-
Notifications
You must be signed in to change notification settings - Fork 122
/
cfgs_res50_dota_r3det_v1.py
152 lines (130 loc) · 4.65 KB
/
cfgs_res50_dota_r3det_v1.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
# -*- coding: utf-8 -*-
from __future__ import division, print_function, absolute_import
import os
import tensorflow as tf
import math
"""
This is your result for task 1:
mAP: 0.7040175568277504
ap of each class:
plane:0.890153676787004,
baseball-diamond:0.7546823004821948,
bridge:0.43856818970048655,
ground-track-field:0.6584323172228589,
small-vehicle:0.758265556666476,
large-vehicle:0.7343692077868644,
ship:0.8603390134740575,
tennis-court:0.9056898929544596,
basketball-court:0.8111416145602515,
storage-tank:0.8284442512925325,
soccer-ball-field:0.5557191091213718,
roundabout:0.5910437513923295,
harbor:0.5657488814247862,
swimming-pool:0.7031169348003156,
helicopter:0.5045486547502677
The submitted information is :
Description: RetinaNet_DOTA_R3Det_2x_20191108_75.6w
Username: SJTU-Det
Institute: SJTU
Emailadress: yangxue-2019-sjtu@sjtu.edu.cn
TeamMembers: yangxue
"""
# ------------------------------------------------
VERSION = 'RetinaNet_DOTA_R3Det_2x_20191108'
NET_NAME = 'resnet50_v1d' # 'MobilenetV2'
ADD_BOX_IN_TENSORBOARD = True
# ---------------------------------------- System_config
ROOT_PATH = os.path.abspath('../')
print(20*"++--")
print(ROOT_PATH)
GPU_GROUP = "0,1,3"
NUM_GPU = len(GPU_GROUP.strip().split(','))
SHOW_TRAIN_INFO_INTE = 20
SMRY_ITER = 200
SAVE_WEIGHTS_INTE = 27000 * 2
SUMMARY_PATH = ROOT_PATH + '/output/summary'
TEST_SAVE_PATH = ROOT_PATH + '/tools/test_result'
if NET_NAME.startswith("resnet"):
weights_name = NET_NAME
elif NET_NAME.startswith("MobilenetV2"):
weights_name = "mobilenet/mobilenet_v2_1.0_224"
else:
raise Exception('net name must in [resnet_v1_101, resnet_v1_50, MobilenetV2]')
PRETRAINED_CKPT = ROOT_PATH + '/data/pretrained_weights/' + weights_name + '.ckpt'
TRAINED_CKPT = os.path.join(ROOT_PATH, 'output/trained_weights')
EVALUATE_DIR = ROOT_PATH + '/output/evaluate_result_pickle/'
# ------------------------------------------ Train config
RESTORE_FROM_RPN = False
FIXED_BLOCKS = 1 # allow 0~3
FREEZE_BLOCKS = [True, False, False, False, False] # for gluoncv backbone
USE_07_METRIC = True
MUTILPY_BIAS_GRADIENT = 2.0 # if None, will not multipy
GRADIENT_CLIPPING_BY_NORM = 10.0 # if None, will not clip
CLS_WEIGHT = 1.0
REG_WEIGHT = 1.0
USE_IOU_FACTOR = False
BATCH_SIZE = 1
EPSILON = 1e-5
MOMENTUM = 0.9
LR = 5e-4
DECAY_STEP = [SAVE_WEIGHTS_INTE*12, SAVE_WEIGHTS_INTE*16, SAVE_WEIGHTS_INTE*20]
MAX_ITERATION = SAVE_WEIGHTS_INTE*20
WARM_SETP = int(1.0 / 4.0 * SAVE_WEIGHTS_INTE)
# -------------------------------------------- Data_preprocess_config
DATASET_NAME = 'DOTA' # 'pascal', 'coco'
PIXEL_MEAN = [123.68, 116.779, 103.939] # R, G, B. In tf, channel is RGB. In openCV, channel is BGR
PIXEL_MEAN_ = [0.485, 0.456, 0.406]
PIXEL_STD = [0.229, 0.224, 0.225] # R, G, B. In tf, channel is RGB. In openCV, channel is BGR
IMG_SHORT_SIDE_LEN = 800
IMG_MAX_LENGTH = 800
CLASS_NUM = 15
IMG_ROTATE = False
RGB2GRAY = False
VERTICAL_FLIP = False
HORIZONTAL_FLIP = True
IMAGE_PYRAMID = False
# --------------------------------------------- Network_config
SUBNETS_WEIGHTS_INITIALIZER = tf.random_normal_initializer(mean=0.0, stddev=0.01, seed=None)
SUBNETS_BIAS_INITIALIZER = tf.constant_initializer(value=0.0)
PROBABILITY = 0.01
FINAL_CONV_BIAS_INITIALIZER = tf.constant_initializer(value=-math.log((1.0 - PROBABILITY) / PROBABILITY))
WEIGHT_DECAY = 1e-4
USE_GN = False
NUM_SUBNET_CONV = 4
NUM_REFINE_STAGE = 1
USE_RELU = False
FPN_CHANNEL = 256
# ---------------------------------------------Anchor config
LEVEL = ['P3', 'P4', 'P5', 'P6', 'P7']
BASE_ANCHOR_SIZE_LIST = [32, 64, 128, 256, 512]
ANCHOR_STRIDE = [8, 16, 32, 64, 128]
ANCHOR_SCALES = [2 ** 0, 2 ** (1.0 / 3.0), 2 ** (2.0 / 3.0)]
ANCHOR_RATIOS = [1, 1 / 2, 2., 1 / 3., 3., 5., 1 / 5.]
ANCHOR_ANGLES = [-90, -75, -60, -45, -30, -15]
ANCHOR_SCALE_FACTORS = None
USE_CENTER_OFFSET = True
METHOD = 'H'
USE_ANGLE_COND = False
ANGLE_RANGE = 90
# --------------------------------------------RPN config
SHARE_NET = True
USE_P5 = True
IOU_POSITIVE_THRESHOLD = 0.5
IOU_NEGATIVE_THRESHOLD = 0.4
REFINE_IOU_POSITIVE_THRESHOLD = [0.6, 0.7]
REFINE_IOU_NEGATIVE_THRESHOLD = [0.5, 0.6]
NMS = True
NMS_IOU_THRESHOLD = 0.1
MAXIMUM_DETECTIONS = 100
FILTERED_SCORE = 0.05
VIS_SCORE = 0.4
# --------------------------------------------MASK config
USE_SUPERVISED_MASK = False
MASK_TYPE = 'r' # r or h
BINARY_MASK = False
SIGMOID_ON_DOT = False
MASK_ACT_FET = True # weather use mask generate 256 channels to dot feat.
GENERATE_MASK_LIST = ["P3", "P4", "P5", "P6", "P7"]
ADDITION_LAYERS = [4, 4, 3, 2, 2] # add 4 layer to generate P2_mask, 2 layer to generate P3_mask
ENLAEGE_RF_LIST = ["P3", "P4", "P5", "P6", "P7"]
SUPERVISED_MASK_LOSS_WEIGHT = 1.0