Comments (5)
-
Yes. I ran the official Caffe2 implementation of Detectron on HICO-DET dataset. The filename gives you the cue about the parameters, i.e. R-50-PFN_2x.
-
As for training, I didn't use anything from tf-faster-rcnn. Could you please specify in which line of my training code you found tf-faster-rcnn is involved? I will take a look at it. Thanks!
from ican.
- Yes. I ran the official Caffe2 implementation of Detectron on HICO-DET dataset. The filename gives you the cue about the parameters, i.e. R-50-PFN_2x.
- As for training, I didn't use anything from tf-faster-rcnn. Could you please specify in which line of my training code you found tf-faster-rcnn is involved? I will take a look at it. Thanks!
In lib/networks/iCAN_ResNet50_HICO.py
, the implementation of backbone is similar to the one in tf-faster-rcnn, but I'm not sure whether they're exactly the same.
iCAN/lib/networks/iCAN_ResNet50_HICO.py
Lines 289 to 293 in 752ce5b
Additionally, it seems that the pretrained weights of Faster R-CNN
Weights/res50_faster_rcnn_iter_1190000.ckpt
were loaded before training, so during the training process, the model gets detection results from itself instead of Detectron, which is different from the way in the testing process.from ican.
@gaochen315 Sorry for my mistake, I've read your code carefully, and it seems that you've used a refined ResNet-50 (only stage 1 to stage 4) for feature extraction before the three streams. So I wonder whether the feature extraction network has been pre-trained on any datasets or it can be trained end-to-end during the training process of the whole model?
Thank you for your attention!
from ican.
The feature extraction network is initialized from tf-faster-rcnn's model (trained on COCO). It is not trained from scratch.
from ican.
The feature extraction network is initialized from tf-faster-rcnn's model (trained on COCO). It is not trained from scratch.
Thank you!
from ican.
Related Issues (20)
- What is the data format in 'Trainval_GT_VCOCO.pkl'? HOT 1
- about training loss
- about the negative samples? HOT 1
- visualizing the attention maps HOT 2
- No prior_mask.pkl file and no detection on Djokovic image HOT 3
- Why is fc7_SH and fc7_SO sent into the classifier
- How to generate my "Trainval_GT_VCOCO.pkl"and "Trainval_Neg_VCOCO.pkl"
- About the batchsize and epoch?
- Testing without train using pretrained weights HOT 2
- The single category score in the output value is greater than 1 HOT 1
- python3 with tensorflow1.13 HOT 1
- How to train on my own image dataset? HOT 2
- Visualize the attention map using heatmap HOT 2
- How to use trained model after finishing the training HOT 3
- Annotations for objects and verbs HOT 4
- Prior_mask.pkl and action_index.json missing HOT 2
- the reason for considering negative samples
- Performing Demo on Video Directly HOT 1
- Questions about test output for HICO
- How is the trainval_GT and trainval_Neg files prepared HOT 2
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 ican.