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)
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
data_script run seem ok	67420c08fc1c10a66404d3698994865726a106cd	Thai Thien	2020-02-01 03:33:18
add perspective	642d6fff8c9f31e510fda85a7fb631fb855d8a6d	Thai Thien	2019-10-06 16:54:44
fix padding with p	86c2fa07822d956a34b3b37e14da485a4249f01b	Thai Thien	2019-10-06 02:52:58
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

Commit e8c454d2b6d287c830c1286c9a37884b3cfc615f - eval context aware network on ShanghaiTechB can run
Author: Thai Thien
Author date (UTC): 2020-02-02 04:09
Committer name: Thai Thien
Committer date (UTC): 2020-02-02 04:09
Parent(s): 39b10e744904df9ab7dfe0ce77aa271cd37b3881
Signer:
Signing key:
Signing status: N
Tree: 8807269793f18b44254c1c7cae00747ea4fe05c5

File	Lines added	Lines deleted
eval_context_aware_network.py	81	0
models/context_aware_network.py	0	0

File eval_context_aware_network.py added (mode: 100644) (index 0000000..760e6bd)
	1	import h5py
	2	import PIL.Image as Image
	3	import numpy as np
	4	import os
	5	import glob
	6	import torch
	7	from torch.autograd import Variable
	8	from sklearn.metrics import mean_squared_error,mean_absolute_error
	9	from torchvision import transforms
	10	from models.context_aware_network import CANNet
	11	from data_util import ShanghaiTechDataPath
	12	from hard_code_variable import HardCodeVariable
	13
	14	_description="""
	15	This file run predict
	16	Data path = /home/tt/project/ShanghaiTechCAN/part_B/test_data/images
	17	model path = /home/tt/project/MODEL/Context-aware/part_B_pre.pth.tar
	18	"""
	19
	20	transform=transforms.Compose([
	21	transforms.ToTensor(),transforms.Normalize(mean=[0.485, 0.456, 0.406],
	22	std=[0.229, 0.224, 0.225]),
	23	])
	24
	25	# the folder contains all the test images
	26	hard_code = HardCodeVariable()
	27	shanghaitech_data = ShanghaiTechDataPath(root=hard_code.SHANGHAITECH_PATH)
	28	# img_folder='/home/tt/project/ShanghaiTechCAN/part_B/test_data/images'
	29	img_folder = shanghaitech_data.get_b().get_test().get_images()
	30	print("image folder = " + str(img_folder))
	31
	32	img_paths=[]
	33
	34	for img_path in glob.glob(os.path.join(img_folder, '*.jpg')):
	35	img_paths.append(img_path)
	36	# img_paths = img_paths[:10]
	37
	38
	39	model = CANNet()
	40
	41	model = model.cuda()
	42
	43	checkpoint = torch.load('/home/tt/project/MODEL/Context-aware/part_B_pre.pth.tar')
	44
	45	model.load_state_dict(checkpoint['state_dict'])
	46
	47	model.eval()
	48
	49	pred= []
	50	gt = []
	51
	52	for i in range(len(img_paths)):
	53	img = transform(Image.open(img_paths[i]).convert('RGB')).cuda()
	54	img = img.unsqueeze(0)
	55	h,w = img.shape[2:4]
	56	h_d = int(h/2)
	57	w_d = int(w/2)
	58	img_1 = Variable(img[:,:,:h_d,:w_d].cuda())
	59	img_2 = Variable(img[:,:,:h_d,w_d:].cuda())
	60	img_3 = Variable(img[:,:,h_d:,:w_d].cuda())
	61	img_4 = Variable(img[:,:,h_d:,w_d:].cuda())
	62	density_1 = model(img_1).data.cpu().numpy()
	63	density_2 = model(img_2).data.cpu().numpy()
	64	density_3 = model(img_3).data.cpu().numpy()
	65	density_4 = model(img_4).data.cpu().numpy()
	66
	67	pure_name = os.path.splitext(os.path.basename(img_paths[i]))[0]
	68	gt_file = h5py.File(img_paths[i].replace('.jpg','.h5').replace('images','ground-truth-h5'),'r')
	69	groundtruth = np.asarray(gt_file['density'])
	70	pred_sum = density_1.sum()+density_2.sum()+density_3.sum()+density_4.sum()
	71	pred.append(pred_sum)
	72	gt.append(np.sum(groundtruth))
	73	print("done ", i, "pred ",pred_sum, " gt ", np.sum(groundtruth))
	74
	75	print(len(pred))
	76	print(len(gt))
	77	mae = mean_absolute_error(pred,gt)
	78	rmse = np.sqrt(mean_squared_error(pred,gt))
	79
	80	print('MAE: ',mae)
	81	print('RMSE: ',rmse)

File models/context_aware_network.py renamed from models/model_context_aware_network.py (similarity 100%)

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