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)
fix evaluation shb	51cbe92724973f64cb046f7f49fb1976400827e4	Thai Thien	2020-08-23 09:18:35
typo	1cba17e02cc79ee73c4ad5c9f1faab4913f92b01	Thai Thien	2020-08-23 08:53:21
fix file, mae, mse	245396d814f5d83dff1fd1ecc9fcd403be1805cb	Thai Thien	2020-08-23 08:52:16
file name strage stuff	caeb9f9608e91cf6a1323d9ae9f4fb215c4dd6ea	Thai Thien	2020-08-23 08:44:54
TypeError: can only concatenate str (not "list") to str	e8aebcfb782966c11c3ca116b5a9cc254021a73d	Thai Thien	2020-08-23 08:41:02
key error	5732100d6aca8e3fea6a4d25270edefbc8148a2a	Thai Thien	2020-08-23 08:39:09
fix target	fdbda2c6923dd164560448a445cd64ff413fc804	Thai Thien	2020-08-23 08:37:48
test path	06d268f873e6ceea93a8e8741d819a03b324cedb	Thai Thien	2020-08-23 08:27:38
a	1d73d926894edbc600db678316b9b24a583c4cb8	Thai Thien	2020-08-23 08:25:58
test set	bb1e40fc7806c8bef5e94fbaa54ac9af3b599041	Thai Thien	2020-08-23 08:23:30
remove epoch stuff	2cc6434aa298b6da90b4577ce529f971119b86c7	Thai Thien	2020-08-23 07:53:36
evaluation_shb_CompactCNNV7i_t1	28cf202a306b775967c6e466120b019ae1eb6a4d	Thai Thien	2020-08-23 07:49:51
evaluation shb	44f3dfdc9e3ad2787cc5286a64f1b28363796b19	Thai Thien	2020-08-23 07:32:50
performance_shb_CompactCNNV7i_t1	2698927959f377bb8308e54aebf029d8a18abf39	Thai Thien	2020-08-14 16:47:58
t7 test size 1 again	06fd0b91bf3c4c7d7713972f91c75ad33e0f25e7	Thai Thien	2020-08-14 16:38:33
t6 pin mem	c573feae8f739502b53497c3482dae7a5c55aff7	Thai Thien	2020-08-14 16:35:19
testsize 20	77b4d29cbc8305943c2ec025d60b3937e1686d33	Thai Thien	2020-08-14 16:31:53
t4 increase core	80bcac87ccb6b10ce6e438fcce2f52e52fe1600a	Thai Thien	2020-08-14 16:30:02
t3	eb03a48f24f38a078e8a77ba7a25fc647ecb642d	Thai Thien	2020-08-14 16:27:21
eval and no grad	c6d1e1fdeb6c7ebcc5318139ef22abb53b14e34e	Thai Thien	2020-08-14 16:25:11

Commit 51cbe92724973f64cb046f7f49fb1976400827e4 - fix evaluation shb
Author: Thai Thien
Author date (UTC): 2020-08-23 09:18
Committer name: Thai Thien
Committer date (UTC): 2020-08-23 09:18
Parent(s): 1cba17e02cc79ee73c4ad5c9f1faab4913f92b01
Signer:
Signing key:
Signing status: N
Tree: 9087a55d8ed5e9ee4d2f5629ba9f7075b50ea392

File	Lines added	Lines deleted
debug/evaluate_shb.py	9	16
debug/evaluation_shb_CompactCNNV7i_t1.txt	1	0
train_script/debug/a1/local.sh	21	0
train_script/debug/evaluation_shb_CompactCNNV7i_t1.sh	3	0

File debug/evaluate_shb.py changed (mode: 100644) (index 1e9801e..1d637ab)
...	...	from data_flow import get_train_val_list, get_dataloader, create_training_image_
33	33	This file evaluation on SHB and get information on evaluation process	This file evaluation on SHB and get information on evaluation process
34	34	"""	"""
35	35
	36		"/data/ShanghaiTech/part_A/test_data"
36	37
37	38	def _parse():	def _parse():
38	39	parser = argparse.ArgumentParser(description='evaluatiuon SHB')	parser = argparse.ArgumentParser(description='evaluatiuon SHB')
39	40	parser.add_argument('--input', action="store", type=str, default=HardCodeVariable().SHANGHAITECH_PATH_PART_A)	parser.add_argument('--input', action="store", type=str, default=HardCodeVariable().SHANGHAITECH_PATH_PART_A)
40	41	parser.add_argument('--output', action="store", type=str, default="visualize/verify_dataloader_shanghaitech")	parser.add_argument('--output', action="store", type=str, default="visualize/verify_dataloader_shanghaitech")
41		parser.add_argument('--load_model', action="store", type=str, default="visualize/verify_dataloader_shanghaitech")
	42		parser.add_argument('--load_model', action="store", type=str, default=None)
42	43	parser.add_argument('--model', action="store", type=str, default="visualize/verify_dataloader_shanghaitech")	parser.add_argument('--model', action="store", type=str, default="visualize/verify_dataloader_shanghaitech")
43	44	parser.add_argument('--meta_data', action="store", type=str, default="data_info.txt")	parser.add_argument('--meta_data', action="store", type=str, default="data_info.txt")
44	45	parser.add_argument('--datasetname', action="store", default="shanghaitech_keepfull_r50")	parser.add_argument('--datasetname', action="store", default="shanghaitech_keepfull_r50")

...	...	def visualize_evaluation_shanghaitech_keepfull(model, args):
60	61	mae_s = 0	mae_s = 0
61	62	mse_s = 0	mse_s = 0
62	63	n = 0	n = 0
	64		train_loader_iter = iter(train_loader)
	65		_, gt_density,_ = next(train_loader_iter)
63	66	with torch.no_grad():	with torch.no_grad():
64	67	for item in test_loader:	for item in test_loader:
65	68	img, gt_density, debug_info = item	img, gt_density, debug_info = item

...	...	def visualize_evaluation_shanghaitech_keepfull(model, args):
69	72	file_name_only = file_name[0].split(".")[0]	file_name_only = file_name[0].split(".")[0]
70	73	save_path = os.path.join(saved_folder, "label_" + file_name_only +".png")	save_path = os.path.join(saved_folder, "label_" + file_name_only +".png")
71	74	save_pred_path = os.path.join(saved_folder, "pred_" + file_name_only +".png")	save_pred_path = os.path.join(saved_folder, "pred_" + file_name_only +".png")
72		save_density_map(gt_density.numpy()[0][0], save_path)
	75		save_density_map(gt_density.numpy()[0], save_path)
73	76	pred = model(img.cuda())	pred = model(img.cuda())
74	77	predicted_density_map = pred.detach().cpu().clone().numpy()	predicted_density_map = pred.detach().cpu().clone().numpy()
75	78	predicted_density_map_enlarge = cv2.resize(np.squeeze(predicted_density_map[0][0]), (int(predicted_density_map.shape[3] * 8), int(predicted_density_map.shape[2] * 8)), interpolation=cv2.INTER_CUBIC) / 64	predicted_density_map_enlarge = cv2.resize(np.squeeze(predicted_density_map[0][0]), (int(predicted_density_map.shape[3] * 8), int(predicted_density_map.shape[2] * 8)), interpolation=cv2.INTER_CUBIC) / 64

...	...	if __name__ == "__main__":
104	107	args = _parse()	args = _parse()
105	108	print(args)	print(args)
106	109
107		DATA_PATH = args.input
108		TRAIN_PATH = os.path.join(DATA_PATH, "train_data_train_split")
109		VAL_PATH = os.path.join(DATA_PATH, "train_data_validate_split")
110		TEST_PATH = os.path.join(DATA_PATH, "test_data")
111		dataset_name = args.datasetname
112		if dataset_name == "shanghaitech":
113		print("will use shanghaitech dataset with crop ")
114		elif dataset_name == "shanghaitech_keepfull":
115		print("will use shanghaitech_keepfull")
116		else:
117		print("cannot detect dataset_name")
118		print("current dataset_name is ", dataset_name)
	110
119	111
120	112	# # create list	# # create list
121	113	# train_list = create_image_list(TRAIN_PATH)	# train_list = create_image_list(TRAIN_PATH)

...	...	if __name__ == "__main__":
200	192	print("error: you didn't pick a model")	print("error: you didn't pick a model")
201	193	exit(-1)	exit(-1)
202	194	model = model.to(device)	model = model.to(device)
203		checkpoint = torch.load(args.load_model)
204		model.load_state_dict(checkpoint["model"])
	195		if args.load_model is not None:
	196		checkpoint = torch.load(args.load_model)
	197		model.load_state_dict(checkpoint["model"])
205	198	model.eval()	model.eval()
206	199	visualize_evaluation_shanghaitech_keepfull(model, args)	visualize_evaluation_shanghaitech_keepfull(model, args)
207	200

File debug/evaluation_shb_CompactCNNV7i_t1.txt added (mode: 100644) (index 0000000..9ff254b)
	1		IMG_98 146.8988037109375 153369.7569580078125

File train_script/debug/a1/local.sh added (mode: 100644) (index 0000000..63114cc)
	1	task="evaluation_shb_CompactCNNV7i_t1"
	2	CUDA_VISIBLE_DEVICES=2 OMP_NUM_THREADS=4 PYTHONWARNINGS="ignore" HTTPS_PROXY="http://10.60.28.99:86" nohup python debug/evaluate_shb.py \
	3	--model "CompactCNNV7i" \
	4	--input /data/ShanghaiTech/part_A/test_data \
	5	--output visualize/$task \
	6	--load_model saved_model_best/g1_ccnn_v7_t3_shb/g1_ccnn_v7_t3_shb_checkpoint_valid_mae=-8.881268501281738.pth \
	7	--meta_data logs/$task.txt \
	8	--datasetname shanghaitech_non_overlap \
	9	> logs/$task.log &
	10
	11	echo logs/$task.log
	12
	13
	14	"/data/ShanghaiTech/part_A/test_data"
	15
	16
	17	--model "CompactCNNV7i" \
	18	--input /data/ShanghaiTech/part_A/test_data
	19	--output visualize/evaluation_shb_CompactCNNV7i_t1
	20	--meta_data logs/evaluation_shb_CompactCNNV7i_t1.txt
	21	--datasetname shanghaitech_non_overlap

File train_script/debug/evaluation_shb_CompactCNNV7i_t1.sh changed (mode: 100644) (index cff9849..b785539)
...	...	CUDA_VISIBLE_DEVICES=2 OMP_NUM_THREADS=4 PYTHONWARNINGS="ignore" HTTPS_PROXY="ht
10	10
11	11	echo logs/$task.log	echo logs/$task.log
12	12
	13
	14		"/data/ShanghaiTech/part_A/test_data"
	15
13	16	##	##
14	17	#def _parse():	#def _parse():
15	18	# parser = argparse.ArgumentParser(description='evaluatiuon SHB')	# parser = argparse.ArgumentParser(description='evaluatiuon SHB')

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