RocketGit

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

List of commits:

Subject	Hash	Author	Date (UTC)
pacnn perspective loss	fb673e38a5f24ae9004fe2b7b93c88991e0c2304	Thai Thien	2019-10-06 01:38:28
data_flow shanghaitech_pacnn_with_perspective seem working	91d350a06f358e03223966297d124daee94123d0	Thai Thien	2019-10-06 01:31:11
multiscale loss and final loss only mode	c65dd0e74ad28503821e5c8651a3b47b4a0c7c64	Thai Thien	2019-10-05 15:58:19
wip : perspective map	eac63f2671dc5b064753acc4f40bf0f9f216ad2a	Thai Thien	2019-10-04 16:26:56
shell script	f2106e700b6f6174d4dd276f25ec6f3d9ff239bb	thient	2019-10-04 07:42:51
WIP	42c7c8e1d772fbbda61a4bdf9e329f74e1efb600	tthien	2019-10-03 17:52:47
add readme	580cf43d1edddd67b1f6a2c57fdd5cee3dba925c	Thai Thien	2019-10-02 17:44:49
update script, debug	ddb68b95389be1c1d398118677dd227a8bb2b70b	Thai Thien	2019-10-02 15:52:31
add d (output density map) to loss function)	a0c71bf4bf2ab7393d60b06a84db8dfbbfb1a6c2	tthien	2019-09-30 16:32:39
fix the args, add save interval for model, so we don't save them all	9fdf9daa2ac4bd12b7b62521d81e520db0debd01	tthien	2019-09-30 16:30:00
meow	1ad19a22a310992e27a26471feeb37375124d075	tthien	2019-09-29 18:25:43
fix pacnn perspective map	453ece3ccb818889ba895bfc4285f7905d33cba5	Thai Thien	2019-09-25 17:20:33
apex not work so well	da8c0dd57297f972201f31d57e66897177922f48	Thai Thien	2019-09-24 17:25:59
fix data loader pacnn so it will scale up with correct number of people	11d55b50d764511f2491291f0208fee0905dec49	Thai Thien	2019-09-24 15:40:56
add comet ml	a9d4b89ce594f5e241168ccafdcdf0f150ea0ebb	Thai Thien	2019-09-23 17:07:58
fix pacnn avg schema	c2140a96886195782e5689c24aeeb4fe7a2db7ad	Thai Thien	2019-09-22 17:35:01
debug number not divisible by 8	a568fd7f294a8bd31b3db78437b4b6b51b5b41b9	Thai Thien	2019-09-22 04:36:06
pacnn	967074890d14ab0eefc277801860270a468e8f9f	Thai Thien	2019-09-22 03:54:48
wip: pacnn	2192d7c7b449fecf3868877d9cfbc09bb6f7ae98	Thai Thien	2019-09-22 03:44:56
wip: pacnn	37620e5a9bc0f9516ea964ec58d9bdaa1c40ff36	Thai Thien	2019-09-22 03:14:42

Commit fb673e38a5f24ae9004fe2b7b93c88991e0c2304 - pacnn perspective loss
Author: Thai Thien
Author date (UTC): 2019-10-06 01:38
Committer name: Thai Thien
Committer date (UTC): 2019-10-06 01:38
Parent(s): 91d350a06f358e03223966297d124daee94123d0
Signing key:
Tree: e6f2a6671ca1f39d74beabd9c77f143ee03b432b

File	Lines added	Lines deleted
main_pacnn.py	15	3
visualize_data_loader.py	1	0

File main_pacnn.py changed (mode: 100644) (index fc87076..4eee4ac)
...	...	if __name__ == "__main__":
34	34	MODEL_SAVE_NAME = args.task_id	MODEL_SAVE_NAME = args.task_id
35	35	MODEL_SAVE_INTERVAL = 5	MODEL_SAVE_INTERVAL = 5
36	36	DATA_PATH = args.input	DATA_PATH = args.input
37		DATASET_NAME = "shanghaitech"
38	37	TOTAL_EPOCH = args.epochs	TOTAL_EPOCH = args.epochs
39	38	PACNN_PERSPECTIVE_AWARE_MODEL = args.PACNN_PERSPECTIVE_AWARE_MODEL	PACNN_PERSPECTIVE_AWARE_MODEL = args.PACNN_PERSPECTIVE_AWARE_MODEL
40	39	PACNN_MUTILPLE_SCALE_LOSS = args.PACNN_MUTILPLE_SCALE_LOSS	PACNN_MUTILPLE_SCALE_LOSS = args.PACNN_MUTILPLE_SCALE_LOSS
	40		DATASET_NAME = "shanghaitech_pacnn"
	41		if PACNN_PERSPECTIVE_AWARE_MODEL:
	42		DATASET_NAME = "shanghaitech_pacnn_with_perspective"
41	43
42	44	experiment.set_name(args.task_id)	experiment.set_name(args.task_id)
43	45	experiment.log_parameter("DATA_PATH", DATA_PATH)	experiment.log_parameter("DATA_PATH", DATA_PATH)

...	...	if __name__ == "__main__":
122	124	optimizer.zero_grad()	optimizer.zero_grad()
123	125
124	126	# load data	# load data
125		d1_label, d2_label, d3_label = label
	127		if PACNN_PERSPECTIVE_AWARE_MODEL:
	128		d1_label, d2_label, d3_label, perspective_s, perspective_p = label
	129		perspective_s = perspective_s.to(device).unsqueeze(0)
	130		perspective_p = perspective_p.to(device).unsqueeze(0)
	131		else:
	132		d1_label, d2_label, d3_label = label
126	133	d1_label = d1_label.to(device).unsqueeze(0)	d1_label = d1_label.to(device).unsqueeze(0)
127	134	d2_label = d2_label.to(device).unsqueeze(0)	d2_label = d2_label.to(device).unsqueeze(0)
128	135	d3_label = d3_label.to(device).unsqueeze(0)	d3_label = d3_label.to(device).unsqueeze(0)

...	...	if __name__ == "__main__":
142	149
143	150	if PACNN_PERSPECTIVE_AWARE_MODEL:	if PACNN_PERSPECTIVE_AWARE_MODEL:
144	151	# TODO: loss for perspective map here	# TODO: loss for perspective map here
145		pass
	152		loss_p = criterion_mse(p, perspective_p) + criterion_ssim(p, perspective_p)
	153		loss += loss_p
	154		if PACNN_MUTILPLE_SCALE_LOSS:
	155		loss_p_s = criterion_mse(p_s, perspective_s) + criterion_ssim(p_s, perspective_s)
	156		loss += loss_p_s
	157
146	158	# what is this, loss_d count 2 ?	# what is this, loss_d count 2 ?
147	159	## loss_d = criterion_mse(d, d1_label) + criterion_ssim(d, d1_label)	## loss_d = criterion_mse(d, d1_label) + criterion_ssim(d, d1_label)
148	160	## loss += loss_d	## loss += loss_d

File visualize_data_loader.py changed (mode: 100644) (index f4aa432..b6d376e)
...	...	def visualize_ucf_cc_50_pacnn():
48	48	print("count2 ", label[1].numpy()[0].sum())	print("count2 ", label[1].numpy()[0].sum())
49	49	print("count3 ", label[2].numpy()[0].sum())	print("count3 ", label[2].numpy()[0].sum())
50	50
	51
51	52	def visualize_shanghaitech_pacnn_with_perspective():	def visualize_shanghaitech_pacnn_with_perspective():
52	53	HARD_CODE = HardCodeVariable()	HARD_CODE = HardCodeVariable()
53	54	saved_folder = "visualize/test_dataloader"	saved_folder = "visualize/test_dataloader"

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