Comments (3)
Hi Nigel,
Since C3D uses the older branch of caffe, when the Makefile.config does not have such a flag. If you don't have GPU, you can still use C3D (assume to be slow).
- Compile as normal without modifying Makefile.config
- For feature extraction, you specific GPU ID = -1. For example, in the following command line:
GLOG_logtosterr=1 ../../build/tools/extract_image_features.bin prototxt/c3d_sport1m_feature_extractor_frm.prototxt conv3d_deepnetA_sport1m_iter_1900000 0 50 1 prototxt/output_list_prefix.txt fc7-1 fc6-1 prob
You modify it to:
GLOG_logtosterr=1 ../../build/tools/extract_image_features.bin prototxt/c3d_sport1m_feature_extractor_frm.prototxt conv3d_deepnetA_sport1m_iter_1900000 -1 50 1 prototxt/output_list_prefix.txt fc7-1 fc6-1 prob
For training/finetuning, change option in your solver file
solver_mode: GPU
to
solver_mode: CPU
Hope this helps.
from c3d.
@dutran Thank you very much for your suggestions.
I have successfully built the code and run the examples in your 'C3D User Guide'.
Great work! Cheers!
Nigel
from c3d.
I'm glad to hear it works for you.
Cheers,
Du
from c3d.
Related Issues (20)
- Random crop is bad for this model? HOT 1
- Features are not being extracted for all the frames HOT 5
- static link error with anaconda HOT 1
- Couldn't found the result in the output folder HOT 1
- Make all fails at examples/mnist/convert_mnist_data.cpp HOT 2
- Error with no data at frame xx always appears while set sample_rate > 1
- Check Failed while training from scratch in 1.0 HOT 1
- using more gpu HOT 1
- ERROR : video_data_layer.cpp:252] Check failed: ReadImageSequenceToVolumeDatum
- File not found: conv3d_deepnetA_sport1m_iter_1900000 HOT 2
- [C3D v.1.0] Failed to execute: sh c3d_sport1m_feature_extraction_frm.sh HOT 4
- C3D Google Colab - Extract feature from raw video (mp4)
- Action similarity labeling - Similarity is NAN
- compilation error in C3D v1.0
- recipe for target '.build_release/src/caffe/proto/caffe.pb.o' failed,...Error while make in both C3D1.0 and 1.1
- GPU Configuration Details
- image_io.cpp:339] Could not open or find file HOT 1
- _make clean
- F0905 11:26:43.151420 12241 layer_factory.hpp:81] Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type: Video_Data
- Have some error for running extract_C3D_feature.py in C3D-v1.0
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 c3d.