Comments (14)
Yes, F-score can be calculated by json files saved in score_dir. But my evaluation code is quite messy, I may rewrite and upload it after final exam of this semester. If you are in a hurry to use it, please leave your email and I will send it to you as soon as possible!
from fcsn.
@SSSTEWARDDD
you're student?? Wow!!
if you're okay, can i write code and pull request??
Take a good look at the exam!!
from fcsn.
Thank you, because my research direction is this, I have been thinking about doing this in the near future. If you can send the test code to me, thank you very much. My email address is [email protected]
from fcsn.
@SSSTEWARDDD
you're student?? Wow!!
if you're okay, can i write code and pull request??Take a good look at the exam!!
Thank you so much if you can provide your code and I will try my best to prepare for the exam!
from fcsn.
Thank you, because my research direction is this, I have been thinking about doing this in the near future. If you can send the test code to me, thank you very much. My email address is [email protected]
I have sent the code to your email, hope it can help you!
from fcsn.
@SSSTEWARDDD
If you don't mind, could I also get your test code?
And I wonder your code performance is similar to paper
Thank you and I also hope you take a good look at the exam!
from fcsn.
@SSSTEWARDDD
If you don't mind, could I also get your test code?
And I wonder your code performance is similar to paperThank you and I also hope you take a good look at the exam!
You can download my evaluation code from here
from fcsn.
I am facing with this qunestion "RuntimeError: expected a non-empty list of Tensors". Can you help me, thanks!
from fcsn.
please, explain more detailed.
( e.g. which situation, where line in code, etc )
from fcsn.
拜托,解释得更详细。
(例如,哪种情况,代码行等)
Traceback (most recent call last):
File "train.py", line 119, in
solver.train()
File "train.py", line 73, in train
mean_loss = torch.stack(sum_loss_history).mean().item()
RuntimeError: expected a non-empty list of Tensors
from fcsn.
- Did you just execute code without editing?
- Did you download dataset?
- Did you load dataset correctly?
p.s. I want to make new issue. because this issue is about F-Score.
from fcsn.
拜托,解释得更详细。
(例如,某些情况下,代码行等)追溯(最近一次通话最近): solver.train()中的
文件“ train.py”,第119 行,火车中的文件“ train.py”,行73, mean_loss = torch.stack(sum_loss_history).mean()。item () RuntimeError:预期张量的非空列表
I have encountered the same problem. How did you solve it?
from fcsn.
@SSSTEWARDDD
If you don't mind, could I also get your test code?
And I wonder your code performance is similar to paper
Thank you and I also hope you take a good look at the exam!You can download my evaluation code from here
Hi @weirme
Can not open the link ~ can you share the link again
thanks
from fcsn.
Can someone please tell me, is the F-core code of the warehouse updated at present? I use my own dataset for experiments and the F-core is always 0
from fcsn.
Related Issues (20)
- Hello,Can you send me a dataset? HOT 4
- Hello,can you tell me the concrete structure of the unsupervised FCSN?
- gen_summary failed with IndexError HOT 6
- Is it able to summarize a custom video? HOT 1
- The architecture of the FCSN is different from the paper
- Could you share the SumMe dataset on your google drive?
- KeyError: "Unable to open object (object 'video_tensor(41)' doesn't exist)" HOT 10
- Can you provide‘.h5’ files under three settings of dataset?
- provide data/files (ydata-tvsum50-v1_1)
- hello,Are you the author of the paper?
- How to do this in colab
- index 5866 is out of bounds for axis 0 with size 5846 HOT 1
- A mistake in train.py line 48
- Implementation of Reconstruction and Diversity loss
- Is the model same as discussed in the paper??
- IndexError: index 202 is out of bounds for axis 0 with size 0 HOT 1
- fcsn_dataset.h5
- train on my own dataset
- How test this on single video?
- unable 同openobject(object ‘video_-esJrBWj2d8’ doesn't exit)
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 fcsn.