Comments (6)
We have tried multiple times (did it today as well) with the pre-trained model on CrowdHuman and fine-tuning it on CityPersons. Till now we got 9.56 on the reasonable set of CityPerson on the 3rd epoch (its still running). Since we used 7 gpus(2im/gpu) with learning rate 0.02. Learning rate you set also seems fine according the linear scaling rule. Maybe try 0.001 for starters.
Additionally, what is the LAMR you get when you simply apply (without fine-tuning) on CityPersons the pre-trained model on CrowdHuman ?
from pedestron.
Thanks for your reply!!
The performance of the pre-trained CrowdHuman model (without fine-tuning on CityPersons) is really good (15.53 MR-2). The pre-trained CrowdHuman model is directly downloaded from the link of Google Drive you have provided. Can I directly use it to fine-tune on Citypersons? Or should I train the CrowdHuman model by myself and then fine-tune on Citypersons? I have also tried to use the ECP pre-trained model (also downloaded from the Google Drive) to fine-tune on Citypersons, and I face the same problem as CrowdHuman. I have tried learning rate from 0.0005 to 0.02, but the performance seems unsatisfactory (1st epoch nearly 100MR-2 on Citypersons).
I want to ask for advice:
- can I directly download the pre-trained model on Google Drive and fine-tune on the other dataset?
- will the training with the single GPU influence the performance during fine-tuning?
- I just modify the Config file to use the pre-trained CrowdHuman model. Is it correct? For example, I modify the file 'configs/elephant/cityperson/cascade_hrnet.py' pretrained='open-mmlab://msra/hrnetv2_w32' -> pretrained=path of the downloaded pre-trained model.
Thank you again for your reply!!!!
from pedestron.
I think I know the problem (see point 3).
-
Yes, you can and you should use the pre-trained model we provide for fine-tuning (that is why we provide it for general person detection).
-
It might effect but the effect should not be huge. I mean you can expect a performance drop of 1 or 2 MR-^2 points, but not what you are getting.
-
This is where the problem is, if you want to fine-tune using a pre-trained model, you do not change the pre-trained path, instead (undo it and use as provided in cofig file), in the config file, near the end you have a field
load_from
, which is set toNone
by default. Pass the model along with its path and you should be good to go.
load_from = './models_pretrained/epoch_19.pth'
P.S:- The code might complain that epoch_19.pth is missing (since you have epoch_19.pth.stu), simply make a copy of epoch_19.pth.stu as epoch_19.pth.
This was also discuss here #17 near the end
from pedestron.
It really works!!! Thank you very much!! :)
I have fine-tuned on the Citypersons with the pre-trained CrowdHuman model (AP84.2), and I got 9.25 on the Reasonable set (2nd epoch) with lr 0.001 (1 img, 1GPU).
The problem before was the incorrect manner to load the pre-trained model.
from pedestron.
It really works!!! Thank you very much!! :)
I have fine-tuned on the Citypersons with the pre-trained CrowdHuman model (AP84.2), and I got 9.25 on the Reasonable set (2nd epoch) with lr 0.001 (1 img, 1GPU).
The problem before was the incorrect manner to load the pre-trained model.
Would you kindly share your full command used for this, because I'm struggling with almost the same issue.
Thank you.
from pedestron.
It really works!!! Thank you very much!! :)
I have fine-tuned on the Citypersons with the pre-trained CrowdHuman model (AP84.2), and I got 9.25 on the Reasonable set (2nd epoch) with lr 0.001 (1 img, 1GPU).
The problem before was the incorrect manner to load the pre-trained model.Would you kindly share your full command used for this, because I'm struggling with almost the same issue.
Thank you.
I just modify the config file "load_from = None -> load_from = path of the pre-trained model".
from pedestron.
Related Issues (20)
- Docker image is not working! HOT 4
- Impact of mean_teacher on the training process HOT 1
- CSP pretrained weights HOT 1
- Reproduce resutls on Caltech dataset HOT 3
- Information regarding the training HOT 1
- Image_scale of Caltech while training HOT 6
- ImportError: /pedestron/tools/../mmdet/ops/dcn/deform_conv_cuda.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E HOT 1
- RuntimeError: Expected cudaMemcpy(&mask_host[0], mask_dev, sizeof(unsigned long long) * boxes_num * col_blocks, cudaMemcpyDeviceToHost) == cudaSuccess to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.) HOT 1
- Training citypersons with all the instances? HOT 1
- Welcome update to OpenMMLab 2.0
- Runtime error - Training with EuroCity persons HOT 1
- Training Caltech using CSP HOT 1
- What's ignore_other_vru in ECP evaluation? HOT 2
- result has no bbox HOT 5
- mmdet/ops/roi_align/src/roi_align_kernel.cu(145): error: identifier "THCudaCheck" is undefined HOT 1
- Update instruction for 2023 HOT 1
- custom dataset test HOT 1
- Evaluate different pre-trained model
- A request for advice on pedestrian tracking work. HOT 2
- a bug when converting crowdhuman to coco format
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 pedestron.