abhi2610 / ohem Goto Github PK
View Code? Open in Web Editor NEWOHEM support for Fast R-CNN
License: Other
OHEM support for Fast R-CNN
License: Other
Hi
I am trying to make the idea of this code work with faster rcnn, but I have not been able to do so. Any hints?
Best,
Hi, I met a problem when testing the ohem.
I found some similar talk about it
rbgirshick/py-faster-rcnn#2
[https://github.com/D-X-Y/caffe-faster-rcnn/issues/34] (https://github.com/D-X-Y/caffe-faster-rcnn/issues/34)
By changing the GPU_NMS=False didn't help.
Also when compile, it showed my GPU was sm_35 computing compatible. So it might not caused by this problem.
...............
-- Boost version: 1.58.0
-- Found the following Boost libraries:
-- system
-- thread
-- filesystem
-- chrono
-- date_time
-- atomic
-- Found gflags (include: /usr/local/include, library: /usr/local/lib/libgflags.a)
-- Found glog (include: /usr/local/include, library: /usr/local/lib/libglog.so)
-- Found PROTOBUF Compiler: /usr/bin/protoc
HDF5_ROOT:
-- HDF5: Using hdf5 compiler wrapper to determine C configuration
-- HDF5: Using hdf5 compiler wrapper to determine CXX configuration
-- Found lmdb (include: /usr/local/include, library: /usr/local/lib/liblmdb.so)
-- Found LevelDB (include: /usr/include, library: /usr/lib/x86_64-linux-gnu/libleveldb.so)
-- Found Snappy (include: /usr/include, library: /usr/lib/x86_64-linux-gnu/libsnappy.so)
-- CUDA detected: 8.0
-- Found cuDNN: ver. 5.1.10 found (include: /usr/local/cuda-8.0/include, library: /usr/local/cuda-8.0/lib64/libcudnn.so)
-- Added CUDA NVCC flags for: sm_35
-- OpenCV found (/usr/local/share/OpenCV)
Training and test of the py-faster-rcnn project is OK on the same machine. Training of the ohem also succeed. The problem only occurs at test phase.
Any hints about this issue or how to work around?
@abhi2610 HI
When I perform the training, encount the following error
Traceback (most recent call last):
File "./tools/train_net.py", line 113, in <module>
max_iters=args.max_iters)
File "/home/jmx/ohem-end2end/tools/../lib/fast_rcnn/train.py", line 160, in train_net
model_paths = sw.train_model(max_iters)
File "/home/jmx/ohem-end2end/tools/../lib/fast_rcnn/train.py", line 101, in train_model
self.solver.step(1)
File "/home/jmx/ohem-end2end/tools/../lib/roi_data_layer/layer.py", line 242, in forward
for x in [cls_prob[i,label] for i, label in enumerate(labels)]]
IndexError: only integers, slices (`:`), ellipsis (`...`), numpy.newaxis (`None`) and integer or boolean arrays are valid indices
How do I modify it
many many thanks!!!
what if I want to write this when use the Net_spec() in python ?
layer{
name: "m3@ssh_output_ohem"
type: "Concat"
bottom: "m3@ssh_3x3_output_ohem"
bottom: "m3@ssh_5x5_output_ohem"
bottom: "m3@ssh_7x7_output_ohem"
top: "m3@ssh_output_ohem"
concat_param{
axis: 1
}
propagate_down: false
propagate_down: false
propagate_down: false
}
There are three# propagate_down: false
, and python can not receive the duplicate args.
How to write in python?
hey, I have download your code and I want to have a try, However, I found in your experiments/ directory there are no directory called cfg, but in your training scripts experiments/scripts/faster-rcnn-ohem.sh you have mentioned it. So could you upload your cfg file?
Hello, author.
Is this version of the code now available? Can you give me a reference?
Thanks very much
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.