Comments (3)
@PKUWison they should be related to s_min and s_max, but in the original implementation they are just hard-coded. I think, that the authors experimented with these values, and in the paper they provide only some of the heuristics.
from ssd_keras.
Really thanks for your answers. I have another question, I want to run the SSD model on a public dataset. But the labels of the dataset are saved in .mat file. I don't know how to transfer the .mat file to the .XML file. And I don't know whether the .XML file has any rigid requirements or not. Thanks in advance. @rykov8
from ssd_keras.
@PKUWison you could use loadmat fucntion from scipy. Actually, you don't need to convert annotations to xml, I use a little bit more convenient (at least for me) format. It was described several times in issues, e.g. in #15
from ssd_keras.
Related Issues (20)
- ValueError: shape mismatch: value array of shape (45,20) could not be broadcast to indexing result of shape (45,3) HOT 2
- work files HOT 2
- errors occurred while detecting one picture with no objects
- meaning of syntax : โencoded_box[:, -1][assign_mask] = iou[assign_mask]โ
- function "detection_out()" issue
- TypeError: list indices must be integers or slices, not tuple HOT 1
- Did this implementation do the train data normalization?
- How to Store Coordinates only once?
- Keras yolov3 Mobilenet
- prior_width should be prior_height ?
- I got an error: 'module' object is not callable HOT 3
- how could i do if i want to evaluate my model when coords='minmax'?
- list indices must be integers or slices, not tuple HOT 1
- YOLOv3 Mobilenet VOC2007test
- PriorBox layer
- output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None
- Dimensions must be equal, but are 512 and 38 for 'conv4_3_norm/mul' HOT 2
- Re-implemented SSD has high loss and low acc during training HOT 3
- loss function define?
- cannot import name 'AtrousConvolution2D' from 'keras.layers' HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ssd_keras.