Comments (2)
Thanks for reporting. Seems that caffe cannot load its own protobuf, I'll check the problem in a few days.
from feathercnn.
I'm glad to receive your reply,I solved this problem by using upgrade_net_proto_binary.exe to upgrade the bvlc_googlenet.caffemodel ,and it is successful to conver the caffemodel to the feathermodel,but I have new questions while running on the rk3288(armeabi-v7a)
host:ubantu16.04 NDK r17
1、bvlc_googlenet.feathermodel
Forward
layer conv1/7x7_s2 type Convolution spent 158.054167ms
layer conv1/relu_7x7 type ReLU spent 5.689833ms
layer pool1/3x3_s2 type Pooling spent 19.716958ms
layer pool1/norm1 type LRN spent 69.234666ms
layer conv2/3x3_reduce type Convolution spent 15.302583ms
layer conv2/relu_3x3_reduce type ReLU spent 1.325625ms
Too many args to microtask: 21!
2、my.feathermodel
/test32 my.feathermodel input_3x32x32.txt 20 1
WARNING: linker: ./test32: unused DT entry: type 0x1d arg 0x6ef
WARNING: linker: ./test32: unused DT entry: type 0x6ffffffe arg 0x19a8
WARNING: linker: ./test32: unused DT entry: type 0x6fffffff arg 0x2
++++++Start Loader++++++
Finished loading from file
-- Loading 39 layers
input num 1 input dim num 4
input_name data (n c h w) (1 3 32 32)
stride 1, 1
_bottom data
setup layer conv0
_bottom conv0
setup layer relu0
stride 1, 1
_bottom relu0
setup layer conv1/1
_bottom conv1/1
setup layer conv1/1_relu
stride 1, 1
_bottom conv1/1_relu
setup layer conv1/e1
_bottom conv1/e1
setup layer conv1/e1_relu
_bottom conv1/e1_relu
kernel (3 3) pad (0 0) stride (2 2) global_pooling 0
setup layer conv1/e1_pool
stride 2, 2
_bottom conv1/1_relu
setup layer conv1/s3
_bottom conv1/s3
setup layer conv1/s3_relu
_bottom conv1/e1_pool
_bottom conv1/s3_relu
setup layer conv1/concat
_bottom conv1/concat
setup layer conv1/concat_BN
stride 1, 1
_bottom conv1/concat_BN
setup layer conv2/1
_bottom conv2/1
setup layer conv2/1_relu
stride 1, 1
_bottom conv2/1_relu
setup layer conv2/e1
_bottom conv2/e1
setup layer conv2/e1_relu
_bottom conv2/e1_relu
kernel (3 3) pad (0 0) stride (2 2) global_pooling 0
setup layer conv2/e1_pool
stride 2, 2
_bottom conv2/1_relu
setup layer conv2/s3
_bottom conv2/s3
setup layer conv2/s3_relu
_bottom conv2/e1_pool
_bottom conv2/s3_relu
setup layer conv2/concat
_bottom conv2/concat
setup layer conv2/concat_BN
stride 1, 1
_bottom conv2/concat_BN
setup layer conv3/1
_bottom conv3/1
setup layer conv3/1_relu
stride 1, 1
_bottom conv3/1_relu
setup layer conv3/e1
_bottom conv3/e1
setup layer conv3/e1_relu
_bottom conv3/e1_relu
kernel (3 3) pad (0 0) stride (2 2) global_pooling 0
setup layer conv3/e1_pool
stride 2, 2
_bottom conv3/1_relu
setup layer conv3/s3
_bottom conv3/s3
setup layer conv3/s3_relu
_bottom conv3/e1_pool
_bottom conv3/s3_relu
setup layer conv3/concat
_bottom conv3/concat
setup layer conv3/concat_BN
stride 1, 1
_bottom conv3/concat_BN
setup layer conv_cls
Layer type PReLU not registered
setup layer relu_cls
_bottom relu_cls
setup layer conv_cls_BN
stride 1, 1
_bottom conv_cls_BN
setup layer fc_cls
_bottom fc_cls
setup layer cls_prob
stride 1, 1
_bottom conv3/concat_BN
setup layer conv_reg
Layer type PReLU not registered
setup layer relu_reg
_bottom relu_reg
setup layer conv_BN_reg
stride 1, 1
_bottom conv_BN_reg
setup layer fc_reg
Output shape 32 16 16
Output shape 64 8 8
Output shape 64 4 4
Segmentation fault
from feathercnn.
Related Issues (20)
- Do you plan to support convert pytorch model to feathercnn model? HOT 2
- InitFromPath never returns HOT 1
- 请问该框架与ncnn的区别与联系? HOT 12
- 请问是否支持ssd? HOT 1
- Running benchmark with SqueezeNet model, segmentation fault occured HOT 2
- Does this also support RPi3B with Raspbian OS (armv7l) HOT 3
- 请问转换caffe模型的文件是feather_convert_caffe还是caffe_model_convert HOT 5
- typo and why so large input buffer HOT 1
- supported layer mismatch between layer_factory.cpp and feather_convert_caffe.cc
- Model convert error - libprotobuf HOT 1
- Performance testing using experimental branch on Andriod
- build_linux.sh
- 未使用的局部变量
- Add support for tf or split+transpose in caffe.
- loadparam
- 这个项目还在维护吗?
- Layer type Deconvolution not registered
- Documentation or examples for ARM usage. HOT 3
- OpenCL or Vulkan port?
- Evaluation
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from feathercnn.