Comments (9)
Hi, there! I faced the same issue, but finally find the errors in PVAnet_test.py. Here is the lines I've changed to make the test work:
lines to comment:
85 --> .scale(c_in=384, name='conv5_4/last_bn_scale')
118 --> (self.feed('convf_rpn', 'convf_2')
119 --> .concat(axis=3, name='convf'))
lines to change:
92 --> (self.feed('downsample', 'conv4_4', 'upsamle') ---> (self.feed('downsample', 'conv4_4')
121 --> (self.feed('convf', 'rois') ---> (self.feed('convf_2', 'rois')
122 --> .roi_pool(7, 7, 1.0/16, name='roi_pooling') ---> .roi_pool(6, 6, 1.0/16, name='roi_pooling')
Hope this will help!
BTW, as mentioned by @jwnsu, test error is quite high. I trained the model using VOC2012 data with 200000 iters, the mAP is about 0.03, which is totally unacceptable. I am gonna train the model with more iters, and meanwhile, check the PVAnet to see if it is the same with the caffe version mentioned by @autumnqin.
Will update if any news.
from tffrcnn.
Was it solved?
There must be a typo in the test net.
I'll run some debug in my spare time
from tffrcnn.
test error is easy to resolve, however it has very high error (mAP is below 0.1) -- caffe version is one of most accurate models. It seems conv2_1/1/conv layer is different from the paper, can also be caused by issue in pva_negation_block/v2.
from tffrcnn.
train is different from test, and both are different from Caffe version
from tffrcnn.
@baileyqbb Haven't you figured out the issue with the low mAP by any chance?
from tffrcnn.
Hi guys, can anyone please share some tips on improving the mAP?
from tffrcnn.
thank you very much @baileyqbb
from tffrcnn.
@baileyqbb @QueenJuliaZxx do you run pva-faster-rcnn successfully?my pva.npy seem to be wrong.where do you download?what the script command do you run ?thanks for your help
from tffrcnn.
@baileyqbb
thank you so much 👍
it works very well 💯 🥇
from tffrcnn.
Related Issues (20)
- Error compiling Cython file
- My GPU card doesn't support cuda,can I use your code?
- easydict HOT 1
- How to load tensorflow's new v2 format checkpoint? HOT 1
- Meet some problems when training on my own data. See below. HOT 3
- ZF_imagenet.npy file
- nvcc fatal : A single input file is required for a non-link phase when an outputfile is specified HOT 2
- NameError: name 'xrange' is not defined HOT 1
- AttributeError: 'NoneType' object has no attribute 'model_checkpoint_path'
- demo.py HOT 2
- Nontype error when run demo and train HOT 4
- A question about anchors HOT 1
- How to load half of the trained model, then go to that point to train
- About BachNorm Layer
- deform_conv.so: undefined symbol: _ZN10tensorflow8internal21CheckOpMessageBuilder9NewStringB5cxx11Ev HOT 1
- Compile Error
- I want to ask how i can get the model when i run the demo.py
- TypeError: 'NoneType' object is not subscriptable
- For getting more accuracy in faster rcnn , which parameters i have to tune (tuning parameters)
- potential bug in __init__.py
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 tffrcnn.