Comments (18)
23pointsNorth
commented on July 27, 2024
2
Another addition would be
-
Mask R-CNN.
code: https://github.com/CharlesShang/FastMaskRCNN -
FC DenseNet The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
code: https://github.com/SimJeg/FC-DenseNet
from chainercv.
yuyu2172
commented on July 27, 2024
Thumbs up on this issue. 👍
I would prefer a model which we can compare performance to the reported ones.
from chainercv.
zori
commented on July 27, 2024
@23pointsNorth Just to mention Mask R-CNN is for instance segmentation and cannot produce a semantic segmentation. Otherwise, certainly a good to have one!
from chainercv.
souravsingh
commented on July 27, 2024
I am interested in working on the issue
from chainercv.
yuyu2172
commented on July 27, 2024
Cool! Which model are you interested in?
from chainercv.
souravsingh
commented on July 27, 2024
@yuyu2172 I am interested in adding U-Net and FC DenseNet.
from chainercv.
yuyu2172
commented on July 27, 2024
Nice. I would love to have those added.
It would be nice if the PR has the similar structure as this one #757
from chainercv.
kumasento
commented on July 27, 2024
Hi @mitmul , sorry for bothering you, but I'm really curious about how to reproduce the result you've got for SegNet on CamVid. I tried the script with its default setting, but the best evaluation mIoU I can get is just 0.3368. Maybe you ran it for longer time than 16k iterations? Thanks!
from chainercv.
mitmul
commented on July 27, 2024
@kumasento I haven’t confirmed the reproduction with newer version of ChainerCV code by myself for a long while, so let me check the result using the latest version again. I’ll run this example:
https://github.com/chainer/chainercv/tree/master/examples/segnet
from chainercv.
kumasento
commented on July 27, 2024
@mitmul Thank you very much! That's the exact script I've run before.
from chainercv.
mitmul
commented on July 27, 2024
@kumasento I ran the script and got the following result (I removed log lines containing only training error information):
$ python calc_weight.py
$ MPLBACKEND=Agg python train.py --gpu 0
epoch iteration elapsed_time lr main/loss validation/main/miou validation/main/mean_class_accuracy validation/main/pixel_accuracy
65 2000 1117.47 0.1 0.187626 0.569284 0.772247 0.855193
130 4000 2229.86 0.1 0.105407 0.543893 0.701374 0.855025
196 6000 3340 0.1 0.110691 0.361815 0.59967 0.650387
261 8000 4448.21 0.1 0.10473 0.500844 0.703283 0.821186
326 10000 5555.72 0.1 0.341374 0.27762 0.541763 0.551853
392 12000 6666.44 0.1 0.0865148 0.501126 0.657423 0.830836
457 14000 7776.4 0.1 0.114381 0.534688 0.750539 0.835903
523 16000 8884.18 0.1 0.101966 0.588422 0.763433 0.879876
So, the final mIoU reached to 0.588422 that is somehow better than the results reported in the README of this example code. What versions of Python, Chainer, ChainerCV and CuPy did you use? My environment was:
$ python -V
Python 3.7.4
$ python -c 'import chainer; print(chainer.print_runtime_info())'
Platform: Linux-4.15.0-58-generic-x86_64-with-debian-buster-sid
Chainer: 7.0.0
ChainerX: Not Available
NumPy: 1.17.4
CuPy:
CuPy Version : 7.0.0
CUDA Root : /usr/local/cuda
CUDA Build Version : 10010
CUDA Driver Version : 10010
CUDA Runtime Version : 10010
cuBLAS Version : 10201
cuFFT Version : 10101
cuRAND Version : 10101
cuSOLVER Version : (10, 2, 0)
cuSPARSE Version : 10300
NVRTC Version : (10, 1)
cuDNN Build Version : 7605
cuDNN Version : 7605
NCCL Build Version : 2402
NCCL Runtime Version : 2402
iDeep: Not Available
Could you also give me the log?
from chainercv.
kumasento
commented on July 27, 2024
Thanks for your update! I think the result you’ve gotten is validation
accuracy, but the one listed in the table means test accuracy, if I
understand correctly. You can use the evaluation script to evaluate this
snapshot to give a double check :)
…On Thu, 9 Jan 2020 at 01:20, Shunta Saito ***@***.***> wrote:
@kumasento <https://github.com/kumasento> I ran the script and got the
following result (I removed log lines containing only training error
information):
$ python calc_weight.py
$ MPLBACKEND=Agg python train.py --gpu 0
epoch iteration elapsed_time lr main/loss validation/main/miou validation/main/mean_class_accuracy validation/main/pixel_accuracy
65 2000 1117.47 0.1 0.187626 0.569284 0.772247 0.855193
130 4000 2229.86 0.1 0.105407 0.543893 0.701374 0.855025
196 6000 3340 0.1 0.110691 0.361815 0.59967 0.650387
261 8000 4448.21 0.1 0.10473 0.500844 0.703283 0.821186
326 10000 5555.72 0.1 0.341374 0.27762 0.541763 0.551853
392 12000 6666.44 0.1 0.0865148 0.501126 0.657423 0.830836
457 14000 7776.4 0.1 0.114381 0.534688 0.750539 0.835903
523 16000 8884.18 0.1 0.101966 0.588422 0.763433 0.879876
So, the final mIoU reached to 0.588422 that is somehow better than the
results reported in the README of this example code
<https://github.com/chainer/chainercv/blob/master/examples/segnet/README.md>.
What versions of Python, Chainer, ChainerCV and CuPy did you use? My
environment was:
$ python -V
Python 3.7.4
$ python -c 'import chainer; print(chainer.print_runtime_info())'
Platform: Linux-4.15.0-58-generic-x86_64-with-debian-buster-sid
Chainer: 7.0.0
ChainerX: Not Available
NumPy: 1.17.4
CuPy:
CuPy Version : 7.0.0
CUDA Root : /usr/local/cuda
CUDA Build Version : 10010
CUDA Driver Version : 10010
CUDA Runtime Version : 10010
cuBLAS Version : 10201
cuFFT Version : 10101
cuRAND Version : 10101
cuSOLVER Version : (10, 2, 0)
cuSPARSE Version : 10300
NVRTC Version : (10, 1)
cuDNN Build Version : 7605
cuDNN Version : 7605
NCCL Build Version : 2402
NCCL Runtime Version : 2402
iDeep: Not Available
Could you also give me the log?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#158?email_source=notifications&email_token=ACC42R3MJHCXKNV6VICAA2DQ4Z3WRA5CNFSM4DKPZMA2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEIOSRXQ#issuecomment-572336350>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ACC42R6NXVQUOUITPKSYVMLQ4Z3WRANCNFSM4DKPZMAQ>
.
from chainercv.
mitmul
commented on July 27, 2024
@kumasento OK, thanks for the guide. I'll run the evaluation on the test dataset. Please give me some more time.
from chainercv.
mitmul
commented on July 27, 2024
@kumasento I ran the evaluation on the test dataset of CamVid with this script:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import argparse
import json
from chainer import iterators
from chainer.dataset import concat_examples
from chainer.serializers import load_npz
from chainercv.datasets import CamVidDataset, camvid_label_names
from chainercv.evaluations import eval_semantic_segmentation
from chainercv.links import SegNetBasic
from chainercv.utils import apply_to_iterator
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('--snapshot', type=str,
default='result/snapshot_model.npz')
parser.add_argument('--batchsize', type=int, default=12)
parser.add_argument('--gpu', type=int, default=0)
args = parser.parse_args()
test = CamVidDataset(split='test')
test_iter = iterators.SerialIterator(
test, args.batchsize, shuffle=False, repeat=False)
model = SegNetBasic(n_class=len(camvid_label_names))
load_npz(args.snapshot, model)
model = model.to_gpu(args.gpu)
in_values, out_values, rest_values = apply_to_iterator(
model.predict, test_iter)
del in_values
pred_labels, = out_values
gt_labels, = rest_values
result = eval_semantic_segmentation(pred_labels, gt_labels)
print(f"miou: {result['miou']}")and got miou: 0.4834565081914471 that is actually worse than the reported value in the README (49.4 %) but better than the original value of 46.3 %.
I used this snapshot:
snapshot_model.npz.zip
So, from my experiments, it seems not to succeed to reproduce your result with miou: 0.3368.
Could you also let me know the information about your environment?
from chainercv.
kumasento
commented on July 27, 2024
@mitmul Thanks! I can achieve the same accuracy a you did with the same snapshot. I will rerun the training and see whether I can get the same level of accuracy.
from chainercv.
kumasento
commented on July 27, 2024
BTW my environment:
$ python -V
Python 3.7.3
$ python -c 'import chainer; print(chainer.print_runtime_info())'
Platform: Linux-4.4.0-142-generic-x86_64-with-debian-stretch-sid
Chainer: 6.3.0
NumPy: 1.16.4
CuPy:
CuPy Version : 6.3.0
CUDA Root : /usr/local/cuda-10.1
CUDA Build Version : 10010
CUDA Driver Version : 10010
CUDA Runtime Version : 10010
cuDNN Build Version : 7602
cuDNN Version : 7602
NCCL Build Version : 2402
NCCL Runtime Version : 2402
iDeep: Not Available
None
from chainercv.
kumasento
commented on July 27, 2024
@mitmul After running again and using the snapshot that has the highest validation accuracy, I can now get a good test accuracy :) Thanks
from chainercv.
mitmul
commented on July 27, 2024
@kumasento Good!
from chainercv.
Related Issues (20)
- Faster RCNN training result problem HOT 2
- Add a img.resize function in utils HOT 2
- A function to return segmented image HOT 2
- no module named 'chainercv.datasets' HOT 6
- Problems of FCIS HOT 6
- Problem about eval_detection HOT 2
- Accuracy problems of FCIS example HOT 5
- loc_normalize_std in ProposalTargetCreator HOT 5
- yolo/train_v3.py does not work HOT 2
- DirectoryParsingLabelDataset fails to read images with an alpha channel
- Allow empty object bounding box for SSD training
- `neg_iou_thresh_lo` value in `ProposalTargetCreator`
- Is it fixed for loading the trained weights for FPN model? HOT 2
- Change Request in chainercv/examples/fpn/train_multi.py HOT 1
- build wheels for chainerCV failed HOT 1
- can't install environment, invalid channel HOT 3
- "Introduction to Chainer" doc link broken
- Request for train.py for YOLO
- eval_semantic_segmentation and calc_semantic_segmentation_confusion for when we have ignore label
- possible bug in the way that mIoU is computed
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 chainercv.