Comments (17)
Hello, I have uploaded the weights for the code in the repo please let me know if the weights are still a problem as I recently changed countries and have limited access to old machines. When the number of gpus are changed please make sure to change other hyper parameters accordingly because if not scaled properly can lead to very bad results.
from ow-detr.
Hey,
I actually got very simular results to yours after 45 epochs:
Current class AP50: tensor(71.8500)
Current class Precisions50: 5.193744085759178
Current class Recall50: 87.56551145946715
Known AP50: tensor(71.8500)
Known Precisions50: 5.193744085759178
Known Recall50: 87.56551145946715
Unknown AP50: tensor(0.0407)
Unknown Precisions50: 0.4460528530550413
Unknown Recall50: 3.906291129244538
Did you evaluate after 45 epochs like in the codebase or 50 epochs like in the original publication?
from ow-detr.
Hey, I actually got very simular results to yours after 45 epochs:
Current class AP50: tensor(71.8500) Current class Precisions50: 5.193744085759178 Current class Recall50: 87.56551145946715 Known AP50: tensor(71.8500) Known Precisions50: 5.193744085759178 Known Recall50: 87.56551145946715 Unknown AP50: tensor(0.0407) Unknown Precisions50: 0.4460528530550413 Unknown Recall50: 3.906291129244538
Did you evaluate after 45 epochs like in the codebase or 50 epochs like in the original publication?
45 epochs
from ow-detr.
Hey, I actually got very simular results to yours after 45 epochs:
Current class AP50: tensor(71.8500) Current class Precisions50: 5.193744085759178 Current class Recall50: 87.56551145946715 Known AP50: tensor(71.8500) Known Precisions50: 5.193744085759178 Known Recall50: 87.56551145946715 Unknown AP50: tensor(0.0407) Unknown Precisions50: 0.4460528530550413 Unknown Recall50: 3.906291129244538
Did you evaluate after 45 epochs like in the codebase or 50 epochs like in the original publication?
Did you train the results on the experiment iOD? I can't get similar results.
from ow-detr.
Hello @orrzohar-stanford @aooating The paper uses 2 open-world splits and I have provided config files for both the splits. Can you specify which split is causing the problem?
from ow-detr.
Hello @orrzohar-stanford @aooating The paper uses 2 open-world splits and I have provided config files for both the splits. Can you specify which split is causing the problem?
/data/OWDETR/VOC2007/ImageSets/t1_train.txt
from ow-detr.
The results for these splits are present here -> https://arxiv.org/pdf/2112.01513.pdf in Table 6
from ow-detr.
The results for these splits are present here -> https://arxiv.org/pdf/2112.01513.pdf in Table 6
As for the results of 19+1 setting in Table 2, I only got mAP 61. I don't know the reason.
from ow-detr.
for that their are a lot of HP changes involved. You can experiment with a few like change in Lr, epochs, finetuning-epochs, finetuning LR.
from ow-detr.
I wonder if batch size has a great impact on the experimental results? I used two 3090ti to train the model (which means that the batch size is 4). When I trained 30 epochs, the evaluation results of the model are as follows:
It is too far from the results reported in the paper. What may be the reason for this,what may be the reason for this?
from ow-detr.
Hey, I actually got very simular results to yours after 45 epochs:
Current class AP50: tensor(71.8500) Current class Precisions50: 5.193744085759178 Current class Recall50: 87.56551145946715 Known AP50: tensor(71.8500) Known Precisions50: 5.193744085759178 Known Recall50: 87.56551145946715 Unknown AP50: tensor(0.0407) Unknown Precisions50: 0.4460528530550413 Unknown Recall50: 3.906291129244538
Did you evaluate after 45 epochs like in the codebase or 50 epochs like in the original publication?
Hello, how many GPUs did you use for training? Is it V100? Could you share the log files of the whole training process?
from ow-detr.
from ow-detr.
Hey, I actually got very simular results to yours after 45 epochs:
Current class AP50: tensor(71.8500) Current class Precisions50: 5.193744085759178 Current class Recall50: 87.56551145946715 Known AP50: tensor(71.8500) Known Precisions50: 5.193744085759178 Known Recall50: 87.56551145946715 Unknown AP50: tensor(0.0407) Unknown Precisions50: 0.4460528530550413 Unknown Recall50: 3.906291129244538
Did you evaluate after 45 epochs like in the codebase or 50 epochs like in the original publication?Hello, how many GPUs did you use for training? Is it V100? Could you share the log files of the whole training process?
Hey @chengsilin, I used 8 V100s. I sent the logs to your email
from ow-detr.
Hey, I actually got very simular results to yours after 45 epochs:
Current class AP50: tensor(71.8500) Current class Precisions50: 5.193744085759178 Current class Recall50: 87.56551145946715 Known AP50: tensor(71.8500) Known Precisions50: 5.193744085759178 Known Recall50: 87.56551145946715 Unknown AP50: tensor(0.0407) Unknown Precisions50: 0.4460528530550413 Unknown Recall50: 3.906291129244538
Did you evaluate after 45 epochs like in the codebase or 50 epochs like in the original publication?Hello, how many GPUs did you use for training? Is it V100? Could you share the log files of the whole training process?
Hey @chengsilin, I used 8 V100s. I sent the logs to your email
Thanks for your reply @orrzohar-stanford
Here, I still have a question: does it true that you use create_imagenets_t1.py file to generate the test sample corresponding to task 1 during the test stage, instead of directly using the test.txt file provided by the code base?
from ow-detr.
I wonder if batch size has a great impact on the experimental results? I used two 3090ti to train the model (which means that the batch size is 4). When I trained 30 epochs, the evaluation results of the model are as follows: It is too far from the results reported in the paper. What may be the reason for this,what may be the reason for this?
Hi @chengsilin , could you share your 30-epoch pretrained model? This really helps. Thanks in advance.
from ow-detr.
Hi @chengsilin, @akshitac8
I am Tin who is a CS student,
I really appreciate your research and training work that is really helpful in the AI community.
For now, I really need a pre-trained model for my research, because your work is one of a few models that can get the unknown boxes.
So it would be really kind of you if you could share it with me, please.
My email is [email protected] if you want to share it privately.
Best regards,
Tin
from ow-detr.
Thank @akshitac8 for providing us with the weights for the code. Now, I can use it for my own research! 😄 .
Best regards,
Tin
from ow-detr.
Related Issues (20)
- Deploying this model to an edge device.
- The link is still 404. When will it be ready?
- CUDA out of memory HOT 2
- Configs for Reproducing ORE Results on OW-DETR benchmark
- NotImplementedError: Cuda is not availabel HOT 1
- Could you please upload the log.txt file
- 12
- what does this function do?
- How to reimplement your work?
- I can't find this file configs/OWOD_new_split_eval.sh
- OWDETR_t4_ft
- size miss match in 'target' when transforming HOT 5
- I want to know how the visualization in Figure 5 is drawn HOT 1
- About training strategy
- About fine-tuning
- 'OWEvaluator' object has no attribute 'known_classes’ HOT 1
- Hard codes backbone model path
- where the "data/VOC2007/ImageSets/Main/train.txt"
- Unable to run the project at all! HOT 36
- data split
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 ow-detr.