Comments (15)
Thank you very much!
Because i clone the caffe-fast-rcnn by hand, so it is not on the correct branch.
After checking out the fast-rcnn branch and re-compiling the code, the error is gone.
Thank you for give the clue to figure it out.
from fast-rcnn.
My guess is that you have another installation of Caffe already in your PYTHONPATH. You'll need to use the included caffe-fast-rcnn git submodule, which defines a couple of new layers, including the RoI pooling layer.
from fast-rcnn.
I am not quite familiar with git. Could you please explain it more specifically? Thanks a lot!
from fast-rcnn.
You could directly check the src/caffe/proto/caffe.proto. If you couldn't find anything with "ROI", you could add it manually.
Insert the following code in the line around 690.
message ROIPoolingParameter {
// Pad, kernel size, and stride are all given as a single value for equal
// dimensions in height and width or as Y, X pairs.
optional uint32 pooled_h = 1 [default = 0]; // The pooled output height
optional uint32 pooled_w = 2 [default = 0]; // The pooled output width
// Multiplicative spatial scale factor to translate ROI coords from their
// input scale to the scale used when pooling
optional float spatial_scale = 3 [default = 1];
}
Insert the following line in the line around 320
optional ROIPoolingParameter roi_pooling_param = 8266711;
Then build the caffe again with "make all; make pycaffe"
from fast-rcnn.
Good to hear.
from fast-rcnn.
hi, I have the same error as you, how do you re-compile the code, I recompile under the caffe-fast-rcnn root as caffe install guide,but after that ,the error still exist.
from fast-rcnn.
As I have explained, I check out the correct branch and then recompile the code, the error was gone.
I think you should to check that you checked out the correct branch fast-rcnn in the caffe-fast-rcnn root.
from fast-rcnn.
Hi,
I ran "git checkout master" on my current caffe-fast-rcnn root. Before recompiling, I do "make clean". However the following error occurs:
/bin/sh: /usr/local/cuda/bin/nvcc: No such file or directory
(standard_in) 1: parse error
Then I keep moving on, "make all", "make runtest"... No more error occurs. When I try to run the demo again, I however still encounter the same error as before:
$ ./tools/demo.py --cpu
[libprotobuf ERROR google/protobuf/text_format.cc:274] Error parsing text-format caffe.NetParameter: 392:21: Message type "caffe.LayerParameter" has no field named "roi_pooling_param".
WARNING: Logging before InitGoogleLogging() is written to STDERR
F0720 21:37:12.831410 1969263360 upgrade_proto.cpp:928] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: /Users/TRotK/fast-rcnn/models/VGG16/test.prototxt
*** Check failure stack trace: ***
Abort trap: 6
Any suggestion is appreciated!
from fast-rcnn.
Hi,
I have similar situation with above.
I'm using caffe-fast-rcnn the sam with fast-rcnn and checked "PYTHONPATH" parameter indicate the current directory by writing "export PYTHONPATH=/home/ch723.kim/samba/py-faster-rcnn-master/caffe-fast-rcnn/python:$PYTHONPATH" in the ~/.bashrc file.
But I have following error when playing demo.py as follows.
ch723.kim@ubuntu:~/samba/py-faster-rcnn-master$ ./tools/demo.py
[libprotobuf ERROR google/protobuf/text_format.cc:274] Error parsing text-format caffe.NetParameter: 310:18: Message type "caffe.LayerParameter" has no field named "reshape_param".
WARNING: Logging before InitGoogleLogging() is written to STDERR
F1205 21:22:31.945125 17247 upgrade_proto.cpp:928] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: /home/ch723.kim/samba/py-faster-rcnn-master/models/VGG16/faster_rcnn_alt_opt/faster_rcnn_test.pt
*** Check failure stack trace: ***
Aborted (core dumped)
Also I have the same error when I run "./experiments/scripts/faster_rcnn_alt_opt.sh 3 ZF" as follows.
I1205 21:16:10.417134 17205 solver.cpp:32] Initializing solver from parameters:
train_net: "models/ZF/faster_rcnn_alt_opt/stage1_rpn_train.pt"
base_lr: 0.001
display: 20
lr_policy: "step"
gamma: 0.1
momentum: 0.9
weight_decay: 0.0005
stepsize: 60000
snapshot: 0
snapshot_prefix: "zf_rpn"
average_loss: 100
I1205 21:16:10.417202 17205 solver.cpp:61] Creating training net from train_net file: models/ZF/faster_rcnn_alt_opt/stage1_rpn_train.pt
[libprotobuf ERROR google/protobuf/text_format.cc:274] Error parsing text-format caffe.NetParameter: 221:18: Message type "caffe.LayerParameter" has no field named "reshape_param".
F1205 21:16:10.417758 17205 upgrade_proto.cpp:928] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: models/ZF/faster_rcnn_alt_opt/stage1_rpn_train.pt
*** Check failure stack trace: ***
Please give me any suggestion.
Thank you.
from fast-rcnn.
Hello,
I want to start with Fast RCNN but I have this error
linux@linux-XPS-630i:~/FRCN_ROOT$ ./tools/demo.py --cpu
[libprotobuf ERROR google/protobuf/text_format.cc:245] Error parsing text-format caffe.NetParameter: 4:13: Message type "caffe.NetParameter" has no field named "input_shape".
WARNING: Logging before InitGoogleLogging() is written to STDERR
F1206 20:10:44.134786 28081 upgrade_proto.cpp:928] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: /home/linux/FRCN_ROOT/models/VGG16/test.prototxt
*** Check failure stack trace: ***
Abandon (core dumped)
Don't really know how to fix this error. I Hope you can help me.
from fast-rcnn.
I have similar situation with above.When i run python demo.py --cpu,I have the error 👍
C:\Users\Administrator>f:
F:>cd caffe\fast-rcnn-master\tools
F:\caffe\fast-rcnn-master\tools>python demo.py --cpu
D:\caffe\caffe-master\Build\x64\Release\pycaffe\caffe\pycaffe.py:13: Runtime
[libprotobuf ERROR ..\src\google\protobuf\text_format.cc:274] Error parsing text
-format caffe.NetParameter: 392:21: Message type "caffe.LayerParameter" has no f
ield named "roi_pooling_param".
WARNING: Logging before InitGoogleLogging() is written to STDERR
F0516 08:40:48.301647 5344 upgrade_proto.cpp:79] Check failed: ReadProtoFromTex
tFile(param_file, param) Failed to parse NetParameter file: F:\caffe\fast-rcnn-m
aster\models\VGG16\test.prototxt
*** Check failure stack trace: ***
F:\caffe\fast-rcnn-master\tools>
I have found lots of solution but still don't solve it.Please can you help me?This is my fast-rcnn folder:
from fast-rcnn.
Hello,
You have a problem in the download of fast RCNN, you must use this command
for donlowed the fast RCNN (git clone --recursive
https://github.com/rbgirshick/fast-rcnn.git), because you have
incompatibility between caffe and Fast RCNN (you dowlonded Fast with
Download Zip? )
2016-05-16 3:26 GMT+02:00 oversnowgrass [email protected]:
I have similar situation with above.When i run python demo.py --cpu,I have
the error [image: 👍]C:\Users\Administrator>f:
F:>cd caffe\fast-rcnn-master\tools
F:\caffe\fast-rcnn-master\tools>python demo.py --cpu
D:\caffe\caffe-master\Build\x64\Release\pycaffe\caffe\pycaffe.py:13:
Runtime
[libprotobuf ERROR ..\src\google\protobuf\text_format.cc:274] Error
parsing text
-format caffe.NetParameter: 392:21: Message type "caffe.LayerParameter"
has no f
ield named "roi_pooling_param".
WARNING: Logging before InitGoogleLogging() is written to STDERR
F0516 08:40:48.301647 5344 upgrade_proto.cpp:79] Check failed:
ReadProtoFromTex
tFile(param_file, param) Failed to parse NetParameter file:
F:\caffe\fast-rcnn-m
aster\models\VGG16\test.prototxt
*** Check failure stack trace: ***F:\caffe\fast-rcnn-master\tools>
I have found lots of solution but still don't solve it.Please can you help
me?This is my fast-rcnn folder:
[image: qq 20160516092511]
https://cloud.githubusercontent.com/assets/19328128/15278235/3ab64970-1b48-11e6-8199-81c3e49e00c5.png—
You are receiving this because you commented.
Reply to this email directly or view it on GitHub
#1 (comment)
from fast-rcnn.
Thank you for your letter while sleeping.I have downloaded the fast-rcnn in the right way,but it still appear the problem
Do you think there have any other solution to the problem?I'm looking forward to your letter.
from fast-rcnn.
how to solve this ?
WARNING: Logging before InitGoogleLogging() is written to STDERR
W0718 17:01:06.813407 26562 _caffe.cpp:122] DEPRECATION WARNING - deprecated use of Python interface
W0718 17:01:06.813459 26562 _caffe.cpp:123] Use this instead (with the named "weights" parameter):
W0718 17:01:06.813477 26562 _caffe.cpp:125] Net('/home/rvlab/Documents/fast-rcnn-master/models/VGG16/test.prototxt', 1, weights='/home/rvlab/Documents/fast-rcnn-master/data/fast_rcnn_models/vgg16_fast_rcnn_iter_40000.caffemodel')
[libprotobuf ERROR google/protobuf/text_format.cc:245] Error parsing text-format caffe.NetParameter: 392:21: Message type "caffe.LayerParameter" has no field named "roi_pooling_param".
F0718 17:01:06.815565 26562 upgrade_proto.cpp:79] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: /home/rvlab/Documents/fast-rcnn-master/models/VGG16/test.prototxt
*** Check failure stack trace: ***
Aborted (core dumped
from fast-rcnn.
hi,@rbgirshick @songjun54cm
I am in China where some places cannot use the git clone --recursive https://github.com/rbgirshick/fast-rcnn.git
. Once I did that, it would print time run out error. So I manually downloaded your zip fast-rcnn-master.zip
and unzip into the file FRCN_ROOT
. Then I followed your README.md and began from "3.Build the Cython modules": cd $FRCN_ROOT/lib &&make
. Everything was fine except for this
dawin@dawin-Lenovo:~/Downloads/FRCN_ROOT$ sudo ./tools/demo.py WARNING: Logging before InitGoogleLogging() is written to STDERR W0829 15:08:30.115890 7010 _caffe.cpp:122] DEPRECATION WARNING - deprecated use of Python interface W0829 15:08:30.115929 7010 _caffe.cpp:123] Use this instead (with the named "weights" parameter): W0829 15:08:30.115936 7010 _caffe.cpp:125] Net('/home/dawin/Downloads/FRCN_ROOT/models/VGG16/test.prototxt', 1, weights='/home/dawin/Downloads/FRCN_ROOT/data/fast_rcnn_models/vgg16_fast_rcnn_iter_40000.caffemodel') [libprotobuf ERROR google/protobuf/text_format.cc:245] Error parsing text-format caffe.NetParameter: 392:21: Message type "caffe.LayerParameter" has no field named "roi_pooling_param". F0829 15:08:30.118136 7010 upgrade_proto.cpp:79] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: /home/dawin/Downloads/FRCN_ROOT/models/VGG16/test.prototxt *** Check failure stack trace: ***
I had read all the blogs here and I tried, but I cannot figure out how to deal it.
I would appreciate your suggestions.
from fast-rcnn.
Related Issues (20)
- error(message('MATLAB:textread:FileNotFound')); HOT 1
- SyntaxError when l running demo.py HOT 1
- image_path_at : Path does not exist
- Python stopped working when execute 'self.solver.step(1)' code in 'train.py' file. HOT 2
- TypeError: 'numpy.float64' object cannot be interpreted as an index HOT 3
- ImportError: ~/fast-rcnn/caffe-fast-rcnn/distribute/python/caffe/_caffe.so: undefined symbol: _ZN5caffe34_PythonParameter_default_instance_E
- unable to run "fetch_faster_rcnn_models.sh" HOT 1
- Error test_roi_pooling_layer.cpp when running make test HOT 1
- annotation
- Fast-rcnn training error: Check failed: data_ *** Check failure stack trace: *** Aborted (core dumped) when training a VGG16 network HOT 1
- luguo
- nms.py - why are we incrementing inds of order?
- bbox.pyx line44, ih equation issue
- Can only predict one class
- How use first five layer?
- gtx 1080
- How to change VGG16 SSD 300*300 deploy.prototxt to work with 38 classes
- Confusion about the nms implementation HOT 1
- step by step understanding approximate joint training method
- approximate joint training method problem
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 fast-rcnn.