zhanghang1989 / zhanghang1989/PyTorch-Encoding
The time and some problems for test.py
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 448
- PR merge metrics
- No merged PRs in 30d
Description
Hello, I just set up the environment and configured the PASCAL Context API.
Now I am running python test.py --dataset PContext --model-zoo Encnet_ResNet50_PContext --eval according to the instructions given by the author.
According to the author's github. The picture shows that the total is 1276, but my total is 2552.
And the time I run indicates that I have to run 36 hours. Would you like to ask, does it take so long to run test.py? My environment is Ubuntun14.04+Chainer, CPU: Intel(R) Xeon(R) CPU E5-2643; memory size: 64 GB; GPU: NVIDIA Tesla K40 m×2; memory size: 12 GB×2.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with test.py and reproduce the documented python test.py --dataset PContext --model-zoo Encnet_ResNet50_PContext --eval command using the reported PASCAL Context API setup. Compare the reported total of 2552 with the author's 1276 and measure the runtime; the issue is done when the discrepancy and expected execution time are explained.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100