Comments (5)
Hello, it's been a while since I read the paper, so I don't remember my thought process regarding why I went ahead with a scale of 0,1 for conv4_3
.
Looking at the paper now, in Section 3.1 (Page 7), it is stated the conv4_3
will use a scale of 0.1.
We set default box with scale 0.1 on
conv4_3
.
So does this mean s_min
is now 0.1? Apparently not, because the paper treats conv4_3
as somewhat of a special case and considers s_min
to be the scale of conv7
instead. And from conv7
onwards, they are regularly spaced up to s_max
.
This is apparent in their wording throughout the paper. At the end of page 7:
For SSD512 model, we add extra
conv12_2
for prediction, sets_min
to 0.15, and 0.07 onconv4_3
.
Here too, the scale for conv4_3
is set separately.
On page 11:
We follow the strategy mentioned in Sec. 2.2, but now our smallest default box has a scale of 0.15 instead of 0.2, and the scale of the default box on
conv4_3
is 0.07 (e.g. 21 pixels for a 300 × 300 image)
For SSD512 model, we add extra
conv12_2
for prediction, sets_min
to 0.1, and 0.04 onconv4_3
.
I don't remember if my understanding of this is as clear now as it was when I wrote the code, but this is all I can tell you now, off the top of my head. I'm sure I must have been confused at that time too, and I must've checked with other repositories to confirm. This paper is a little too empirical sometimes.
from a-pytorch-tutorial-to-object-detection.
We set default box with scale 0.1 on conv4_3.
Oh, it's written!!!
Thanks a lot! You saved a lot of my time!
from a-pytorch-tutorial-to-object-detection.
I have same question.
But many SSD's implementation use s_1 = 0.1
.
e.g.) ssd.pytorch
...
s_k = self.min_sizes[k]/self.image_size
...
min_size = [30, 60, 11, 262, 213, 264]
. So, s_1 =30/300=0.1
.
Where s_k=0.1
is from?? I can't find one in original paper...
from a-pytorch-tutorial-to-object-detection.
Author says "An alternative way of improving SSD is to design a better tiling of default boxes so
that its position and scale are better aligned with the receptive field of each position on
a feature map. We leave this for future work."
s_1=0.1
may be from feature work :(
EDIT:
chainercv's issue comments helped me.
from a-pytorch-tutorial-to-object-detection.
which relationship between anchors and min_size. Suppose I have 6 anchors box (w:h) (100,50)(125:75)(150:175), (175,180),(205,175),(235,153). How to calculate min_size, max_size. Thanks in advance if share the formular.
from a-pytorch-tutorial-to-object-detection.
Related Issues (20)
- Wrong feature map size after conv7 in the picture
- What is the order of execution of programs
- in eval.py RuntimeError: legacy constructor expects device type: cpu but device type: cuda was passed
- Accuracy, precision, recall ,TF,FP,FN,TN
- gender classification
- How to use on custom dataset HOT 2
- Possible bug in the trained checkpoint?
- MultiBox Los Calculation
- broken .tar file with pretrained model
- classification layers arent training
- PredictionConvolutions separates locs and classes, doesn't follow the paper?
- Pre-trained model is not available HOT 2
- What if the x_min, y_min(or x_max, y_max) goes beyond (0, 1) when decoding gxgy to xy?
- question about MultiBoxLoss and the Model HOT 1
- FileNotFoundError: [Errno 2] No such file or directory: 'generator_checkpoint19.pth.tar'
- Can I use it for realtime or video
- prior box not clipped as expected HOT 12
- performence with not clipped prior boxes HOT 1
- mAP is 0
- ONNX model
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 a-pytorch-tutorial-to-object-detection.