Comments (12)
@shadyatscu @Baby47 @ZhengMengbin @SM047
VoVNet backbone is stronger for small object detection.
I also plugged VoVNet-57 into the FCOS and got this result.
This is the initial version and I expect further accuracy gain after optimizing the code.
from fcos.
@shadyatscu The finest feature maps we use is 1/8 resolution of an input image. If you want to improve the performance of very small objects, you may use the feature maps with 1/4 resolution.
from fcos.
@shadyatscu The finest feature maps we use is 1/8 resolution of an input image. If you want to improve the performance of very small objects, you may use the feature maps with 1/4 resolution.
thanks for your reply, i change the configs followed your advice from the default
_C.MODEL.FCOS.FPN_STRIDES = [8, 16, 32, 64, 128]
to
_C.MODEL.FCOS.FPN_STRIDES = [4, 8, 16, 32, 64]
hope that works! thanks a lot!
from fcos.
@shadyatscu It is not correct if you only changed that. The code at
needs to be changed as well.from fcos.
Follow your advice i changed the code from the default:
in_channels_p6p7 = in_channels_stage2 * 8 if cfg.MODEL.RETINANET.USE_C5
else out_channels
fpn = fpn_module.FPN( in_channels_p6p7 = in_channels_stage2 * 8 if cfg.MODEL.RETINANET.USE_C5
else out_channels
in_channels_list=[
0,
in_channels_stage2 * 2,
in_channels_stage2 * 4,
in_channels_stage2 * 8,
],
to this:
fpn = fpn_module.FPN(
in_channels_list=[
0,
in_channels_stage2,
in_channels_stage2 * 2,
in_channels_stage2 * 4,
],
error occoured like this:
RuntimeError: Given groups=1, weight of size [256, 1024, 1, 1], expected input[2, 2048, 7, 8] to have 1024 channels, but got 2048 channels instead
i am confused about this part, could you plz give me some detailed advices?
from fcos.
@shadyatscu in order to use the feature maps with 1/4 resolution, you need to change the first 0 to in_channels_stage2
and add 4
to FPN_STRIDES
(i.e., [4, 8, 16, 32, 64, 128]
).
You also need to add the object_sizes_of_interest
for the level of feature maps to
from fcos.
@shadyatscu Have you tried as the author suggested, and if it works well too?
from fcos.
@shadyatscu Have you tried as the author suggested, and if it works well too?
I tried the suggestions of author, an error always occoured when i change 'the first 0 to in_channels_stage2', so still things to work on
from fcos.
@shadyatscu I guess you do not change this code(the number 5 should be modified to 6):
self.scales = nn.ModuleList([Scale(init_value=1.0) for _ in range(5)])
(the code is in /maskrcnn_benchmark/modeling/rpn/fcos/fcos.py)
It will report an Error!
from fcos.
I found FCOS was hard to detect small objects too. I think this problem is caused by center-ness branch. For example, a 16 * 16 bbox. The center-ness in P3 is probably 0.333. This value multiply class_pred gets a negative result.
I try to abandon the center-ness branch, a lot of low-quality predicted bounding boxes appear. Maybe a tricked center-ness ground truth for small objects is a solution.
from fcos.
@shadyatscu That's wonderful!!! Would you like to make your models publicly available? It will be very nice.
from fcos.
@stigma0617 [email protected] of 0.6 is not exactly 'stronger.' I've used SNIPER with similar results. The search continues...
https://github.com/mahyarnajibi/SNIPER
from fcos.
Related Issues (20)
- Can I use it on CPU?
- Can we use this FCOS algorithm for counting the objects in images??
- May I ask you for a train log file?
- Which is the accuracy index in the paper?
- Error pip install git+https://github.com/tianzhi0549/FCOS.git
- use my dataset to train FCOS net,why the loss is nan? HOT 2
- Can’t calculate the Params and FLOPs of Backbone
- Testing with test dataset while training
- ValueError: Unknown CUDA arch (8.6) or GPU not supported HOT 2
- weird time consuming of FCOS head when changing the backbone
- Problem with the last line of Testing-only installation HOT 1
- Deepcopy returns TypeError: 'int' object is not callable HOT 1
- assert len(proposal_losses) == 1 and proposal_losses["zero"] == 0 # loss_dict should be empty dict
- tools/train_net.py FAILED HOT 1
- Convert onnx
- Segmentation fault (core dumped)
- gempy to load csv data
- ImportError: cannot import name '_C'
- Why regression head wasn't normalized ?
- ValueError: num_samples should be a positive integer value, but got num_samples=0
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 fcos.