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)
we freeze vgg pretrain layer	459cefbfbf53949cb9636ca002cd4f78e964bb83	Thai Thien	2020-02-27 18:24:17
fix error when save	86a8f467d47a67da0accc963e8baacbaea07ab14	Thai Thien	2020-02-27 17:55:46
we discard deform 7 and keep deform 5 instead	91ff78e4a1aef3677b15447b631c2927c9e62a31	Thai Thien	2020-02-27 16:22:47
reduce image by crop	530516ff40b744cac79756c97faaed50c8b65cfb	Thai Thien	2020-02-27 16:19:11
try to solve x8/8 dimension mismatch	6b0616197995b3c95041cde43030245f96f1f81e	Thai Thien	2020-02-27 16:17:12
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

Commit 459cefbfbf53949cb9636ca002cd4f78e964bb83 - we freeze vgg pretrain layer
Author: Thai Thien
Author date (UTC): 2020-02-27 18:24
Committer name: Thai Thien
Committer date (UTC): 2020-02-27 18:24
Parent(s): 86a8f467d47a67da0accc963e8baacbaea07ab14
Signing key:
Tree: 445a25d3cf4f71125ecb19c57f2b71609bf74bc0

File	Lines added	Lines deleted
models/__init__.py	2	1
models/attn_can_adcrowdnet_freeze_vgg.py	6	2
train_attn_can_adcrowdnet_freeze_vgg.py	2	2
train_script/attn_can_adcrowdnet/train_server_31_epoch_shA_freeze_vgg.sh	6	0

File models/__init__.py changed (mode: 100644) (index af62baf..202d017)
...	...	from .csrnet import CSRNet
2	2	from .pacnn import PACNN, PACNNWithPerspectiveMap	from .pacnn import PACNN, PACNNWithPerspectiveMap
3	3	from .context_aware_network import CANNet	from .context_aware_network import CANNet
4	4	from .deform_conv_v2 import DeformConv2d	from .deform_conv_v2 import DeformConv2d
5		from .attn_can_adcrowdnet import AttnCanAdcrowdNet
	5		from .attn_can_adcrowdnet import AttnCanAdcrowdNet
	6		from .attn_can_adcrowdnet_freeze_vgg import AttnCanAdcrowdNetFreezeVgg

File models/attn_can_adcrowdnet_freeze_vgg.py copied from file models/attn_can_adcrowdnet.py (similarity 96%) (mode: 100644) (index 0d825f6..061b604)
...	...	from .squeeze_and_excitation import ChannelSpatialSELayer
9	9	# from dcn.modules.deform_conv import DeformConvPack, ModulatedDeformConvPack	# from dcn.modules.deform_conv import DeformConvPack, ModulatedDeformConvPack
10	10
11	11
12		class AttnCanAdcrowdNet(nn.Module):
	12		class AttnCanAdcrowdNetFreezeVgg(nn.Module):
13	13	def __init__(self, load_weights=False):	def __init__(self, load_weights=False):
14		super(AttnCanAdcrowdNet, self).__init__()
	14		super(AttnCanAdcrowdNetFreezeVgg, self).__init__()
15	15	self.frontend_feat = [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512]	self.frontend_feat = [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512]
16	16	self.frontend = make_layers(self.frontend_feat)	self.frontend = make_layers(self.frontend_feat)
17	17
	18		# freeze vgg layer
	19		for param in self.frontend.parameters():
	20		param.requires_grad = False
	21
18	22	self.csSE = ChannelSpatialSELayer(num_channels=512, reduction_ratio=1)	self.csSE = ChannelSpatialSELayer(num_channels=512, reduction_ratio=1)
19	23
20	24	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)

File train_attn_can_adcrowdnet_freeze_vgg.py copied from file train_attn_can_adcrowdnet.py (similarity 97%) (mode: 100644) (index 2706723..de7e0fb)
...	...	from visualize_util import get_readable_time
9	9
10	10	import torch	import torch
11	11	from torch import nn	from torch import nn
12		from models import AttnCanAdcrowdNet
	12		from models import AttnCanAdcrowdNetFreezeVgg
13	13	import os	import os
14	14
15	15

...	...	if __name__ == "__main__":
32	32
33	33
34	34	# model	# model
35		model = AttnCanAdcrowdNet()
	35		model = AttnCanAdcrowdNetFreezeVgg()
36	36	model = model.to(device)	model = model.to(device)
37	37
38	38	# loss function	# loss function

File train_script/attn_can_adcrowdnet/train_server_31_epoch_shA_freeze_vgg.sh added (mode: 100644) (index 0000000..4971c9c)
	1	CUDA_VISIBLE_DEVICES=5 nohup python train_attn_can_adcrowdnet_freeze_vgg.py \
	2	--task_id attn_can_adcrowdnet_default_shtA_31_freeze_vgg \
	3	--input /data/rnd/thient/thient_data/ShanghaiTech/part_A \
	4	--output saved_model/attn_can_adcrowdnet_default_shtA_31_freeze_vgg \
	5	--datasetname shanghaitech \
	6	--epochs 31 > logs/attn_can_adcrowdnet_default_shtA_31_freeze_vgg_nohup.log &

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