Comments (7)
@Xujianzhong 方便贴下代码链接么,我没有指定h为1。
from master-tf.
backbone:
gcb:
ratio: 0.0625
headers: 1
att_scale: True
fusion_type: 'channel_add' # channel_add channel_mul channel_concat
pooling_type: 'att'
layers:
- False
- True
- True
- True
headers被设置为1,还有一个疑问请教一下,为啥layers 的第一个被设置False?
from master-tf.
@jiangxiluning 你好,multi GC block在结构中放在Res block后面而不是放在里面,是为了减少计算复杂度?
from master-tf.
@Xujianzhong 你说的是headers, 1是当前数据集下做的最好的超参设置,第一个 resnet block 不需要加 gc 是原论文中的实验结论,放在 resnet block 以后是能够将结合 low-level feature 和 high-level feature 一起计算attention,效果更好吧。
from master-tf.
@jiangxiluning 但是代码实现的时候,好像又放在Res的里面了?
def call(self, inputs, **kwargs):
out = self.conv1(inputs)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.gcb(out)
out = out + self.downsample(inputs)
out = self.relu(out)
论文的结构是Res block重复堆叠后再加multi GC block
from master-tf.
哦,这里的实验实现是照搬原GCB的实现的,@Xujiangzhong, 我只是针对 GCB 放在 skip connection 之后做了一个讨论。
from master-tf.
@jiangxiluning 您好,方便加一下联系方式,交流沟通起来方便一些哈。qq 274543014
from master-tf.
Related Issues (17)
- english character or chinese words recognition? HOT 1
- 关于transformer_tf的Decoder中可能存在的一个bug HOT 3
- 测试精度问题 HOT 5
- About inference time HOT 3
- what's the difference between transformer_tf and transformer.py ? HOT 1
- The training phase converges quickly (acc>0.95), but the validate result is very bad (acc<0.3) HOT 4
- raise FileNotFoundError('LMDB file is not found. {}'.format(lmdb_path)) FileNotFoundError: LMDB file is not found. \data_lmdb_release\training\MJ\MJ_train
- raise FileNotFoundError('LMDB file is not found. {}'.format(lmdb_path)) FileNotFoundError: LMDB file is not found. \data_lmdb_release\training\MJ\MJ_train HOT 1
- write OCR in file log
- 代码怎样进行单张图片的推理啊?
- 请问这个模型对长文本的识别和CRNN比较,哪个效果好? HOT 1
- train_net.py 裡計算 step 和 epoch 總是不對
- Upload checkpoint to Google Drive HOT 3
- Hello, when I initialized the model, I only saw the decoder, not the GCAttention part HOT 2
- 模型输入尺寸是限定的吗 HOT 7
- pytorch implementation HOT 8
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 master-tf.