hahattpro / crowd_counting_framework (public) (License: Unspecified) (since 2020-12-23) (hash sha1)
backupfrom https://github.com/ttpro1995/crowd_counting_framework
Clone URLs: https://rocketgit.com/user/hahattpro/crowd_counting_framework ssh://rocketgit@ssh.rocketgit.com/user/hahattpro/crowd_counting_framework git://git.rocketgit.com/user/hahattpro/crowd_counting_framework
debug/a-1 develop feature/add_can_adcrowdnet feature/add_context_aware_network feature/attn_can_adcrowd_simple feature/cache_dataloader feature/compact_cnn feature/compare_with_original_count feature/dataloader_not_divide_8 feature/debug_viz feature/documentation feature/improve_density_gen feature/improve_loss_fn feature/loader_full_and_augment feature/refactor-dataflow feature/refactor_ccnn_basecode feature/save_best feature/simple_cometml feature/train_context_aware_network_on_shtA feature/train_dev_test_split hotfix/fix_visualize_data_loader master meow_exp server-training with_apex
List of commits:
Subject Hash Author Date (UTC)
debug dataset_name thing 7331c2ce0e1aff3daea07ca20ed681ceacc4d4b0 Thai Thien 2020-02-29 16:53:04
ready train keepfull 24e7e7f29248f609b26999b2b8564b1157231f49 Thai Thien 2020-02-29 16:41:59
print 9ba6ea17ab117e362360afa3ee541a219c240d49 Thai Thien 2020-02-29 16:33:39
add some if else a086920254c085f8ae8aa30498d3181cfee45443 Thai Thien 2020-02-29 02:22:52
fix args dataset name 55aa10b342aa2921639ddb214c91a1ece401d400 Thai Thien 2020-02-29 02:04:00
fix deprecate d16b3ed34285df19d950d4f0472867020922cb91 Thai Thien 2020-02-29 01:56:38
fix dataset_name 16a6b9ccc89d647c239778662d1371f4e43c864a Thai Thien 2020-02-29 01:40:50
fix my_args_parse c0f526e0affc64cc00134a84c8c7275e91297b70 Thai Thien 2020-02-29 01:36:50
minor fix 8f3909b1a4c62e67bc2a8c2f218fc0697ff7cef3 Thai Thien 2020-02-29 01:35:32
train script 96afb84e92320e5389a302964b6a5d68186f6435 Thai Thien 2020-02-29 01:32:14
done 12f18f211de9ae25ee3ed25812cef1c7a361b31d Thai Thien 2020-02-29 01:30:11
fix error: argument --decay: invalid float value: '5*1e-4' a144c83e69e4363311fa74f1c091d1a3f834ad8a Thai Thien 2020-02-28 17:16:41
change optim to Adam, lr and decay same with content aware network 0b0879b22e9d202015e67a0cc8c87ddcafb3c2d2 Thai Thien 2020-02-28 17:15:05
train with higher learning rate 3fa7e328dc4b7b4570fd32908b3df5fab8283919 Thai Thien 2020-02-28 16:57:16
train 25 epoch only 1cfb58b5eae299f49e3b64289c3a12a8f35cee45 Thai Thien 2020-02-27 18:35:58
we freeze vgg pretrain layer 459cefbfbf53949cb9636ca002cd4f78e964bb83 Thai Thien 2020-02-27 18:24:17
fix error when save 86a8f467d47a67da0accc963e8baacbaea07ab14 Thai Thien 2020-02-27 17:55:46
we discard deform 7 and keep deform 5 instead 91ff78e4a1aef3677b15447b631c2927c9e62a31 Thai Thien 2020-02-27 16:22:47
reduce image by crop 530516ff40b744cac79756c97faaed50c8b65cfb Thai Thien 2020-02-27 16:19:11
try to solve x8/8 dimension mismatch 6b0616197995b3c95041cde43030245f96f1f81e Thai Thien 2020-02-27 16:17:12
Commit 7331c2ce0e1aff3daea07ca20ed681ceacc4d4b0 - debug dataset_name thing
Author: Thai Thien
Author date (UTC): 2020-02-29 16:53
Committer name: Thai Thien
Committer date (UTC): 2020-02-29 16:53
Parent(s): 24e7e7f29248f609b26999b2b8564b1157231f49
Signer:
Signing key:
Signing status: N
Tree: 73fe0797a822c852b6d47ab2e2ee71f4a1b7dcc7
File Lines added Lines deleted
train_attn_can_adcrowdnet_simple.py 6 3
File train_attn_can_adcrowdnet_simple.py changed (mode: 100644) (index 4d32695..f51d0f3)
... ... if __name__ == "__main__":
22 22 TRAIN_PATH = os.path.join(DATA_PATH, "train_data") TRAIN_PATH = os.path.join(DATA_PATH, "train_data")
23 23 TEST_PATH = os.path.join(DATA_PATH, "test_data") TEST_PATH = os.path.join(DATA_PATH, "test_data")
24 24 dataset_name = args.datasetname dataset_name = args.datasetname
25 if (dataset_name=="shanghaitech"):
25 if dataset_name=="shanghaitech":
26 26 print("will use shanghaitech dataset with crop ") print("will use shanghaitech dataset with crop ")
27 if dataset_name == "shanghaitech_keepfull":
27 elif dataset_name == "shanghaitech_keepfull":
28 28 print("will use shanghaitech_keepfull") print("will use shanghaitech_keepfull")
29 else:
30 print("cannot detect dataset_name")
31 print("current dataset_name is ", dataset_name)
29 32
30 33 # create list # create list
31 34 train_list, val_list = get_train_val_list(TRAIN_PATH) train_list, val_list = get_train_val_list(TRAIN_PATH)
 
... ... if __name__ == "__main__":
90 93
91 94 trainer.add_event_handler(Events.EPOCH_COMPLETED(every=3), save_handler) trainer.add_event_handler(Events.EPOCH_COMPLETED(every=3), save_handler)
92 95
93 trainer.run(train_loader, max_epochs=args.epochs)
96 trainer.run(train_loader, max_epochs=args.epochs)
Hints:
Before first commit, do not forget to setup your git environment:
git config --global user.name "your_name_here"
git config --global user.email "your@email_here"

Clone this repository using HTTP(S):
git clone https://rocketgit.com/user/hahattpro/crowd_counting_framework

Clone this repository using ssh (do not forget to upload a key first):
git clone ssh://rocketgit@ssh.rocketgit.com/user/hahattpro/crowd_counting_framework

Clone this repository using git:
git clone git://git.rocketgit.com/user/hahattpro/crowd_counting_framework

You are allowed to anonymously push to this repository.
This means that your pushed commits will automatically be transformed into a merge request:
... clone the repository ...
... make some changes and some commits ...
git push origin main