Caffe: Accuracy stuck on 0
1
I'm trying to train AlexNet with multi class lmdb data.
The input layers are:
layer {
name: "data"
type: "Data"
top: "data"
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/TrainImage"
backend: LMDB
batch_size: 64
}
transform_param {
crop_size: 227
mean_file: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/TrainImage/TrainImage.binaryproto"
mirror: true
}
include: { phase: TRAIN }
}
layer {
name: "labels"
type: "Data"
top: "labels"
include {
phase: TRAIN
}
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/TrainLabel"
batch_size: 64
backend: LMDB
}
}
layer {
name: "data"
type: "Data"
top: "data"
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/ValImage"
backend: LMDB
batch_size: 64
}
transform_param {
crop_size: 227
mean_file: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/ValImage/ValImage.binaryproto"
mirror: false
}
include: { phase: TEST }
}
layer {
name: "labels"
type: "Data"
top: "labels"
include {
phase: TEST
}
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/ValLabel"
batch_size: 64
backend: LMDB
}
}
layer {
name: "slice"
type: "Slice"
bottom: "labels"
top: "class"
top: "subclass"
top: "color"
slice_param {
axis: 1
slice_point: 1
slice_point: 2
}
}
And the outputs layers are:
layer {
name: "fc8_1_class"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_1_class"
param {
lr_mult: 5
decay_mult: 1
}
param {
lr_mult: 10
decay_mult: 0
}
inner_product_param {
num_output: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "fc8_2_subclass"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_2_subclass"
param {
lr_mult: 5
decay_mult: 1
}
param {
lr_mult: 10
decay_mult: 0
}
inner_product_param {
num_output: 15
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "fc8_3_color"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_3_color"
param {
lr_mult: 5
decay_mult: 1
}
param {
lr_mult: 10
decay_mult: 0
}
inner_product_param {
num_output: 8
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy_class"
type: "Accuracy"
bottom: "fc8_1_class"
bottom: "class"
top: "accuracy_class"
include: { phase: TEST }
}
layer {
name: "loss_class"
type: "SoftmaxWithLoss"
bottom: "fc8_1_class"
bottom: "class"
top: "loss_class"
loss_weight: 0.5
}
layer {
name: "accuracy_subclass"
type: "Accuracy"
bottom: "fc8_2_subclass"
bottom: "subclass"
top: "accuracy_subclass"
include: { phase: TEST }
}
layer {
name: "loss_subclass"
type: "SoftmaxWithLoss"
bottom: "fc8_2_subclass"
bottom: "subclass"
top: "loss_subclass"
loss_weight: 0.5
}
layer {
name: "accuracy_color"
type: "Accuracy"
bottom: "fc8_3_color"
bottom: "color"
top: "accuracy_color"
include: { phase: TEST }
}
layer {
name: "loss_color"
type: "SoftmaxWithLoss"
bottom: "fc8_3_color"
bottom: "color"
top: "loss_color"
loss_weight: 0.5
}
"Class" is a dominant class with 2 labels which gives good accuracy, on the other hand "SubClass" has 15 labels and gives poor results, "Color" keeps giving me accuracy=0 no matter what I tryed.
This is part of train output:
I1123 10:47:52.258751 3392 solver.cpp:273] Learning Rate Policy: step
I1123 10:47:52.422647 3392 solver.cpp:218] Iteration 0 (7.96684e-08 iter/s, 0.163777s/100 iters), loss = 3.50787
I1123 10:47:52.422716 3392 solver.cpp:237] Train net output #0: loss_class = 1.83086 (* 0.5 = 0.915429 loss)
I1123 10:47:52.422742 3392 solver.cpp:237] Train net output #1: loss_color = 2.39675 (* 0.5 = 1.19837 loss)
I1123 10:47:52.422768 3392 solver.cpp:237] Train net output #2: loss_subclass = 2.78814 (* 0.5 = 1.39407 loss)
I1123 10:47:52.422803 3392 sgd_solver.cpp:105] Iteration 0, lr = 0.0001
I1123 10:48:01.282282 3392 solver.cpp:330] Iteration 100, Testing net (#0)
I1123 10:48:01.554111 3392 blocking_queue.cpp:49] Waiting for data
I1123 10:48:03.717224 3406 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:03.884392 3405 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:04.193727 3392 solver.cpp:397] Test net output #0: accuracy_class = 0.958594
I1123 10:48:04.193784 3392 solver.cpp:397] Test net output #1: accuracy_color = 0
I1123 10:48:04.193802 3392 solver.cpp:397] Test net output #2: accuracy_subclass = 0.495313
I1123 10:48:04.193841 3392 solver.cpp:397] Test net output #3: loss_class = 0.143002 (* 0.5 = 0.0715012 loss)
I1123 10:48:04.193871 3392 solver.cpp:397] Test net output #4: loss_color = 1.53319 (* 0.5 = 0.766597 loss)
I1123 10:48:04.193894 3392 solver.cpp:397] Test net output #5: loss_subclass = 1.40099 (* 0.5 = 0.700494 loss)
I1123 10:48:04.290772 3392 solver.cpp:218] Iteration 100 (8.42592 iter/s, 11.8681s/100 iters), loss = 1.50249
I1123 10:48:04.302697 3392 solver.cpp:237] Train net output #0: loss_class = 0.145322 (* 0.5 = 0.0726612 loss)
I1123 10:48:04.302740 3392 solver.cpp:237] Train net output #1: loss_color = 1.44309 (* 0.5 = 0.721547 loss)
I1123 10:48:04.302767 3392 solver.cpp:237] Train net output #2: loss_subclass = 1.41657 (* 0.5 = 0.708286 loss)
I1123 10:48:04.302788 3392 sgd_solver.cpp:105] Iteration 100, lr = 0.0001
I1123 10:48:08.030251 3404 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:08.077759 3403 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:13.195049 3392 solver.cpp:330] Iteration 200, Testing net (#0)
I1123 10:48:15.287199 3406 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:15.466104 3405 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:16.056556 3392 solver.cpp:397] Test net output #0: accuracy_class = 0.958594
I1123 10:48:16.056615 3392 solver.cpp:397] Test net output #1: accuracy_color = 0
I1123 10:48:16.056633 3392 solver.cpp:397] Test net output #2: accuracy_subclass = 0.520703
I1123 10:48:16.056658 3392 solver.cpp:397] Test net output #3: loss_class = 0.11685 (* 0.5 = 0.0584251 loss)
I1123 10:48:16.056679 3392 solver.cpp:397] Test net output #4: loss_color = 1.53322 (* 0.5 = 0.766609 loss)
I1123 10:48:16.056707 3392 solver.cpp:397] Test net output #5: loss_subclass = 1.42879 (* 0.5 = 0.714395 loss)
I1123 10:48:16.151207 3392 solver.cpp:218] Iteration 200 (8.43993 iter/s, 11.8484s/100 iters), loss = 1.74936
I1123 10:48:16.163187 3392 solver.cpp:237] Train net output #0: loss_class = 0.253774 (* 0.5 = 0.126887 loss)
I1123 10:48:16.163224 3392 solver.cpp:237] Train net output #1: loss_color = 1.69651 (* 0.5 = 0.848255 loss)
I1123 10:48:16.163246 3392 solver.cpp:237] Train net output #2: loss_subclass = 1.54843 (* 0.5 = 0.774216 loss)
I1123 10:48:16.163265 3392 sgd_solver.cpp:105] Iteration 200, lr = 0.0001
The data contains around 9000 images for train and another 2000 for validation, labels are in this form (starts from 0):
/media/gal/USB/MAFAT/crops/train/img/15036.png 0 4 18
/media/gal/USB/MAFAT/crops/train/img/31658.png 1 7 17
/media/gal/USB/MAFAT/crops/train/img/26971.png 0 4 17
/media/gal/USB/MAFAT/crops/train/img/19301.png 0 4 20
/media/gal/USB/MAFAT/crops/train/img/35906.png 1 7 17
/media/gal/USB/MAFAT/crops/train/img/24690.png 1 11 23
/media/gal/USB/MAFAT/crops/train/img/27442.png 0 9 24
/media/gal/USB/MAFAT/crops/train/img/26689.png 1 11 23
/media/gal/USB/MAFAT/crops/train/img/38403.png 0 4 19
/media/gal/USB/MAFAT/crops/train/img/37141.png 0 4 19
/media/gal/USB/MAFAT/crops/train/img/16961.png 0 4 21
/media/gal/USB/MAFAT/crops/train/img/23952.png 1 16 24
This is the solver file:
net: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/AlexNetMulti.prototxt"
test_initialization: false
test_iter: 40
test_interval: 100
base_lr: 0.0001
momentum: 0.9
gamma: 0.1
lr_policy: "step"
stepsize: 1600 # drop the learning rate every .... iterations
max_iter: 4800
display: 100
weight_decay: 0.0005
snapshot: 300000
snapshot_prefix: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/snapshot/GoogleNet_class"
solver_mode: GPU
Why am I keep getting accuracy 0 on "color" class?
caffe multilabel-classification multiclass-classification
asked Nov 23 '18 at 9:10
Gal DalaliGal Dalali
3916
add a comment |
1
I'm trying to train AlexNet with multi class lmdb data.
The input layers are:
layer {
name: "data"
type: "Data"
top: "data"
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/TrainImage"
backend: LMDB
batch_size: 64
}
transform_param {
crop_size: 227
mean_file: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/TrainImage/TrainImage.binaryproto"
mirror: true
}
include: { phase: TRAIN }
}
layer {
name: "labels"
type: "Data"
top: "labels"
include {
phase: TRAIN
}
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/TrainLabel"
batch_size: 64
backend: LMDB
}
}
layer {
name: "data"
type: "Data"
top: "data"
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/ValImage"
backend: LMDB
batch_size: 64
}
transform_param {
crop_size: 227
mean_file: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/ValImage/ValImage.binaryproto"
mirror: false
}
include: { phase: TEST }
}
layer {
name: "labels"
type: "Data"
top: "labels"
include {
phase: TEST
}
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/ValLabel"
batch_size: 64
backend: LMDB
}
}
layer {
name: "slice"
type: "Slice"
bottom: "labels"
top: "class"
top: "subclass"
top: "color"
slice_param {
axis: 1
slice_point: 1
slice_point: 2
}
}
And the outputs layers are:
layer {
name: "fc8_1_class"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_1_class"
param {
lr_mult: 5
decay_mult: 1
}
param {
lr_mult: 10
decay_mult: 0
}
inner_product_param {
num_output: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "fc8_2_subclass"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_2_subclass"
param {
lr_mult: 5
decay_mult: 1
}
param {
lr_mult: 10
decay_mult: 0
}
inner_product_param {
num_output: 15
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "fc8_3_color"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_3_color"
param {
lr_mult: 5
decay_mult: 1
}
param {
lr_mult: 10
decay_mult: 0
}
inner_product_param {
num_output: 8
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy_class"
type: "Accuracy"
bottom: "fc8_1_class"
bottom: "class"
top: "accuracy_class"
include: { phase: TEST }
}
layer {
name: "loss_class"
type: "SoftmaxWithLoss"
bottom: "fc8_1_class"
bottom: "class"
top: "loss_class"
loss_weight: 0.5
}
layer {
name: "accuracy_subclass"
type: "Accuracy"
bottom: "fc8_2_subclass"
bottom: "subclass"
top: "accuracy_subclass"
include: { phase: TEST }
}
layer {
name: "loss_subclass"
type: "SoftmaxWithLoss"
bottom: "fc8_2_subclass"
bottom: "subclass"
top: "loss_subclass"
loss_weight: 0.5
}
layer {
name: "accuracy_color"
type: "Accuracy"
bottom: "fc8_3_color"
bottom: "color"
top: "accuracy_color"
include: { phase: TEST }
}
layer {
name: "loss_color"
type: "SoftmaxWithLoss"
bottom: "fc8_3_color"
bottom: "color"
top: "loss_color"
loss_weight: 0.5
}
"Class" is a dominant class with 2 labels which gives good accuracy, on the other hand "SubClass" has 15 labels and gives poor results, "Color" keeps giving me accuracy=0 no matter what I tryed.
This is part of train output:
I1123 10:47:52.258751 3392 solver.cpp:273] Learning Rate Policy: step
I1123 10:47:52.422647 3392 solver.cpp:218] Iteration 0 (7.96684e-08 iter/s, 0.163777s/100 iters), loss = 3.50787
I1123 10:47:52.422716 3392 solver.cpp:237] Train net output #0: loss_class = 1.83086 (* 0.5 = 0.915429 loss)
I1123 10:47:52.422742 3392 solver.cpp:237] Train net output #1: loss_color = 2.39675 (* 0.5 = 1.19837 loss)
I1123 10:47:52.422768 3392 solver.cpp:237] Train net output #2: loss_subclass = 2.78814 (* 0.5 = 1.39407 loss)
I1123 10:47:52.422803 3392 sgd_solver.cpp:105] Iteration 0, lr = 0.0001
I1123 10:48:01.282282 3392 solver.cpp:330] Iteration 100, Testing net (#0)
I1123 10:48:01.554111 3392 blocking_queue.cpp:49] Waiting for data
I1123 10:48:03.717224 3406 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:03.884392 3405 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:04.193727 3392 solver.cpp:397] Test net output #0: accuracy_class = 0.958594
I1123 10:48:04.193784 3392 solver.cpp:397] Test net output #1: accuracy_color = 0
I1123 10:48:04.193802 3392 solver.cpp:397] Test net output #2: accuracy_subclass = 0.495313
I1123 10:48:04.193841 3392 solver.cpp:397] Test net output #3: loss_class = 0.143002 (* 0.5 = 0.0715012 loss)
I1123 10:48:04.193871 3392 solver.cpp:397] Test net output #4: loss_color = 1.53319 (* 0.5 = 0.766597 loss)
I1123 10:48:04.193894 3392 solver.cpp:397] Test net output #5: loss_subclass = 1.40099 (* 0.5 = 0.700494 loss)
I1123 10:48:04.290772 3392 solver.cpp:218] Iteration 100 (8.42592 iter/s, 11.8681s/100 iters), loss = 1.50249
I1123 10:48:04.302697 3392 solver.cpp:237] Train net output #0: loss_class = 0.145322 (* 0.5 = 0.0726612 loss)
I1123 10:48:04.302740 3392 solver.cpp:237] Train net output #1: loss_color = 1.44309 (* 0.5 = 0.721547 loss)
I1123 10:48:04.302767 3392 solver.cpp:237] Train net output #2: loss_subclass = 1.41657 (* 0.5 = 0.708286 loss)
I1123 10:48:04.302788 3392 sgd_solver.cpp:105] Iteration 100, lr = 0.0001
I1123 10:48:08.030251 3404 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:08.077759 3403 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:13.195049 3392 solver.cpp:330] Iteration 200, Testing net (#0)
I1123 10:48:15.287199 3406 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:15.466104 3405 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:16.056556 3392 solver.cpp:397] Test net output #0: accuracy_class = 0.958594
I1123 10:48:16.056615 3392 solver.cpp:397] Test net output #1: accuracy_color = 0
I1123 10:48:16.056633 3392 solver.cpp:397] Test net output #2: accuracy_subclass = 0.520703
I1123 10:48:16.056658 3392 solver.cpp:397] Test net output #3: loss_class = 0.11685 (* 0.5 = 0.0584251 loss)
I1123 10:48:16.056679 3392 solver.cpp:397] Test net output #4: loss_color = 1.53322 (* 0.5 = 0.766609 loss)
I1123 10:48:16.056707 3392 solver.cpp:397] Test net output #5: loss_subclass = 1.42879 (* 0.5 = 0.714395 loss)
I1123 10:48:16.151207 3392 solver.cpp:218] Iteration 200 (8.43993 iter/s, 11.8484s/100 iters), loss = 1.74936
I1123 10:48:16.163187 3392 solver.cpp:237] Train net output #0: loss_class = 0.253774 (* 0.5 = 0.126887 loss)
I1123 10:48:16.163224 3392 solver.cpp:237] Train net output #1: loss_color = 1.69651 (* 0.5 = 0.848255 loss)
I1123 10:48:16.163246 3392 solver.cpp:237] Train net output #2: loss_subclass = 1.54843 (* 0.5 = 0.774216 loss)
I1123 10:48:16.163265 3392 sgd_solver.cpp:105] Iteration 200, lr = 0.0001
The data contains around 9000 images for train and another 2000 for validation, labels are in this form (starts from 0):
/media/gal/USB/MAFAT/crops/train/img/15036.png 0 4 18
/media/gal/USB/MAFAT/crops/train/img/31658.png 1 7 17
/media/gal/USB/MAFAT/crops/train/img/26971.png 0 4 17
/media/gal/USB/MAFAT/crops/train/img/19301.png 0 4 20
/media/gal/USB/MAFAT/crops/train/img/35906.png 1 7 17
/media/gal/USB/MAFAT/crops/train/img/24690.png 1 11 23
/media/gal/USB/MAFAT/crops/train/img/27442.png 0 9 24
/media/gal/USB/MAFAT/crops/train/img/26689.png 1 11 23
/media/gal/USB/MAFAT/crops/train/img/38403.png 0 4 19
/media/gal/USB/MAFAT/crops/train/img/37141.png 0 4 19
/media/gal/USB/MAFAT/crops/train/img/16961.png 0 4 21
/media/gal/USB/MAFAT/crops/train/img/23952.png 1 16 24
This is the solver file:
net: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/AlexNetMulti.prototxt"
test_initialization: false
test_iter: 40
test_interval: 100
base_lr: 0.0001
momentum: 0.9
gamma: 0.1
lr_policy: "step"
stepsize: 1600 # drop the learning rate every .... iterations
max_iter: 4800
display: 100
weight_decay: 0.0005
snapshot: 300000
snapshot_prefix: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/snapshot/GoogleNet_class"
solver_mode: GPU
Why am I keep getting accuracy 0 on "color" class?
caffe multilabel-classification multiclass-classification
asked Nov 23 '18 at 9:10
Gal DalaliGal Dalali
3916
add a comment |
1
1
1
I'm trying to train AlexNet with multi class lmdb data.
The input layers are:
layer {
name: "data"
type: "Data"
top: "data"
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/TrainImage"
backend: LMDB
batch_size: 64
}
transform_param {
crop_size: 227
mean_file: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/TrainImage/TrainImage.binaryproto"
mirror: true
}
include: { phase: TRAIN }
}
layer {
name: "labels"
type: "Data"
top: "labels"
include {
phase: TRAIN
}
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/TrainLabel"
batch_size: 64
backend: LMDB
}
}
layer {
name: "data"
type: "Data"
top: "data"
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/ValImage"
backend: LMDB
batch_size: 64
}
transform_param {
crop_size: 227
mean_file: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/ValImage/ValImage.binaryproto"
mirror: false
}
include: { phase: TEST }
}
layer {
name: "labels"
type: "Data"
top: "labels"
include {
phase: TEST
}
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/ValLabel"
batch_size: 64
backend: LMDB
}
}
layer {
name: "slice"
type: "Slice"
bottom: "labels"
top: "class"
top: "subclass"
top: "color"
slice_param {
axis: 1
slice_point: 1
slice_point: 2
}
}
And the outputs layers are:
layer {
name: "fc8_1_class"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_1_class"
param {
lr_mult: 5
decay_mult: 1
}
param {
lr_mult: 10
decay_mult: 0
}
inner_product_param {
num_output: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "fc8_2_subclass"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_2_subclass"
param {
lr_mult: 5
decay_mult: 1
}
param {
lr_mult: 10
decay_mult: 0
}
inner_product_param {
num_output: 15
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "fc8_3_color"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_3_color"
param {
lr_mult: 5
decay_mult: 1
}
param {
lr_mult: 10
decay_mult: 0
}
inner_product_param {
num_output: 8
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy_class"
type: "Accuracy"
bottom: "fc8_1_class"
bottom: "class"
top: "accuracy_class"
include: { phase: TEST }
}
layer {
name: "loss_class"
type: "SoftmaxWithLoss"
bottom: "fc8_1_class"
bottom: "class"
top: "loss_class"
loss_weight: 0.5
}
layer {
name: "accuracy_subclass"
type: "Accuracy"
bottom: "fc8_2_subclass"
bottom: "subclass"
top: "accuracy_subclass"
include: { phase: TEST }
}
layer {
name: "loss_subclass"
type: "SoftmaxWithLoss"
bottom: "fc8_2_subclass"
bottom: "subclass"
top: "loss_subclass"
loss_weight: 0.5
}
layer {
name: "accuracy_color"
type: "Accuracy"
bottom: "fc8_3_color"
bottom: "color"
top: "accuracy_color"
include: { phase: TEST }
}
layer {
name: "loss_color"
type: "SoftmaxWithLoss"
bottom: "fc8_3_color"
bottom: "color"
top: "loss_color"
loss_weight: 0.5
}
"Class" is a dominant class with 2 labels which gives good accuracy, on the other hand "SubClass" has 15 labels and gives poor results, "Color" keeps giving me accuracy=0 no matter what I tryed.
This is part of train output:
I1123 10:47:52.258751 3392 solver.cpp:273] Learning Rate Policy: step
I1123 10:47:52.422647 3392 solver.cpp:218] Iteration 0 (7.96684e-08 iter/s, 0.163777s/100 iters), loss = 3.50787
I1123 10:47:52.422716 3392 solver.cpp:237] Train net output #0: loss_class = 1.83086 (* 0.5 = 0.915429 loss)
I1123 10:47:52.422742 3392 solver.cpp:237] Train net output #1: loss_color = 2.39675 (* 0.5 = 1.19837 loss)
I1123 10:47:52.422768 3392 solver.cpp:237] Train net output #2: loss_subclass = 2.78814 (* 0.5 = 1.39407 loss)
I1123 10:47:52.422803 3392 sgd_solver.cpp:105] Iteration 0, lr = 0.0001
I1123 10:48:01.282282 3392 solver.cpp:330] Iteration 100, Testing net (#0)
I1123 10:48:01.554111 3392 blocking_queue.cpp:49] Waiting for data
I1123 10:48:03.717224 3406 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:03.884392 3405 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:04.193727 3392 solver.cpp:397] Test net output #0: accuracy_class = 0.958594
I1123 10:48:04.193784 3392 solver.cpp:397] Test net output #1: accuracy_color = 0
I1123 10:48:04.193802 3392 solver.cpp:397] Test net output #2: accuracy_subclass = 0.495313
I1123 10:48:04.193841 3392 solver.cpp:397] Test net output #3: loss_class = 0.143002 (* 0.5 = 0.0715012 loss)
I1123 10:48:04.193871 3392 solver.cpp:397] Test net output #4: loss_color = 1.53319 (* 0.5 = 0.766597 loss)
I1123 10:48:04.193894 3392 solver.cpp:397] Test net output #5: loss_subclass = 1.40099 (* 0.5 = 0.700494 loss)
I1123 10:48:04.290772 3392 solver.cpp:218] Iteration 100 (8.42592 iter/s, 11.8681s/100 iters), loss = 1.50249
I1123 10:48:04.302697 3392 solver.cpp:237] Train net output #0: loss_class = 0.145322 (* 0.5 = 0.0726612 loss)
I1123 10:48:04.302740 3392 solver.cpp:237] Train net output #1: loss_color = 1.44309 (* 0.5 = 0.721547 loss)
I1123 10:48:04.302767 3392 solver.cpp:237] Train net output #2: loss_subclass = 1.41657 (* 0.5 = 0.708286 loss)
I1123 10:48:04.302788 3392 sgd_solver.cpp:105] Iteration 100, lr = 0.0001
I1123 10:48:08.030251 3404 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:08.077759 3403 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:13.195049 3392 solver.cpp:330] Iteration 200, Testing net (#0)
I1123 10:48:15.287199 3406 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:15.466104 3405 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:16.056556 3392 solver.cpp:397] Test net output #0: accuracy_class = 0.958594
I1123 10:48:16.056615 3392 solver.cpp:397] Test net output #1: accuracy_color = 0
I1123 10:48:16.056633 3392 solver.cpp:397] Test net output #2: accuracy_subclass = 0.520703
I1123 10:48:16.056658 3392 solver.cpp:397] Test net output #3: loss_class = 0.11685 (* 0.5 = 0.0584251 loss)
I1123 10:48:16.056679 3392 solver.cpp:397] Test net output #4: loss_color = 1.53322 (* 0.5 = 0.766609 loss)
I1123 10:48:16.056707 3392 solver.cpp:397] Test net output #5: loss_subclass = 1.42879 (* 0.5 = 0.714395 loss)
I1123 10:48:16.151207 3392 solver.cpp:218] Iteration 200 (8.43993 iter/s, 11.8484s/100 iters), loss = 1.74936
I1123 10:48:16.163187 3392 solver.cpp:237] Train net output #0: loss_class = 0.253774 (* 0.5 = 0.126887 loss)
I1123 10:48:16.163224 3392 solver.cpp:237] Train net output #1: loss_color = 1.69651 (* 0.5 = 0.848255 loss)
I1123 10:48:16.163246 3392 solver.cpp:237] Train net output #2: loss_subclass = 1.54843 (* 0.5 = 0.774216 loss)
I1123 10:48:16.163265 3392 sgd_solver.cpp:105] Iteration 200, lr = 0.0001
The data contains around 9000 images for train and another 2000 for validation, labels are in this form (starts from 0):
/media/gal/USB/MAFAT/crops/train/img/15036.png 0 4 18
/media/gal/USB/MAFAT/crops/train/img/31658.png 1 7 17
/media/gal/USB/MAFAT/crops/train/img/26971.png 0 4 17
/media/gal/USB/MAFAT/crops/train/img/19301.png 0 4 20
/media/gal/USB/MAFAT/crops/train/img/35906.png 1 7 17
/media/gal/USB/MAFAT/crops/train/img/24690.png 1 11 23
/media/gal/USB/MAFAT/crops/train/img/27442.png 0 9 24
/media/gal/USB/MAFAT/crops/train/img/26689.png 1 11 23
/media/gal/USB/MAFAT/crops/train/img/38403.png 0 4 19
/media/gal/USB/MAFAT/crops/train/img/37141.png 0 4 19
/media/gal/USB/MAFAT/crops/train/img/16961.png 0 4 21
/media/gal/USB/MAFAT/crops/train/img/23952.png 1 16 24
This is the solver file:
net: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/AlexNetMulti.prototxt"
test_initialization: false
test_iter: 40
test_interval: 100
base_lr: 0.0001
momentum: 0.9
gamma: 0.1
lr_policy: "step"
stepsize: 1600 # drop the learning rate every .... iterations
max_iter: 4800
display: 100
weight_decay: 0.0005
snapshot: 300000
snapshot_prefix: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/snapshot/GoogleNet_class"
solver_mode: GPU
Why am I keep getting accuracy 0 on "color" class?
caffe multilabel-classification multiclass-classification
asked Nov 23 '18 at 9:10
Gal DalaliGal Dalali
3916
I'm trying to train AlexNet with multi class lmdb data.
The input layers are:
layer {
name: "data"
type: "Data"
top: "data"
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/TrainImage"
backend: LMDB
batch_size: 64
}
transform_param {
crop_size: 227
mean_file: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/TrainImage/TrainImage.binaryproto"
mirror: true
}
include: { phase: TRAIN }
}
layer {
name: "labels"
type: "Data"
top: "labels"
include {
phase: TRAIN
}
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/TrainLabel"
batch_size: 64
backend: LMDB
}
}
layer {
name: "data"
type: "Data"
top: "data"
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/ValImage"
backend: LMDB
batch_size: 64
}
transform_param {
crop_size: 227
mean_file: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/ValImage/ValImage.binaryproto"
mirror: false
}
include: { phase: TEST }
}
layer {
name: "labels"
type: "Data"
top: "labels"
include {
phase: TEST
}
data_param {
source: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/ValLabel"
batch_size: 64
backend: LMDB
}
}
layer {
name: "slice"
type: "Slice"
bottom: "labels"
top: "class"
top: "subclass"
top: "color"
slice_param {
axis: 1
slice_point: 1
slice_point: 2
}
}
And the outputs layers are:
layer {
name: "fc8_1_class"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_1_class"
param {
lr_mult: 5
decay_mult: 1
}
param {
lr_mult: 10
decay_mult: 0
}
inner_product_param {
num_output: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "fc8_2_subclass"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_2_subclass"
param {
lr_mult: 5
decay_mult: 1
}
param {
lr_mult: 10
decay_mult: 0
}
inner_product_param {
num_output: 15
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "fc8_3_color"
type: "InnerProduct"
bottom: "fc7"
top: "fc8_3_color"
param {
lr_mult: 5
decay_mult: 1
}
param {
lr_mult: 10
decay_mult: 0
}
inner_product_param {
num_output: 8
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy_class"
type: "Accuracy"
bottom: "fc8_1_class"
bottom: "class"
top: "accuracy_class"
include: { phase: TEST }
}
layer {
name: "loss_class"
type: "SoftmaxWithLoss"
bottom: "fc8_1_class"
bottom: "class"
top: "loss_class"
loss_weight: 0.5
}
layer {
name: "accuracy_subclass"
type: "Accuracy"
bottom: "fc8_2_subclass"
bottom: "subclass"
top: "accuracy_subclass"
include: { phase: TEST }
}
layer {
name: "loss_subclass"
type: "SoftmaxWithLoss"
bottom: "fc8_2_subclass"
bottom: "subclass"
top: "loss_subclass"
loss_weight: 0.5
}
layer {
name: "accuracy_color"
type: "Accuracy"
bottom: "fc8_3_color"
bottom: "color"
top: "accuracy_color"
include: { phase: TEST }
}
layer {
name: "loss_color"
type: "SoftmaxWithLoss"
bottom: "fc8_3_color"
bottom: "color"
top: "loss_color"
loss_weight: 0.5
}
"Class" is a dominant class with 2 labels which gives good accuracy, on the other hand "SubClass" has 15 labels and gives poor results, "Color" keeps giving me accuracy=0 no matter what I tryed.
This is part of train output:
I1123 10:47:52.258751 3392 solver.cpp:273] Learning Rate Policy: step
I1123 10:47:52.422647 3392 solver.cpp:218] Iteration 0 (7.96684e-08 iter/s, 0.163777s/100 iters), loss = 3.50787
I1123 10:47:52.422716 3392 solver.cpp:237] Train net output #0: loss_class = 1.83086 (* 0.5 = 0.915429 loss)
I1123 10:47:52.422742 3392 solver.cpp:237] Train net output #1: loss_color = 2.39675 (* 0.5 = 1.19837 loss)
I1123 10:47:52.422768 3392 solver.cpp:237] Train net output #2: loss_subclass = 2.78814 (* 0.5 = 1.39407 loss)
I1123 10:47:52.422803 3392 sgd_solver.cpp:105] Iteration 0, lr = 0.0001
I1123 10:48:01.282282 3392 solver.cpp:330] Iteration 100, Testing net (#0)
I1123 10:48:01.554111 3392 blocking_queue.cpp:49] Waiting for data
I1123 10:48:03.717224 3406 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:03.884392 3405 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:04.193727 3392 solver.cpp:397] Test net output #0: accuracy_class = 0.958594
I1123 10:48:04.193784 3392 solver.cpp:397] Test net output #1: accuracy_color = 0
I1123 10:48:04.193802 3392 solver.cpp:397] Test net output #2: accuracy_subclass = 0.495313
I1123 10:48:04.193841 3392 solver.cpp:397] Test net output #3: loss_class = 0.143002 (* 0.5 = 0.0715012 loss)
I1123 10:48:04.193871 3392 solver.cpp:397] Test net output #4: loss_color = 1.53319 (* 0.5 = 0.766597 loss)
I1123 10:48:04.193894 3392 solver.cpp:397] Test net output #5: loss_subclass = 1.40099 (* 0.5 = 0.700494 loss)
I1123 10:48:04.290772 3392 solver.cpp:218] Iteration 100 (8.42592 iter/s, 11.8681s/100 iters), loss = 1.50249
I1123 10:48:04.302697 3392 solver.cpp:237] Train net output #0: loss_class = 0.145322 (* 0.5 = 0.0726612 loss)
I1123 10:48:04.302740 3392 solver.cpp:237] Train net output #1: loss_color = 1.44309 (* 0.5 = 0.721547 loss)
I1123 10:48:04.302767 3392 solver.cpp:237] Train net output #2: loss_subclass = 1.41657 (* 0.5 = 0.708286 loss)
I1123 10:48:04.302788 3392 sgd_solver.cpp:105] Iteration 100, lr = 0.0001
I1123 10:48:08.030251 3404 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:08.077759 3403 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:13.195049 3392 solver.cpp:330] Iteration 200, Testing net (#0)
I1123 10:48:15.287199 3406 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:15.466104 3405 data_layer.cpp:73] Restarting data prefetching from start.
I1123 10:48:16.056556 3392 solver.cpp:397] Test net output #0: accuracy_class = 0.958594
I1123 10:48:16.056615 3392 solver.cpp:397] Test net output #1: accuracy_color = 0
I1123 10:48:16.056633 3392 solver.cpp:397] Test net output #2: accuracy_subclass = 0.520703
I1123 10:48:16.056658 3392 solver.cpp:397] Test net output #3: loss_class = 0.11685 (* 0.5 = 0.0584251 loss)
I1123 10:48:16.056679 3392 solver.cpp:397] Test net output #4: loss_color = 1.53322 (* 0.5 = 0.766609 loss)
I1123 10:48:16.056707 3392 solver.cpp:397] Test net output #5: loss_subclass = 1.42879 (* 0.5 = 0.714395 loss)
I1123 10:48:16.151207 3392 solver.cpp:218] Iteration 200 (8.43993 iter/s, 11.8484s/100 iters), loss = 1.74936
I1123 10:48:16.163187 3392 solver.cpp:237] Train net output #0: loss_class = 0.253774 (* 0.5 = 0.126887 loss)
I1123 10:48:16.163224 3392 solver.cpp:237] Train net output #1: loss_color = 1.69651 (* 0.5 = 0.848255 loss)
I1123 10:48:16.163246 3392 solver.cpp:237] Train net output #2: loss_subclass = 1.54843 (* 0.5 = 0.774216 loss)
I1123 10:48:16.163265 3392 sgd_solver.cpp:105] Iteration 200, lr = 0.0001
The data contains around 9000 images for train and another 2000 for validation, labels are in this form (starts from 0):
/media/gal/USB/MAFAT/crops/train/img/15036.png 0 4 18
/media/gal/USB/MAFAT/crops/train/img/31658.png 1 7 17
/media/gal/USB/MAFAT/crops/train/img/26971.png 0 4 17
/media/gal/USB/MAFAT/crops/train/img/19301.png 0 4 20
/media/gal/USB/MAFAT/crops/train/img/35906.png 1 7 17
/media/gal/USB/MAFAT/crops/train/img/24690.png 1 11 23
/media/gal/USB/MAFAT/crops/train/img/27442.png 0 9 24
/media/gal/USB/MAFAT/crops/train/img/26689.png 1 11 23
/media/gal/USB/MAFAT/crops/train/img/38403.png 0 4 19
/media/gal/USB/MAFAT/crops/train/img/37141.png 0 4 19
/media/gal/USB/MAFAT/crops/train/img/16961.png 0 4 21
/media/gal/USB/MAFAT/crops/train/img/23952.png 1 16 24
This is the solver file:
net: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/AlexNetMulti.prototxt"
test_initialization: false
test_iter: 40
test_interval: 100
base_lr: 0.0001
momentum: 0.9
gamma: 0.1
lr_policy: "step"
stepsize: 1600 # drop the learning rate every .... iterations
max_iter: 4800
display: 100
weight_decay: 0.0005
snapshot: 300000
snapshot_prefix: "/home/gal/caffe-1.0/models/mixDCNN/hdf5/snapshot/GoogleNet_class"
solver_mode: GPU
Why am I keep getting accuracy 0 on "color" class?
caffe multilabel-classification multiclass-classification
caffe multilabel-classification multiclass-classification
asked Nov 23 '18 at 9:10
Gal DalaliGal Dalali
3916
asked Nov 23 '18 at 9:10
Gal DalaliGal Dalali
3916
asked Nov 23 '18 at 9:10
Gal DalaliGal Dalali
3916
asked Nov 23 '18 at 9:10
Gal DalaliGal Dalali
3916
asked Nov 23 '18 at 9:10
Gal DalaliGal Dalali
3916
3916
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
0
You set num_output: 8 for your "fc8_3_color" layer, that is, you are trying to predict "color" with 8 discrete classes 0..7. However, looking at your data the labels for color ranges from 17 to 24 -- this cannot work. the labels MUST be from 0..7 if you are using "SoftmaxWithLoss" and "Accuracy" layers.
answered Nov 26 '18 at 13:52
ShaiShai
70.7k23138247
add a comment |
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53443596%2fcaffe-accuracy-stuck-on-0%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
0
You set num_output: 8 for your "fc8_3_color" layer, that is, you are trying to predict "color" with 8 discrete classes 0..7. However, looking at your data the labels for color ranges from 17 to 24 -- this cannot work. the labels MUST be from 0..7 if you are using "SoftmaxWithLoss" and "Accuracy" layers.
answered Nov 26 '18 at 13:52
ShaiShai
70.7k23138247
add a comment |
0
You set num_output: 8 for your "fc8_3_color" layer, that is, you are trying to predict "color" with 8 discrete classes 0..7. However, looking at your data the labels for color ranges from 17 to 24 -- this cannot work. the labels MUST be from 0..7 if you are using "SoftmaxWithLoss" and "Accuracy" layers.
answered Nov 26 '18 at 13:52
ShaiShai
70.7k23138247
add a comment |
0
0
0
You set num_output: 8 for your "fc8_3_color" layer, that is, you are trying to predict "color" with 8 discrete classes 0..7. However, looking at your data the labels for color ranges from 17 to 24 -- this cannot work. the labels MUST be from 0..7 if you are using "SoftmaxWithLoss" and "Accuracy" layers.
answered Nov 26 '18 at 13:52
ShaiShai
70.7k23138247
You set num_output: 8 for your "fc8_3_color" layer, that is, you are trying to predict "color" with 8 discrete classes 0..7. However, looking at your data the labels for color ranges from 17 to 24 -- this cannot work. the labels MUST be from 0..7 if you are using "SoftmaxWithLoss" and "Accuracy" layers.
answered Nov 26 '18 at 13:52
ShaiShai
70.7k23138247
answered Nov 26 '18 at 13:52
ShaiShai
70.7k23138247
answered Nov 26 '18 at 13:52
ShaiShai
70.7k23138247
answered Nov 26 '18 at 13:52
ShaiShai
70.7k23138247
70.7k23138247
add a comment |
add a comment |
draft saved
draft discarded
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53443596%2fcaffe-accuracy-stuck-on-0%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
