mirrors
/
fast-reid
mirror of https://github.com/JDAI-CV/fast-reid.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
508 Commits
1 Branch
4 Tags
15 MiB
Commit Graph

508 Commits (d792a69f3f69159ba3ca6341a8be0e6da2b31633)
 

Author SHA1 Message Date
liaoxingyu 154a06b875 refactor code 2020-09-23 19:31:46 +08:00
liaoxingyu 2f29228086 fix regnet cfg problem 2020-09-23 14:41:44 +08:00
liaoxingyu df823da09a fix typro bce loss 
close #273
 2020-09-18 10:39:10 +08:00
liaoxingyu d9a63a959f fix bug in mgn #272 
Summary: fix get_norm bug in mgn
 2020-09-17 18:17:53 +08:00
liaoxingyu 4fa3f08a4a fix typro 
close #268
 2020-09-14 11:34:28 +08:00
Lingxiao He cf246e9bee
Delete CrowdReID 
delete
 2020-09-11 15:53:17 +08:00
liaoxingyu c9824be7e1 fix non-local inter_channels 2020-09-10 11:40:13 +08:00
liaoxingyu 1f4e4909eb fix typro ##255 
fix #255
 2020-09-10 11:10:40 +08:00
liaoxingyu 74a6938289 fix typro 2020-09-10 11:04:59 +08:00
liaoxingyu 648198e6e5 add efficientnet support 2020-09-10 11:04:52 +08:00
liaoxingyu 296fbea989 extent gem pool 2020-09-10 11:01:22 +08:00
liaoxingyu 1b84348619 remove `num_splits` in batchnorm 
Summary: `num_splits` works for GhostBN, but it's very uncommon
 2020-09-10 11:01:07 +08:00
liaoxingyu 3c48bf78c1 change config file 2020-09-10 10:58:56 +08:00
liaoxingyu 4d573b8107 refactor reid head 
Summary: merge BNneckHead, LinearHead and ReductionHead into EmbeddingHead
because they are highly similar and can be prepared for ClsHead
 2020-09-10 10:57:37 +08:00
liaoxingyu 77caa01e34 fix memory leak in sgd #217 2020-09-10 10:50:22 +08:00
liaoxingyu aa5c422606 fix pair-wise circle loss 
fix #252
 2020-09-09 15:28:52 +08:00
liaoxingyu 919a515eb7 fix combine all training 2020-09-09 15:28:21 +08:00
wangguanan 7e2bc6873f support set up with conda 2020-09-08 11:14:05 +08:00
liaoxingyu 57710a9df7 add docs for amp training 2020-09-02 18:07:54 +08:00
liaoxingyu 53fed7451d feat: support amp training 
Summary: support automatic mixed precision training #217
 2020-09-02 18:03:12 +08:00
liaoxingyu 78f2166596 refactor mgn config 2020-09-02 18:01:07 +08:00
liaoxingyu 0d2c477060 update mgn config 2020-09-01 16:16:40 +08:00
liaoxingyu d00ce8fc3c refactor model arch 2020-09-01 16:14:45 +08:00
liaoxingyu 866a196d19 add more datasets support 2020-09-01 16:13:12 +08:00
liaoxingyu c1dc4919ef update model zoo 2020-08-31 18:23:14 +08:00
liaoxingyu 1d6e970260 fix typro #229 
fix #229
 2020-08-26 23:26:01 +08:00
liaoxingyu f06c8b2ed9 fix bug: make CJ works #239 
fix #239
 2020-08-25 11:31:49 +08:00
Xingyu Liao a2fe1f5271
fix typro 
fix typro in README
 2020-08-24 23:28:19 +08:00
liaoxingyu 9fb3285d5c rm extra sh file 2020-08-21 18:00:36 +08:00
liaoxingyu 198592a202 Merge branch 'master' of github.com:L1aoXingyu/fast-reid 2020-08-21 14:54:22 +08:00
liaoxingyu 5ea89bf607 fix bug in sampler 
Summary: remove set, which will lead to a bug in random choice.
 2020-08-21 14:54:17 +08:00
Xingyu Liao 8f65597d18
update pytorch version 2020-08-21 11:20:00 +08:00
liaoxingyu 8d4bd77ae3 fix visualization problem #233 2020-08-20 17:03:43 +08:00
liaoxingyu 07872d4cdb fix caffe export bug 
Summary: put tensor to gpu device
 2020-08-20 16:28:52 +08:00
liaoxingyu f4305b0964 fix bnneck 2020-08-20 16:21:14 +08:00
liaoxingyu ac8409a7da updating for pytorch1.6 2020-08-20 15:51:41 +08:00
liaoxingyu 9844760d7f fix naive sampler time-consuming problem 
Summary: list.remove has O(n) time complexity and use set instead.
 2020-08-20 15:44:26 +08:00
liaoxingyu 2c0320da1a fix bug in pid_dict 
Summary: id index will be different in different machine.
This will lead to different fc layer when training on different machine.
 2020-08-20 15:41:14 +08:00
liaoxingyu a5550d7725 fix balanced sampler bug 
Summary: fix typing error in balanced sampler with missing `len` in ret.
 2020-08-19 16:28:10 +08:00
liaoxingyu fd06a2819a delete sh file 2020-08-14 19:07:46 +08:00
liaoxingyu f29bc025cc update readme for distill 2020-08-14 19:06:36 +08:00
Xingyu Liao c01b859205
support distillation 
Merge distillation code from @wangguanan 

Reviewed by: l1aoxingyu
 2020-08-14 17:31:04 +08:00
liaoxingyu 9c667d1a0f add pretrain_path support in backbone 2020-08-14 14:00:26 +08:00
liaoxingyu e0cf8ac56e fix sampler problem #217 
Fix problem about periodic long waiting time when number of images is large.

In the old version, it will prepare the whole epoch indices when finishing one epoch.
Now it changes to prepare the current batch indices.
 2020-08-14 13:57:22 +08:00
liaoxingyu ae7c9288cf support faiss retrieval and cython roc evaluation 2020-08-12 16:27:57 +08:00
Xingyu Liao f74cebcd88
fix rank_cylib bug about valid query index 
fix bugs of rank_cylib

Reviewed by: l1aoxingyu
 2020-08-10 19:28:05 +08:00
liaoxingyu a198567f27 update ibn-net pretrain path 2020-08-10 14:51:35 +08:00
liaoxingyu db6b42da4f update resnest url 2020-08-10 14:18:00 +08:00
wangguanan dc9d1e39d0 add msmt17 results 2020-08-10 11:04:28 +08:00
wangguanan bbbcdb35ea add msmt17 results 2020-08-10 10:54:42 +08:00