Comments (3)
Hi,
May be the names might not be similar however the architecture is same. In case if you feel that there is difference in architecture please pin point where is the difference.
Thanks
from scl.
Thanks for your reply!
In [(https://github.com/harsh-99/SCL/blob/master/lib/model/faster_rcnn/vgg16_dfrcnn.py)]
class netD_img(nn.Module):
def init(self, beta=1, ch_in=1024, ch_out=1024, W=38, H=75, stride_1=1, padding_1=1, kernel=3):
super(netD_img, self).init()
self.conv_image = nn.Conv2d(ch_in, ch_out, stride=stride_1, padding=padding_1, kernel_size=kernel)
self.bn_image = nn.BatchNorm2d(ch_out)
self.fc_1_image = nn.Linear(1, 2)
self.ch_out = ch_out
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=2)
self.bn_2 = nn.BatchNorm2d(ch_out)
#self.softmax = nn.Softmax()
#self.logsoftmax = nn.LogSoftmax()
def forward(self, x):
x = self.conv_image(x)
x = self.relu(x)
x = self.bn_image(x)
x = self.maxpool(x)
x = self.bn_2(x)
# convert to 1024WH x 1.
x = flatten(x)
x = torch.transpose(x, 0, 1)
x = self.fc_1_image(x)
# 1 x n vector
#y = self.softmax(x)
#x = self.logsoftmax(x)
#return x, y
return x
I noticed that you used the BN layer and max pool layer, which didn't seem to exist in the original implementation. Are they necessary and why add these layers?
from scl.
Hi,
Thanks for pointing out. I checked with my colleague about the same and found that this slight difference is to stabilize the training. However the overall architecture is kept same.
Thanks
from scl.
Related Issues (20)
- Experimental details HOT 1
- visualization of features from PASCAL to Clipart HOT 1
- Applying SCL on SSD HOT 1
- Can this method be used as unsupervised object detection, if yes then how to do object detection on unlabelled target domain data HOT 4
- How to do Object detection on target domain(ex: Clipart) that don't have annotation.xml label HOT 2
- Can I run this Solution in real time or without the need to train the target data HOT 3
- About cityscape and foggy dataset HOT 3
- Can i generate or train model using this method and run it on different dataset/images that is similar to target domain data but this new dataset don't exist in target domain data when it was trained
- Run trainval_net_SCL.py with custom dataset raises RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. HOT 4
- How can I add custom new class labels, lets say-x classes to a SCL trained model( which is already trained on y classes). So I do not replace those y classes and in total I have x+y class labels. HOT 1
- About sim10k dataset HOT 2
- Your implementation of domain adaptive faster rcnn performs better than paper values, what might be the reason? HOT 1
- About the trained model. HOT 1
- after filtering, there are 0 images HOT 1
- question of t-sne
- Heat Map
- About cityscape-->foggy cityscape test set
- Using multilple GPUs to accomplish distributed training HOT 1
- ImportError: No module named cython_bbox HOT 1
- File "/home/lty/anaconda3/envs/SWDA/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 301, in forward self.padding, self.dilation, self.groups) RuntimeError: cublas runtime error : the GPU program failed to execute at /opt/conda/conda-bld/pytorch_1525909934016/work/aten/src/THC/THCBlas.cu:249
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 scl.