-
Notifications
You must be signed in to change notification settings - Fork 584
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Add] Support HOTA evaluation for MOTChallenge. #417
Conversation
# Use 'track' as the default tracker | ||
TRACKERS_TO_EVAL=['track'], | ||
# Option values: ['pedestrian'] | ||
CLASSES_TO_EVAL=['pedestrian'], |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We have self.classes
, is CLASSES_TO_EVAL
related to this item?
# Option values: ['pedestrian'] | ||
CLASSES_TO_EVAL=['pedestrian'], | ||
# Option Values: 'MOT17', 'MOT16', 'MOT20', 'MOT15' | ||
BENCHMARK=self.img_prefix.rsplit('/', 2)[-2], |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is risky, write a function to convert lower-case names, and raise errors if there are no specific benchmarks in their names.
'to manually install trackeval') | ||
|
||
seqmap = osp.join(self.img_prefix, 'videoseq.txt') | ||
if not osp.exists(seqmap): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Add document instructions to indicate dataset preparations.
Codecov Report
@@ Coverage Diff @@
## master #417 +/- ##
==========================================
+ Coverage 70.89% 70.98% +0.09%
==========================================
Files 117 117
Lines 6249 6296 +47
Branches 1198 1208 +10
==========================================
+ Hits 4430 4469 +39
- Misses 1458 1459 +1
- Partials 361 368 +7
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
'to manually install trackeval') | ||
|
||
# get video name sequence for HOTA evaluation | ||
seqmap = osp.join(self.img_prefix, 'videoseq.txt') |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we online generate this txt ?
change CI and install.md |
docs/zh_cn/install.md
Outdated
@@ -51,7 +51,16 @@ | |||
|
|||
如果不是安装预构建的包,而是从源码中构建 PyTorch,则可以使用更多的 CUDA 版本,例如 CUDA 9.0。 | |||
|
|||
3. 安装 mmcv-full,我们推荐您安装以下预构建包: | |||
3. 为VOT数据集测试评估安装额外库(可选) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
typically, we need add a blank space between Chinese and English
No description provided.