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)
reduce model size, discard middle deform (kernal size 5)	00fb477cf699a8f2eed8e861f241c077b2046000	Thai Thien	2020-02-27 16:11:51
shanghaitech same size density map	25fc2e9395dd67bb6cc273c7fe6cd64c3b154120	Thai Thien	2020-02-27 16:03:05
fix target1.unsqueeze(0)	bb5c46f121207fd9838ee085314df40513e2ed32	Thai Thien	2020-02-27 15:56:07
because GPU too small, we crop shanghaitech A	0f97517dd8de5d3d75cf49af9aa9d20e4595ea3e	Thai Thien	2020-02-27 15:52:21
meow	3b9576511e597b4894c7c95ca06dc5219ef9c524	tthien	2020-02-27 15:44:39
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

Commit 00fb477cf699a8f2eed8e861f241c077b2046000 - reduce model size, discard middle deform (kernal size 5)
Author: Thai Thien
Author date (UTC): 2020-02-27 16:11
Committer name: Thai Thien
Committer date (UTC): 2020-02-27 16:11
Parent(s): 0528a58508989c20be4c013606c513e0570258df
Signing key:
Tree: 3d0b3fff8076561282b1d174068b99668478e0f7

File	Lines added	Lines deleted
models/attn_can_adcrowdnet.py	15	12

File models/attn_can_adcrowdnet.py changed (mode: 100644) (index 1f95223..59bb7ff)
...	...	class AttnCanAdcrowdNet(nn.Module):
20	20	self.concat_filter_layer = nn.Conv2d(1024, 512, kernel_size=3, padding=2, dilation=2)	self.concat_filter_layer = nn.Conv2d(1024, 512, kernel_size=3, padding=2, dilation=2)
21	21
22	22	self.deform_conv_1_3 = DeformConv2d(512, 256, kernel_size=3, stride=1, padding=1)	self.deform_conv_1_3 = DeformConv2d(512, 256, kernel_size=3, stride=1, padding=1)
23		self.deform_conv_1_5 = DeformConv2d(512, 256, kernel_size=5, stride=1, padding=2)
	23		# self.deform_conv_1_5 = DeformConv2d(512, 256, kernel_size=5, stride=1, padding=2)
24	24	self.deform_conv_1_7 = DeformConv2d(512, 256, kernel_size=7, stride=1, padding=3)	self.deform_conv_1_7 = DeformConv2d(512, 256, kernel_size=7, stride=1, padding=3)
25		self.concat_filter_layer_1 = nn.Conv2d(256 * 3, 256, kernel_size=3, padding=2, dilation=2)
	25		self.concat_filter_layer_1 = nn.Conv2d(256 * 2, 256, kernel_size=3, padding=2, dilation=2)
26	26
27	27	self.deform_conv_2_3 = DeformConv2d(256, 128, kernel_size=3, stride=1, padding=1)	self.deform_conv_2_3 = DeformConv2d(256, 128, kernel_size=3, stride=1, padding=1)
28		self.deform_conv_2_5 = DeformConv2d(256, 128, kernel_size=5, stride=1, padding=2)
	28		# self.deform_conv_2_5 = DeformConv2d(256, 128, kernel_size=5, stride=1, padding=2)
29	29	self.deform_conv_2_7 = DeformConv2d(256, 128, kernel_size=7, stride=1, padding=3)	self.deform_conv_2_7 = DeformConv2d(256, 128, kernel_size=7, stride=1, padding=3)
30		self.concat_filter_layer_2 = nn.Conv2d(128 * 3, 128, kernel_size=3, padding=2, dilation=2)
	30		self.concat_filter_layer_2 = nn.Conv2d(128 * 2, 128, kernel_size=3, padding=2, dilation=2)
31	31
32	32	self.deform_conv_3_3 = DeformConv2d(128, 64, kernel_size=3, stride=1, padding=1)	self.deform_conv_3_3 = DeformConv2d(128, 64, kernel_size=3, stride=1, padding=1)
33		self.deform_conv_3_5 = DeformConv2d(128, 64, kernel_size=5, stride=1, padding=2)
	33		# self.deform_conv_3_5 = DeformConv2d(128, 64, kernel_size=5, stride=1, padding=2)
34	34	self.deform_conv_3_7 = DeformConv2d(128, 64, kernel_size=7, stride=1, padding=3)	self.deform_conv_3_7 = DeformConv2d(128, 64, kernel_size=7, stride=1, padding=3)
35		self.concat_filter_layer_3 = nn.Conv2d(64 * 3, 64, kernel_size=3, padding=2, dilation=2)
	35		self.concat_filter_layer_3 = nn.Conv2d(64 * 2, 64, kernel_size=3, padding=2, dilation=2)
36	36
37	37	self.output_layer = nn.Conv2d(64, 1, kernel_size=1)	self.output_layer = nn.Conv2d(64, 1, kernel_size=1)
38	38	self.conv1_1 = nn.Conv2d(512, 512, kernel_size=1, bias=False)	self.conv1_1 = nn.Conv2d(512, 512, kernel_size=1, bias=False)

...	...	class AttnCanAdcrowdNet(nn.Module):
92	92	x = F.relu(self.concat_filter_layer(x))	x = F.relu(self.concat_filter_layer(x))
93	93
94	94	x3 = self.deform_conv_1_3(x)	x3 = self.deform_conv_1_3(x)
95		x5 = self.deform_conv_1_5(x)
	95		# x5 = self.deform_conv_1_5(x)
96	96	x7 = self.deform_conv_1_7(x)	x7 = self.deform_conv_1_7(x)
97		x = torch.cat((x3, x5, x7), 1)
	97		# x = torch.cat((x3, x5, x7), 1)
	98		x = torch.cat((x3, x7), 1)
98	99	x = F.relu(self.concat_filter_layer_1(x))	x = F.relu(self.concat_filter_layer_1(x))
99	100
100	101	x3 = self.deform_conv_2_3(x)	x3 = self.deform_conv_2_3(x)
101		x5 = self.deform_conv_2_5(x)
	102		# x5 = self.deform_conv_2_5(x)
102	103	x7 = self.deform_conv_2_7(x)	x7 = self.deform_conv_2_7(x)
103		x = torch.cat((x3, x5, x7), 1)
	104		# x = torch.cat((x3, x5, x7), 1)
	105		x = torch.cat((x3, x7), 1)
104	106	x = F.relu(self.concat_filter_layer_2(x))	x = F.relu(self.concat_filter_layer_2(x))
105	107
106	108	x3 = self.deform_conv_3_3(x)	x3 = self.deform_conv_3_3(x)
107		x5 = self.deform_conv_3_5(x)
	109		# x5 = self.deform_conv_3_5(x)
108	110	x7 = self.deform_conv_3_7(x)	x7 = self.deform_conv_3_7(x)
109		x = torch.cat((x3, x5, x7), 1)
	111		# x = torch.cat((x3, x5, x7), 1)
	112		x = torch.cat((x3, x7), 1)
110	113	x = F.relu(self.concat_filter_layer_3(x))	x = F.relu(self.concat_filter_layer_3(x))
111	114
112	115	x = self.output_layer(x)	x = self.output_layer(x)

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