Comments (9)
这个在哪个文件第几号报错?另外,你是否改动过测试代码tester.py?
from dual_encoding.
我没有改动过tester.py
具体错误如下
Traceback (most recent call last):
File "/data/projects/untitled/tester.py", line 136, in
main()
File "/data/projects/untitled/tester.py", line 110, in main
torch.save({'errors': c2i_all_errors, 'videos': video_ids, 'captions': caption_ids}, pred_error_matrix_file)
File "/data/anaconda3/envs/pytorch/lib/python2.7/site-packages/torch/serialization.py", line 161, in save
return _with_file_like(f, "wb", lambda f: _save(obj, f, pickle_module, pickle_protocol))
File "/data/anaconda3/envs/pytorch/lib/python2.7/site-packages/torch/serialization.py", line 116, in _with_file_like
f = open(f, mode)
IOError: [Errno 20] Not a directory: '/home/VisualSearch/testCollection/runs/model_best.pth.tar/pred_errors_matrix.pth.tar'
from dual_encoding.
保存相似度矩阵的时候报了错,你可以注释掉line 110,这不影响测试。
你看看是否存在/home/VisualSearch/testCollection/runs/model_best.pth.tar这个文件夹,如果存在请列出下面的文件。另外,你的testCollection是不是弄错了?应该是marvvt10ktest
from dual_encoding.
非常感谢!我注释掉110行之后就运行成功了。
但是我无法提取model_best.pth.tar文件下的文件。显示压缩文件格式错误。
请问这个压缩文件有什么特殊的提取方法吗?
from dual_encoding.
train目录下的model_best.pth.tar是pytorch保存模型文件,test目录下的model_best.pth.tar是文件夹而不是文件。我感觉你哪里改了代码,测试的时候理论上会自动生成/home/VisualSearch/testCollection/runs/model_best.pth.tar这个文件夹,然后把相识度矩阵保存在该文件夹下
from dual_encoding.
我运行tester的时候无法自动生成model_best.pth.tar是文件夹。
最开始运行时,他会显示错误:
[28 Apr 16:21:50 - tester.py:line 55] runs/model_best.pth.tar not exists.
于是我就把train目录下的model_best.pth.tar是pytorch保存模型文件复制到/home/VisualSearch/testCollection/runs下
再次运行,还是会显示:
[28 Apr 16:21:50 - tester.py:line 55] runs/model_best.pth.tar not exists.
此时,我就将52行的路径为resume = os.path.join(opt.logger_name, opt.checkpoint_name)
改为了
resume = os.path.join(ROOT_PATH,testCollection,opt.logger_name, opt.checkpoint_name)
此时就会报110行代码的错误。
我按照刚刚你说的方法,将110行注释掉,就可以运行了。
除此之外并没有修改tester的任何代码。
请问我按照以上方法运行出的tester是否正确?为何我不能自动生成test目录下的model_best.pth.tar是文件夹
from dual_encoding.
https://github.com/danieljf24/dual_encoding#expected-performance 按这个你能运行吗?
另外,你不应该去改代码,而是改脚本 --logger_name 指定你model_best.pth.tar在的位置
from dual_encoding.
我们可以加一个联系方式吗?qq?微信?
from dual_encoding.
你把你的微信号发我邮箱吧 [email protected]
from dual_encoding.
Related Issues (20)
- Experiments on MSVD and MPII-MD HOT 1
- #10 More details about MSVD on zero-example video retrieval HOT 12
- A question about MPII-MD
- Error while training HOT 3
- torch.backends.cudnn.CuDNNError: 8: CUDNN_STATUS_EXECUTION_FAILED HOT 3
- The model is very sensitive to the batch size HOT 2
- Issue about dataset format HOT 2
- Evaluating performance on a single video
- Could this work do video to text task?
- Anyone run this code on python3? HOT 2
- Code for newly published TPAMI2021 version HOT 2
- Alternative to baidu for downloading the frame features.
- IP not active
- Training time on MSVD dataset
- Question about feature extraction method HOT 1
- about the testing result
- about the testing result HOT 1
- Seeking information for CNN model used on MSRVTT
- ./do_test_dual_encoding_msrvtt10ktest.sh: 没有那个文件或目录 HOT 4
- An error when perform script HOT 1
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 dual_encoding.