/files…
-
Hi all,
I have been trying to run through the tutorial [Loading Pretrained Models](https://github.com/caffe2/caffe2/blob/master/caffe2/python/tutorials/Loading_Pretrained_Models.ipynb), but keep ge…
-
Similar to #799, I am trying to run through the Loading Pre-Trained Models Tutorial with GPU/CUDA/Windows10: https://caffe2.ai/docs/tutorial-loading-pre-trained-models.html
The following code execu…
-
Hi I'm trying to implement Squeezenet 1.1 (https://github.com/DeepScale/SqueezeNet/blob/master/SqueezeNet_v1.1/train_val.prototxt)
I can't seem to get the concat of the to (left, right) conv layers…
-
I have got this error when building with this command
mkdir -p build
cd build
cmake -DCMAKE_OSX_ARCHITECTURES="x86_64;arm64" \
-DVulkan_INCLUDE_DIR=`pwd`/../vulkansdk-macos-1.2.189.0/…
-
大佬好，初学者求指导。
我在win10，vs2017上搭建ncnn，编译都可以的。包括valkan和protobuf等。
但是在用图片测试squeezenet的过程中，
ncnn::Mat out;
ex.extract("prob", out);
输出的out是个全空的值。
而模型载入函数，
squeezenet.load_param("squeezenet_v1.1.pa…
-
Platform: Hikey960 / Linux Debian 4.4.74 aarch64 GNU/Linux
Model: ./data/squeezenet.feathermodel from (http://hpcc.siat.ac.cn/jintao/feathercnn/)
Input data: ./data/input_3x224x224.txt
Descrip…
-
Hi, I'm running a custom prediction on a set of ca 500 images across all 4 supported network types. While for DenseNet, ResNet and InceptionV3 I get over 90% validation accuracy after ~ 20 epochs, for…
-
Platform (like ubuntu 16.04):
Python version:
Source framework with version ( Tensorflow 1.4.0):
Destination framework with version (like onnx 1.7.0):
Pre-trained model path (model_squeeze…