/
darknet53.txt
70 lines (66 loc) · 2.14 KB
/
darknet53.txt
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
################################################################################
# The MIT License (MIT)
#
# Copyright (c) 2019-2021 NVIDIA CORPORATION
#
# Permission is hereby granted, free of charge, to any person obtaining a
# copy of this software and associated documentation files (the "Software"),
# to deal in the Software without restriction, including without limitation
# the rights to use, copy, modify, merge, publish, distribute, sublicense,
# and/or sell copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
# DEALINGS IN THE SOFTWARE.
################################################################################
model_config {
arch: "darknet"
n_layers: 53
use_batch_norm: True
use_bias: False
use_imagenet_head: True
all_projections: False
use_pooling: True
input_image_size: "3,224,224"
}
train_config {
train_dataset_path: "/workspace/tlt-experiments/data/imagenet2012/train"
val_dataset_path: "/workspace/tlt-experiments/data/imagenet2012/val"
optimizer {
sgd {
lr: 0.01
decay: 0.0
momentum: 0.9
nesterov: False
}
}
preprocess_mode: "torch"
enable_random_crop: True
enable_center_crop: True
label_smoothing: 0.0
batch_size_per_gpu: 64
n_epochs: 200
mixup_alpha: 0.2
# Number of CPU cores for loading data
n_workers: 40
reg_config {
type: "L2"
scope: "Conv2D,Dense"
weight_decay: 0.00003
}
lr_config {
cosine{
learning_rate: 0.05
soft_start: 0.0
min_lr_ratio: 0.001
}
}
}