Comments (4)
You could modify the option "model. img_feature_size" in the file "rva/configs/rva.yml" from 2048 to 1024.
from rva.
You could modify the option "model. img_feature_size" in the file "rva/configs/rva.yml" from 2048 to 1024.
感谢你的回复,但我还是想问下,为什么detectron提取出来的是1024,但模型使用的都是2048,这个是如何变化的呢?如果将文件中的 "model. img_feature_size" 改为1024会对结果有什么影响吗?因为我是在想利用以前的提取特征方法,将自己的数据集重新提取特征,跟原来batra-mlp-lab提取的特征保持一致,然后夹杂着一起使用,我看大家都是用的detectron来提取的特征,但我在使用时发现提取的特征是(36,1024)的,如果我直接利用全连接层将这个特征的shape改成(36,2048),然后放入到原来提取好的特征中,我怕这样会对我的结果产生影响。
from rva.
You could modify the option "model. img_feature_size" in the file "rva/configs/rva.yml" from 2048 to 1024.
感谢你的回复,但我还是想问下,为什么detectron提取出来的是1024,但模型使用的都是2048,这个是如何变化的呢?如果将文件中的 "model. img_feature_size" 改为1024会对结果有什么影响吗?因为我是在想利用以前的提取特征方法,将自己的数据集重新提取特征,跟原来batra-mlp-lab提取的特征保持一致,然后夹杂着一起使用,我看大家都是用的detectron来提取的特征,但我在使用时发现提取的特征是(36,1024)的,如果我直接利用全连接层将这个特征的shape改成(36,2048),然后放入到原来提取好的特征中,我怕这样会对我的结果产生影响。
请问你用的哪一个detectron的模型?根据batra-mlp-lab的代码https://github.com/batra-mlp-lab/visdial-challenge-starter-pytorch/blob/master/data/extract_features_detectron.py,提取特征的模型是基于faster_rcnn_x101的,你可以选取对应的模型提取自己的特征
from rva.
You could modify the option "model. img_feature_size" in the file "rva/configs/rva.yml" from 2048 to 1024.
感谢你的回复,但我还是想问下,为什么detectron提取出来的是1024,但模型使用的都是2048,这个是如何变化的呢?如果将文件中的 "model. img_feature_size" 改为1024会对结果有什么影响吗?因为我是在想利用以前的提取特征方法,将自己的数据集重新提取特征,跟原来batra-mlp-lab提取的特征保持一致,然后夹杂着一起使用,我看大家都是用的detectron来提取的特征,但我在使用时发现提取的特征是(36,1024)的,如果我直接利用全连接层将这个特征的shape改成(36,2048),然后放入到原来提取好的特征中,我怕这样会对我的结果产生影响。
请问你用的哪一个detectron的模型?根据batra-mlp-lab的代码https://github.com/batra-mlp-lab/visdial-challenge-starter-pytorch/blob/master/data/extract_features_detectron.py,提取特征的模型是基于faster_rcnn_x101的,你可以选取对应的模型提取自己的特征
是的,我就是选择的他所说的模型,但是特征shape不对应,不太理解。
from rva.
Related Issues (9)
- The file 'init_glove.py' is missing. HOT 1
- Extracting features HOT 1
- Parallelization error HOT 1
- how to visualize val result ?
- Question about Gumbel Sampling HOT 1
- AttributeError: 'ImageFeaturesHdfReader' object has no attribute 'loc_feats' HOT 1
- About Straight Through Gumbel Softmax HOT 1
- the loss is NAN
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 rva.