Comments (13)
Yeah, you need to download the predictions of the interactiveness model, then use them as the reference in NIS function.
Any problems?
from transferable-interactiveness-network.
Thanks for your reply!
One more question:
Should I replace the '60000_TIN_VCOCO_D.pkl' and '80000_TIN_D_noS.pkl' when testing my model in hico and vcoco dataset cause the best binary_score in these two file(used in NIS) is no long match the index of my trained model's predicted hoi pairs? Or I should keep them?
from transferable-interactiveness-network.
Yeah, if you have replaced the human-object pairs, like the boxes, then the interactiveness binary scores are no longer suitable.
You could retrain the interactiveness model and the HOI model on your own pairs.
Then after obtaining your own best interactiveness scores, you may use them to filtering the non-interactive pairs.
from transferable-interactiveness-network.
Got it! Thanks for your reply!
Then I want to ask where I can download your predictions of the interactiveness model of vcoco?
from transferable-interactiveness-network.
You could use:
python script/Download_data.py 1sjV6e916NIPcYYqbGwhKM6Vhl7SY6WqD -Results/80000_TIN_D_noS.pkl
python script/Download_data.py 1sJipmoZ-5u0ymm8diqYd5Yqk2A-QQBXN -Results/60000_TIN_VCOCO_D.pkl
to download the interactiveness scores for HICO-DET and V-COCO, or you may just directly run the script: script/download_dataset.sh. It will get everything done.
from transferable-interactiveness-network.
I have download the 60000_TIN_VCOCO_D.pkl following the script, but when I open the pickle file, I didn't find the binary score for NIS, and in fact I found the 60000_TIN_VCOCO_D.pkl is a file after NIS.
The picture below shows it, and where I should find the binary score?
from transferable-interactiveness-network.
from transferable-interactiveness-network.
Sorry for my carelessness, thanks a for your patience. I will close the issue.
from transferable-interactiveness-network.
File "tools/vcoco_lis_nis.py", line 184, in generate_pkl
score_binary_d = np.array(dic_d['binary_score'])
KeyError: 'binary_score'the dic_d is 60000_TIN_VCOCO_D.pkl, and I have download it from https://docs.google.com/uc?export=download&id=1sJipmoZ-5u0ymm8diqYd5Yqk2A-QQBXN
I have downloaded the prediction file but still got a KeyError when running Test_TIN_VCOCO.py
. Could you please tell me how do you solve this problem?
from transferable-interactiveness-network.
File "tools/vcoco_lis_nis.py", line 184, in generate_pkl
score_binary_d = np.array(dic_d['binary_score'])
KeyError: 'binary_score'
the dic_d is 60000_TIN_VCOCO_D.pkl, and I have download it from https://docs.google.com/uc?export=download&id=1sJipmoZ-5u0ymm8diqYd5Yqk2A-QQBXNI have downloaded the prediction file but still got a KeyError when running
Test_TIN_VCOCO.py
. Could you please tell me how do you solve this problem?
Thanks for using our code! Would you mind providing more detailed error information?
from transferable-interactiveness-network.
Thanks for your reply, especially in this Dragon Boat Festival holiday! Finally I fixed this error by changing the key from 'binary_score'
to b'binary_score'
, and now it works fine. By the way , How do you guys get the HO_weight
and H_weight
appeared in the TIN_VCOCO.py
?
from transferable-interactiveness-network.
Thanks for your reply, especially in this Dragon Boat Festival holiday! Finally I fixed this error by changing the key from
'binary_score'
tob'binary_score'
, and now it works fine. By the way , How do you guys get theHO_weight
andH_weight
appeared in theTIN_VCOCO.py
?
Please refer to #36 for detailed description. The weight generation strategies for HICO-DET and V-COCO are the same.
from transferable-interactiveness-network.
Got it! Many thanks for helping:)
from transferable-interactiveness-network.
Related Issues (20)
- about test the model,mAP value is too low HOT 1
- The eigenvector shape problem of early fusion and late fusion
- The shape of pool5_O in early and late fusion HOT 1
- self.spatial = tf.placeholder(tf.float32, shape=[None, 64, 64, 3], name = 'sp') HOT 9
- What is the reason for using negative examples? HOT 4
- problem in installing HOT 4
- Questions about the ablation studies HOT 2
- About self.HO_weight HOT 1
- V-COCO training results is bad HOT 2
- The empty detections
- the pre-trained weight
- augment and pos_augment? HOT 1
- the code for ten part boxes HOT 1
- What is the approximate speed of video real-time motion detection?
- where to find or download the file res50_faster_rcnn HOT 2
- Bad evaluation results HOT 1
- How to use code to infer in my own data set? My own data set is not labeled, just want to see the actual application effect of HOI algorithm HOT 1
- Question about final HOI classification scores HOT 4
- Issue Downloading Pretrained Weight Files HOT 3
- raceback (most recent call last): │ File "tools/Vcoco_lis_nis.py", line 304, in <module> │ generate_result = generate_pkl(mode, test_D, test_result, prior_mask, Action_dic_inv, (6, 6, 7, 0), args.prior_flag) │ File "tools/Vcoco_lis_nis.py", line 145, in generate_pkl │ score_binary_d = np.array(dic_d['binary_score']) │KeyError: 'binary_score'
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 transferable-interactiveness-network.