Comments (4)
@cuicuizhang1989 @Frandre You can simply add the VP branch to deploy.prototxt as follows.
layer {
name: "vp-conv"
type: "Convolution"
bottom: "L6d"
top: "vp-conv"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 128
kernel_size: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "vp-tile"
type: "Tiling"
bottom: "vp-conv"
top: "vp-conv-tiled"
tiling_param {
tile_dim: 8
}
}
# Pixel level softmax prediction.
layer {
name: "vp-prob"
type: "Softmax"
bottom: "vp-conv-tiled"
top: "vp-prob"
}
from vpgnet.
I am also interested in the VP part. However, I did not find it predicted in deploy.prototxt. I wish I was wrong here.
from vpgnet.
@cuicuizhang1989 @Frandre FYI, the python code to localize the VP is as below.
vp_prob = net.blobs['vp-prob'].data[0]
[vp_y, vp_x] = vp_quadrant(vp_prob)
def vp_quadrant(prob):
prob[0,:,:] = scipy.ndimage.filters.gaussian_filter(prob[0,:,:], 5)
prob[1,:,:] = scipy.ndimage.filters.gaussian_filter(prob[1,:,:], 5)
prob[2,:,:] = scipy.ndimage.filters.gaussian_filter(prob[2,:,:], 5)
prob[3,:,:] = scipy.ndimage.filters.gaussian_filter(prob[3,:,:], 5)
prob[4,:,:] = scipy.ndimage.filters.gaussian_filter(prob[4,:,:], 5)
P_avg = (1 - np.mean(prob[0,:,:])) / 4
avg_map = np.ones(prob[0,:,:].shape) * P_avg
loc_map = np.power((avg_map-prob[1,:,:]), 2) + np.power((avg_map-prob[2,:,:]), 2) + np.power((avg_map-prob[3,:,:]), 2) + np.power((avg_map-prob[4,:,:]), 2)
[y, x] = np.unravel_index(loc_map.argmin(), loc_map.shape)
return [y, x]
from vpgnet.
@SeokjuLee Hi, as you have provided the VP branch deploy.prototxt, can you also provide VP branch train.prototxt ?
And also, I didn't find label data for VP branch in dataset. How can I label VP information in my own dataset?
from vpgnet.
Related Issues (20)
- facing a problem when make all HOT 2
- face a problem when caffe compile HOT 1
- Request for a license HOT 1
- IPM corner points
- Nobody cares this project?
- ENet-Label-Torch is available now (a light-weight and effective lane detection model)
- Test code on other data sets HOT 1
- the dataset and pre-trained model HOT 2
- A good value for test result
- about multi label grid box and object mask some problem HOT 1
- Make runtest failed on Ubuntu 16.04 and CUDA 10.0
- Dataset HOT 14
- Bounding Box Regression task not learning, it has constant loss
- Training on VPGNet dataset. HOT 3
- Make error : src/caffe/util/io.cpp:73:34: error: ‘CV_LOAD_IMAGE_HDR’ was not declared in this scope HOT 2
- Inference scripts using pretrained model
- Could you provide me how you split training set and testing set in your dataset like Table 1 HOT 1
- Could you provide the camera parameters?
- the loss of vp
- no image
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 vpgnet.