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)
fix wrong py name in script, dataset use only 1 worker 3bd765c9aa79e47049a94547e57deb68c947001c Thai Thien 2020-02-27 15:41:44
minor fix 5505b9a8b28df105e11a99d3462323ae9d507102 Thai Thien 2020-02-27 15:28:37
get ready for short training run with 30 epochs 66dda0858561897cd5f81e10077459adb39d86dd Thai Thien 2020-02-27 15:22:01
implement attn_can_adcrowdnet ffd38664a43d861c20cdc225746b9ce2a00260c7 Thai Thien 2020-02-27 15:10:27
WIP: add can-adcrowdnet 5620b83449b31d00a367c8de77e431e19a5ccfb3 Thai Thien 2020-02-25 11:31:38
add readable timestamp viz ae1fdb49ddb9ea77659529dceb7fb87c2790c8dc Thai Thien 2020-02-24 03:49:57
change save name prefix c53a86f30fb8fd4e8f3a409eb67827d56a43ae5c Thai Thien 2020-02-02 10:48:15
training flow that work fb242273e8f696916f9d1ff4bb76b4e5869799ef Thai Thien 2020-02-02 10:42:01
fix the dataloader for shanghaitech 5f2aee9f316e6555e6a70c6ad037a4e6b491867b Thai Thien 2020-02-02 09:19:50
context aware visualize seem ok 1bdb6ffe77ca4e40ef8f299b2506df2266243db4 Thai Thien 2020-02-02 05:07:10
visualize eval context aware network seem ok f3fe45c23dfeab3730624737efabb0b14d23c25b Thai Thien 2020-02-02 04:50:34
visualize_shanghaitech_pacnn_with_perspective run without error 12366a2de2bd60ff4bd36e6132d44e37dedf7462 Thai Thien 2020-02-02 04:21:16
eval context aware network on ShanghaiTechB can run e8c454d2b6d287c830c1286c9a37884b3cfc615f Thai Thien 2020-02-02 04:09:14
import ShanghaiTechDataPath in data_util e81eb56315d44375ff5c0e747d61456601492f8f Thai Thien 2020-02-02 04:04:36
add model_context_aware_network.py 2a36025c001d85afc064c090f4d22987b328977b Thai Thien 2020-02-02 03:46:38
PACNN (TODO: test this) 44d5ae7ec57c760fb4f105dd3e3492148a0cc075 Thai Thien 2020-02-02 03:40:26
add data path 80134de767d0137a663f343e4606bafc57a1bc1f Thai Thien 2020-02-02 03:38:21
test if ShanghaiTech datapath is correct 97ee84944a4393ec3732879b24f614826f8e7798 Thai Thien 2020-02-01 03:57:31
refactor and test ShanghaiTech datapath 9542ebc00f257edc38690180b7a4353794be4019 Thai Thien 2020-02-01 03:53:49
fix the unzip flow b53c5989935335377eb6a88c942713d3eccc5df7 Thai Thien 2020-02-01 03:53:13
Commit 3bd765c9aa79e47049a94547e57deb68c947001c - fix wrong py name in script, dataset use only 1 worker
Author: Thai Thien
Author date (UTC): 2020-02-27 15:41
Committer name: Thai Thien
Committer date (UTC): 2020-02-27 15:41
Parent(s): 5505b9a8b28df105e11a99d3462323ae9d507102
Signing key:
Tree: c6b0150446cf16be1905b6f8173d3620e0d5bd1a
File Lines added Lines deleted
data_flow.py 4 4
train_attn_can_adcrowdnet.py 1 1
train_script/attn_can_adcrowdnet/train_server_31_epoch_shA.sh 1 1
File data_flow.py changed (mode: 100644) (index cb3c78c..9bbb7c1)
... ... def data_augmentation(img, target):
279 279 class ListDataset(Dataset): class ListDataset(Dataset):
280 280 def __init__(self, root, shape=None, shuffle=True, transform=None, train=False, seen=0, batch_size=1, def __init__(self, root, shape=None, shuffle=True, transform=None, train=False, seen=0, batch_size=1,
281 281 debug=False, debug=False,
282 num_workers=4, dataset_name="shanghaitech"):
282 num_workers=0, dataset_name="shanghaitech"):
283 283 """ """
284 284 if you have different image size, then batch_size must be 1 if you have different image size, then batch_size must be 1
285 285 :param root: :param root:
 
... ... def get_dataloader(train_list, val_list, test_list, dataset_name="shanghaitech",
352 352 transform=transformer, transform=transformer,
353 353 train=True, train=True,
354 354 batch_size=1, batch_size=1,
355 num_workers=4,
355 num_workers=0,
356 356 dataset_name=dataset_name), dataset_name=dataset_name),
357 357 batch_size=1, batch_size=1,
358 358 num_workers=4) num_workers=4)
 
... ... def get_dataloader(train_list, val_list, test_list, dataset_name="shanghaitech",
363 363 transform=transformer, transform=transformer,
364 364 train=False, train=False,
365 365 dataset_name=dataset_name), dataset_name=dataset_name),
366 num_workers=4,
366 num_workers=0,
367 367 batch_size=1) batch_size=1)
368 368
369 369 if test_list is not None: if test_list is not None:
 
... ... def get_dataloader(train_list, val_list, test_list, dataset_name="shanghaitech",
373 373 transform=transformer, transform=transformer,
374 374 train=False, train=False,
375 375 dataset_name=dataset_name), dataset_name=dataset_name),
376 num_workers=4,
376 num_workers=0,
377 377 batch_size=1) batch_size=1)
378 378 else: else:
379 379 test_loader = None test_loader = None
File train_attn_can_adcrowdnet.py changed (mode: 100644) (index 878bdea..2dbf75f)
... ... if __name__ == "__main__":
25 25
26 26 # create list # create list
27 27 train_list, val_list = get_train_val_list(TRAIN_PATH) train_list, val_list = get_train_val_list(TRAIN_PATH)
28 test_list = create_training_image_list(TEST_PATH)
28 test_list = None
29 29
30 30 # create data loader # create data loader
31 31 train_loader, val_loader, test_loader = get_dataloader(train_list, val_list, test_list, dataset_name="shanghaitech_keepfull") train_loader, val_loader, test_loader = get_dataloader(train_list, val_list, test_list, dataset_name="shanghaitech_keepfull")
File train_script/attn_can_adcrowdnet/train_server_31_epoch_shA.sh changed (mode: 100644) (index 49459f1..ee917b1)
1 CUDA_VISIBLE_DEVICES=4 nohup python train_context_aware_network.py \
1 CUDA_VISIBLE_DEVICES=4 nohup python train_attn_can_adcrowdnet.py \
2 2 --task_id attn_can_adcrowdnet_default_shtA_31 \ --task_id attn_can_adcrowdnet_default_shtA_31 \
3 3 --input /data/rnd/thient/thient_data/ShanghaiTech/part_A \ --input /data/rnd/thient/thient_data/ShanghaiTech/part_A \
4 4 --output saved_model/attn_can_adcrowdnet_default_shtA_31 \ --output saved_model/attn_can_adcrowdnet_default_shtA_31 \
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