-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcifar10_resnet20.hocon
63 lines (54 loc) · 2.04 KB
/
cifar10_resnet20.hocon
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
# ------------ General options ----------------------------------------
save_path = "./save_cifar10/"
dataPath = "/mnt/cephfs/dataset/"
dataset = "cifar10" # options: imagenet | cifar100
nGPU = 1 # number of GPUs to use by default
GPU = 0 # default gpu to use, options: range(nGPU)
visible_devices = "4"
save_images = True
# ------------- Data options -------------------------------------------
nThreads = 8 # number of data loader threads
# ---------- Optimization options for S --------------------------------------
nEpochs = 400 # number of total epochs to train 400
GAN_aug_train_epoch = 4000
batchSize = 200 # batchsize
momentum = 0.9 # momentum 0.9
weightDecay = 1e-4 # weight decay 1e-4
opt_type = "SGD"
warmup_epochs = 1 # number of epochs for warmup
lr_S = 0.0001 # initial learning rate = 0.00001
lrPolicy_S = "multi_step" # options: multi_step | linear | exp | const | step
step_S = [100,200,300] # step for linear or exp learning rate policy default [100, 200, 300]
decayRate_S = 0.1 # lr decay rate
# ---------- Model options ---------------------------------------------
experimentID = "cifar10_4bit_"
nClasses = 10 # number of classes in the dataset
# ---------- Quantization options ---------------------------------------------
qw = 4
qa = 4
# ----------KD options ---------------------------------------------
temperature = 20
alpha = 1
# ----------Generator options ---------------------------------------------
latent_dim = 100
img_size = 32
channels = 3
lr_G = 0.001 # default 0.001
lrPolicy_G = "multi_step" # options: multi_step | linear | exp | const | step
step_G = [100,200,300] # step for linear or exp learning rate policy
decayRate_G = 0.1 # lr decay rate
lr_D = 0.001 # default 0.001
lrPolicy_D = "multi_step" # options: multi_step | linear | exp | const | step
step_D = [100,200,300] # step for linear or exp learning rate policy
decayRate_D = 0.1 # lr decay rate
b1 = 0.5
b2 = 0.999
beta = 0.1
basis_num = 128 # basis_num of LCC
lcc_lr = 0.01
lcc_beta1 = 0.5
lcc_beta2 = 0.999
#Lv = 0.0001
#Lh = 1
LG = 2
LCCLAMBDA = 0.2