-
Greetings！
I read your paper again and again recently, and I really learned a lot from your work. For the retrain part, I met some problems, would you like to help to answer?
At first, I noticed…
-
It's really beautiful workflow diagram, in the Feature maps(N, 512, H/4, W/4), i am feel confused that after four pooling layer in VGG network, it's height(width) may be H/(2^4) = H/16?
-
Hi, Thanks for your amazing work.
When retraining the model,I changed the encoder of UNet from vgg to resnet,the following error occurred.What is the reason?How to solve it?
 and replace vgg with mobilenet/shufflenet? could you give me some suggestion to…
-
Can you share neural_style configs used at ostagram? I can't get results with clean neural_style from repo similar to "wow" ostagram ouput. Are you using special model or just VGG_ILSVRC_19_layers?
zezic updated
8 years ago
-
Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1356, in _do_call
return fn(*args)
File "/usr/local/lib/python3.5/…
-
### Deep Learning Simplified Repository (Proposing new issue)
:red_circle: **Project Title** : Skin Disease Classification using Deep Learning Models
:red_circle: **Aim** : To build a model to cla…
-
Hi @Sy-Zhang, for 2D-TAN, I think the charades dataset file is not working, tried running the python file for the conversion. Did not seem to work or generate anything.
Can you guide me over that?
…
-
大神您好
我实现过一版VGG16作为backbone的FPN faster rcnn，用来做车辆检测，但是效果惨淡， 车辆的ap大约0.63左右，甚至还没有不用FPN的好。我自己实现的非FPN的 faster rcnn能到0.78。差的还挺多的。
以您的经验，有没有可能VGG16这个主干网不太适合用来实现FPN啊。
此外就是ROI pooling那里，原文中看到的是不同大小的ROI会在不同层…
-
Hello,
After running the **_th train.lua -gpu -1_** command it shows the following output:
loading network weights from .. VGG_ILSVRC_16_layers.caffemodel
**Couldn't load /home/sentinel/5G - …