Comments (18)
Guys, the features extraction works on cpu!
GPU 3: 1/108067 91.213s (projected finish: 2738.10 hours) # 113 days
from bottom-up-attention.
From a computational perspective, the size of the input image doesn't matter as they are all resized to 600 pixels on the shortest side.
The easiest way to reduce the memory requirement is to reduce the SCALES
and MAX_SIZE
image parameters at test time. The parameters are defined here but you can set the values in this config file.
This might reduce the quality / number of features a bit, so a better option would be to maybe chop the network in half after the RPN layers, then run it in two stages (saving intermediate outputs). This would require modifying the code and network though.
Hope that helps.
from bottom-up-attention.
12g is enough.
as anderson said, i extract feature by run it in two stage.
split models/vg/ResNet-101/faster_rcnn_end2end_final/train.prototxt to
models/vg/ResNet-101/faster_rcnn_end2end_final/rpn.prototxt
models/vg/ResNet-101/faster_rcnn_end2end_final/rcnn.prototxt
and modify some code in tools/generate_tsv.py
good luck
from bottom-up-attention.
i have gpu 1080(8G memory)x4, is there anyway i can use multi gpu when predict?
from bottom-up-attention.
cpu mode running success too
from bottom-up-attention.
for generate feature, we need 12G per GPU?
from bottom-up-attention.
any idea to generate feature with 8G GPU x4 on private image data, cpu is a long long time......
from bottom-up-attention.
thx!
from bottom-up-attention.
@StephenZengCn how to solve this problem finally? I come across the same problem, and my gpu has 12g memory. Thanks.
from bottom-up-attention.
@StephenZengCn Thanks for your reply. I'm new to caffe. So it is possible for your to share the modifications to run the demo.ipynb? Thanks a lot!
from bottom-up-attention.
i didn't use demo.ipynb, just use generate_tsv.py to extract bottom-up features.
from bottom-up-attention.
@yangshao did u run demo.ipnb successfully ?
from bottom-up-attention.
12g is enough.
as anderson said, i extract feature by run it in two stage.
split models/vg/ResNet-101/faster_rcnn_end2end_final/train.prototxt to
models/vg/ResNet-101/faster_rcnn_end2end_final/rpn.prototxt
models/vg/ResNet-101/faster_rcnn_end2end_final/rcnn.prototxt
and modify some code in tools/generate_tsv.py
good luck
Hi @StephenZengCn ,
I am also facing the out-of-memory problem when trying to extract bottom-up features. Could you please share the detail (or these files) of how you split the network?
Thank you!
from bottom-up-attention.
Hi @StephenZengCn
Could you please share the scripts of them :)? I would really appreciate for the help.
from bottom-up-attention.
Does anyone have some no grad tricks like Variable(data, volatile=True)
in Pytorch, which doing forward calculation only rather than saving blobs for each layer.
from bottom-up-attention.
@coldmanck : I faced the same issue and the model really needed close to 10.5 gb of memory on a GPU. So I made sure that I have one with enough memory.
from bottom-up-attention.
I also met this problem when using 11g GPU. How I can solve it?
from bottom-up-attention.
I use this code to extract feature from VG datasets, and I found it was caused by some images with big difference in aspect ratio, for example 281 * 500, faster rcnn will scale based on the shorter one, so making the larger one to large.
this code may work on 11G gpu
from bottom-up-attention.
Related Issues (20)
- the link of resnet101_faster_rcnn_final_iter_320000.caffemodel is out of date. HOT 1
- Caffe Installation failed HOT 3
- Inference speed, is this normal?
- Quesntion about image size? HOT 1
- Could I ask about the relation id 's meaning?
- features of the model output are not consistent with those in the TSV file
- Trained with resnet152?
- No module named 'caffe._caffe' HOT 4
- How to run it on google colab HOT 1
- how to read complete tsv file through read_tsv.py?
- Exception: Input blob arguments do not match net inputs HOT 1
- how to train vg/VGG16/faster_rcnn_end2end_attr_softmax_primed/ and vg/VGG16/faster_rcnn_end2end_attr
- how to choose 10 images from Google Image? Want to initialize the classifier layer?
- Would someone please help with generating the features? HOT 1
- attribute classifier
- Does anyone have alternative pretrained model? HOT 1
- The result of the demo.inpynb error. HOT 1
- Could not download the alternative 36 features pretrained model HOT 2
- Do I need to install caffe if I just want to run demo.py? Or I can just start building the Cython modules?
- How to recreate the same features 36 of the links ? HOT 1
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 bottom-up-attention.