Comments (8)
@wishinger-li There are customized layers such as data layer and tiling layer.
from vpgnet.
upsampling layer i have added .i will release it
from vpgnet.
@hexiangquan ,have you release it?
from vpgnet.
@SeokjuLee @wishinger-li
Did you successfully compile with this caffe? Why do I always fail to compile,
the error like that:
./include/caffe/layers/pooling_layer.hpp:54:3: error: ‘PoolingParameter_RoundMode’ does not name a type
PoolingParameter_RoundMode round_mode_;
^
Makefile:524: recipe for target '.build_release/src/caffe/layers/cudnn_pooling_layer.o' failed
make: *** [.build_release/src/caffe/layers/cudnn_pooling_layer.o] Error 1
who can help me?
from vpgnet.
@screamdw Did you uncomment # USE_CUDNN := 1 in Makefile.config?
from vpgnet.
@SeokjuLee can you help me?
I've compiled it successfully,and the make_lmdb.sh runs successfully.but when I run train.sh ,There were some errors:
➜ vpgnet-novp bash train.sh
train.sh: 行 1: 6452 段错误 (核心已转储) ../../build/tools/caffe train --solver=./solver.prototxt >> ./output/output.log 2>&1
The contents of this file(output.log) are as follows:
I0314 15:42:40.633046 6452 caffe.cpp:183] Using GPUs 0
I0314 15:42:40.858393 6452 solver.cpp:54] Initializing solver from parameters:
test_iter: 20
test_interval: 100
base_lr: 0.005
display: 10
max_iter: 100000
lr_policy: "step"
gamma: 0.1
momentum: 0.9
weight_decay: 0.0005
stepsize: 100000
snapshot: 2500
snapshot_prefix: "./snapshots/split"
solver_mode: GPU
device_id: 0
test_compute_loss: true
net: "./train_val.prototxt"
I0314 15:42:40.858433 6452 solver.cpp:96] Creating training net from net file: ./train_val.prototxt
I0314 15:42:40.858779 6452 net.cpp:339] The NetState phase (0) differed from the phase (1) specified by a rule in layer data
I0314 15:42:40.858803 6452 net.cpp:339] The NetState phase (0) differed from the phase (1) specified by a rule in layer pixel-acc
I0314 15:42:40.858808 6452 net.cpp:339] The NetState phase (0) differed from the phase (1) specified by a rule in layer type-acc
I0314 15:42:40.858986 6452 net.cpp:50] Initializing net from parameters:
name: "VPGNet-noVP"
state {
phase: TRAIN
}
layer {
name: "data"
type: "DriveData"
top: "data"
top: "label"
top: "type"
include {
phase: TRAIN
}
transform_param {
mean_file: "./driving_mean_train.binaryproto"
}
data_param {
source: "./LMDB_train"
batch_size: 24
backend: LMDB
}
drive_data_param {
shrink_prob_factor: 1
unrecognize_factor: 0
crop_num: 1
random_crop_ratio: 1
resize: 1
scale: 1
catalog_resolution: 4
reco_min: 4
train_min: 4
}
}
layer {
name: "slice-label"
type: "Slice"
bottom: "label"
top: "pixel-label"
top: "bb-label"
top: "size-label"
top: "norm-label"
slice_param {
slice_dim: 1
slice_point: 1
slice_point: 5
slice_point: 7
}
}
layer {
name: "pixel-block"
type: "Concat"
bottom: "pixel-label"
bottom: "pixel-label"
bottom: "pixel-label"
bottom: "pixel-label"
top: "pixel-block"
concat_param {
concat_dim: 1
}
}
layer {
name: "size-block"
type: "Concat"
bottom: "size-label"
bottom: "size-label"
top: "size-block"
concat_param {
concat_dim: 1
}
}
layer {
name: "norm-block"
type: "Concat"
bottom: "norm-label"
bottom: "norm-label"
bottom: "norm-label"
bottom: "norm-label"
top: "norm-block"
concat_param {
concat_dim: 1
}
}
layer {
name: "bb-label-size-normalization"
type: "Eltwise"
bottom: "bb-label"
bottom: "size-block"
top: "bb-label-sn"
eltwise_param {
operation: PROD
}
}
layer {
name: "bb-label-num-pixel-normalization"
type: "Eltwise"
bottom: "bb-label-sn"
bottom: "norm-block"
top: "bb-label-sn-nn"
eltwise_param {
operation: PROD
}
}
layer {
name: "L0"
type: "Convolution"
bottom: "data"
top: "L0"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "L0"
top: "L0"
}
layer {
name: "norm1"
type: "LRN"
bottom: "L0"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0005
beta: 0.75
k: 2
}
}
layer {
name: "pool1"
type: "Pooling"
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "L1"
type: "Convolution"
bottom: "pool1"
top: "L1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
group: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "L1"
top: "L1"
}
layer {
name: "norm2"
type: "LRN"
bottom: "L1"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0005
beta: 0.75
k: 8
}
}
layer {
name: "pool2"
type: "Pooling"
bottom: "norm2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "L2"
type: "Convolution"
bottom: "pool2"
top: "L2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "L2"
top: "L2"
}
layer {
name: "L3"
type: "Convolution"
bottom: "L2"
top: "L3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "L3"
top: "L3"
}
layer {
name: "L4"
type: "Convolution"
bottom: "L3"
top: "L4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "L4"
top: "L4"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "L4"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "L5"
type: "Convolution"
bottom: "pool5"
top: "L5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 4096
pad: 3
kernel_size: 6
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "L5"
top: "L5"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "L5"
top: "L5"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "L6a"
type: "Convolution"
bottom: "L5"
top: "L6a"
param {
lr_mult: 5
decay_mult: 0.1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 4096
kernel_size: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu7a"
type: "ReLU"
bottom: "L6a"
top: "L6a"
}
layer {
name: "drop7a"
type: "Dropout"
bottom: "L6a"
top: "L6a"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "L6b"
type: "Convolution"
bottom: "L5"
top: "L6b"
param {
lr_mult: 5
decay_mult: 0.1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 4096
kernel_size: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu7b"
type: "ReLU"
bottom: "L6b"
top: "L6b"
}
layer {
name: "drop7b"
type: "Dropout"
bottom: "L6b"
top: "L6b"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "L6c"
type: "Convolution"
bottom: "L5"
top: "L6c"
param {
lr_mult: 5
decay_mult: 0.1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 4096
kernel_size: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu7c"
type: "ReLU"
bottom: "L6c"
top: "L6c"
}
layer {
name: "drop7c"
type: "Dropout"
bottom: "L6c"
top: "L6c"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "bb-output"
type: "Convolution"
bottom: "L6a"
top: "bb-output"
param {
lr_mult: 20
decay_mult: 0.1
}
param {
lr_mult: 20
decay_mult: 0
}
convolution_param {
num_output: 256
kernel_size: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "pixel-conv"
type: "Convolution"
bottom: "L6b"
top: "pixel-conv"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 128
kernel_size: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "type-conv"
type: "Convolution"
bottom: "L6c"
top: "type-conv"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 1024
kernel_size: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "pixel-tile"
type: "Tiling"
bottom: "pixel-conv"
top: "pixel-conv-tiled"
tiling_param {
tile_dim: 8
}
}
layer {
name: "bb-tile"
type: "Tiling"
bottom: "bb-output"
top: "bb-output-tiled"
tiling_param {
tile_dim: 8
}
}
layer {
name: "type-tile"
type: "Tiling"
bottom: "type-conv"
top: "type-conv-tiled"
tiling_param {
tile_dim: 4
}
}
layer {
name: "pixel-loss"
type: "SoftmaxWithLoss"
bottom: "pixel-conv-tiled"
bottom: "pixel-label"
top: "pixel-loss"
loss_weight: 1
}
layer {
name: "type-loss"
type: "SoftmaxWithLoss"
bottom: "type-conv-tiled"
bottom: "type"
top: "type-loss"
loss_weight: 1
}
layer {
name: "bb-prob-mask"
type: "Eltwise"
bottom: "bb-output-tiled"
bottom: "pixel-block"
top: "bb-masked-output"
eltwise_param {
operation: PROD
}
}
layer {
name: "bb-size-normalization"
type: "Eltwise"
bottom: "bb-masked-output"
bottom: "size-block"
top: "bb-masked-output-sn"
eltwise_param {
operation: PROD
}
}
layer {
name: "bb-num-pixel-normalization"
type: "Eltwise"
bottom: "bb-masked-output-sn"
bottom: "norm-block"
top: "bb-masked-output-sn-nn"
eltwise_param {
operation: PROD
}
}
layer {
name: "bb-loss"
type: "L1Loss"
bottom: "bb-masked-output-sn-nn"
bottom: "bb-label-sn-nn"
top: "bb-loss"
loss_weight: 3
}
I0314 15:42:40.859165 6452 layer_factory.hpp:76] Creating layer data
I0314 15:42:40.859302 6452 net.cpp:110] Creating Layer data
I0314 15:42:40.859313 6452 net.cpp:432] data -> data
I0314 15:42:40.859341 6452 net.cpp:432] data -> label
I0314 15:42:40.859350 6452 net.cpp:432] data -> type
I0314 15:42:40.859362 6452 data_transformer.cpp:23] Loading mean file from: ./driving_mean_train.binaryproto
I0314 15:42:40.859751 6456 db_lmdb.cpp:22] Opened lmdb ./LMDB_train
I0314 15:42:40.880087 6452 drive_data_layer.cpp:49] output data size: 24,3,480,640
I0314 15:42:40.983275 6452 net.cpp:155] Setting up data
I0314 15:42:40.983322 6452 net.cpp:163] Top shape: 24 3 480 640 (22118400)
I0314 15:42:40.983328 6452 net.cpp:163] Top shape: 24 8 120 160 (3686400)
I0314 15:42:40.983333 6452 net.cpp:163] Top shape: 24 1 60 80 (115200)
I0314 15:42:40.983340 6452 layer_factory.hpp:76] Creating layer slice-label
I0314 15:42:40.983350 6452 net.cpp:110] Creating Layer slice-label
I0314 15:42:40.983356 6452 net.cpp:476] slice-label <- label
I0314 15:42:40.983366 6452 net.cpp:432] slice-label -> pixel-label
I0314 15:42:40.983376 6452 net.cpp:432] slice-label -> bb-label
I0314 15:42:40.983382 6452 net.cpp:432] slice-label -> size-label
I0314 15:42:40.983387 6452 net.cpp:432] slice-label -> norm-label
I0314 15:42:40.983397 6452 net.cpp:155] Setting up slice-label
I0314 15:42:40.983402 6452 net.cpp:163] Top shape: 24 1 120 160 (460800)
I0314 15:42:40.983405 6452 net.cpp:163] Top shape: 24 4 120 160 (1843200)
I0314 15:42:40.983409 6452 net.cpp:163] Top shape: 24 2 120 160 (921600)
I0314 15:42:40.983413 6452 net.cpp:163] Top shape: 24 1 120 160 (460800)
I0314 15:42:40.983417 6452 layer_factory.hpp:76] Creating layer pixel-label_slice-label_0_split
I0314 15:42:40.983422 6452 net.cpp:110] Creating Layer pixel-label_slice-label_0_split
I0314 15:42:40.983427 6452 net.cpp:476] pixel-label_slice-label_0_split <- pixel-label
I0314 15:42:40.983438 6452 net.cpp:432] pixel-label_slice-label_0_split -> pixel-label_slice-label_0_split_0
I0314 15:42:40.983450 6452 net.cpp:432] pixel-label_slice-label_0_split -> pixel-label_slice-label_0_split_1
I0314 15:42:40.983458 6452 net.cpp:432] pixel-label_slice-label_0_split -> pixel-label_slice-label_0_split_2
I0314 15:42:40.983464 6452 net.cpp:432] pixel-label_slice-label_0_split -> pixel-label_slice-label_0_split_3
I0314 15:42:40.983469 6452 net.cpp:432] pixel-label_slice-label_0_split -> pixel-label_slice-label_0_split_4
I0314 15:42:40.983475 6452 net.cpp:155] Setting up pixel-label_slice-label_0_split
I0314 15:42:40.983479 6452 net.cpp:163] Top shape: 24 1 120 160 (460800)
I0314 15:42:40.983484 6452 net.cpp:163] Top shape: 24 1 120 160 (460800)
I0314 15:42:40.983487 6452 net.cpp:163] Top shape: 24 1 120 160 (460800)
I0314 15:42:40.983491 6452 net.cpp:163] Top shape: 24 1 120 160 (460800)
I0314 15:42:40.983495 6452 net.cpp:163] Top shape: 24 1 120 160 (460800)
I0314 15:42:40.983500 6452 layer_factory.hpp:76] Creating layer size-label_slice-label_2_split
I0314 15:42:40.983503 6452 net.cpp:110] Creating Layer size-label_slice-label_2_split
I0314 15:42:40.983507 6452 net.cpp:476] size-label_slice-label_2_split <- size-label
I0314 15:42:40.983511 6452 net.cpp:432] size-label_slice-label_2_split -> size-label_slice-label_2_split_0
I0314 15:42:40.983517 6452 net.cpp:432] size-label_slice-label_2_split -> size-label_slice-label_2_split_1
I0314 15:42:40.983522 6452 net.cpp:155] Setting up size-label_slice-label_2_split
I0314 15:42:40.983527 6452 net.cpp:163] Top shape: 24 2 120 160 (921600)
I0314 15:42:40.983531 6452 net.cpp:163] Top shape: 24 2 120 160 (921600)
I0314 15:42:40.983534 6452 layer_factory.hpp:76] Creating layer norm-label_slice-label_3_split
I0314 15:42:40.983539 6452 net.cpp:110] Creating Layer norm-label_slice-label_3_split
I0314 15:42:40.983542 6452 net.cpp:476] norm-label_slice-label_3_split <- norm-label
I0314 15:42:40.983547 6452 net.cpp:432] norm-label_slice-label_3_split -> norm-label_slice-label_3_split_0
I0314 15:42:40.983552 6452 net.cpp:432] norm-label_slice-label_3_split -> norm-label_slice-label_3_split_1
I0314 15:42:40.983558 6452 net.cpp:432] norm-label_slice-label_3_split -> norm-label_slice-label_3_split_2
I0314 15:42:40.983566 6452 net.cpp:432] norm-label_slice-label_3_split -> norm-label_slice-label_3_split_3
I0314 15:42:40.983572 6452 net.cpp:155] Setting up norm-label_slice-label_3_split
I0314 15:42:40.983575 6452 net.cpp:163] Top shape: 24 1 120 160 (460800)
I0314 15:42:40.983579 6452 net.cpp:163] Top shape: 24 1 120 160 (460800)
I0314 15:42:40.983583 6452 net.cpp:163] Top shape: 24 1 120 160 (460800)
I0314 15:42:40.983587 6452 net.cpp:163] Top shape: 24 1 120 160 (460800)
I0314 15:42:40.983590 6452 layer_factory.hpp:76] Creating layer pixel-block
I0314 15:42:40.983597 6452 net.cpp:110] Creating Layer pixel-block
I0314 15:42:40.983600 6452 net.cpp:476] pixel-block <- pixel-label_slice-label_0_split_0
I0314 15:42:40.983604 6452 net.cpp:476] pixel-block <- pixel-label_slice-label_0_split_1
I0314 15:42:40.983608 6452 net.cpp:476] pixel-block <- pixel-label_slice-label_0_split_2
I0314 15:42:40.983613 6452 net.cpp:476] pixel-block <- pixel-label_slice-label_0_split_3
I0314 15:42:40.983618 6452 net.cpp:432] pixel-block -> pixel-block
I0314 15:42:40.983625 6452 net.cpp:155] Setting up pixel-block
I0314 15:42:40.983629 6452 net.cpp:163] Top shape: 24 4 120 160 (1843200)
I0314 15:42:40.983633 6452 layer_factory.hpp:76] Creating layer size-block
I0314 15:42:40.983638 6452 net.cpp:110] Creating Layer size-block
I0314 15:42:40.983641 6452 net.cpp:476] size-block <- size-label_slice-label_2_split_0
I0314 15:42:40.983645 6452 net.cpp:476] size-block <- size-label_slice-label_2_split_1
I0314 15:42:40.983650 6452 net.cpp:432] size-block -> size-block
I0314 15:42:40.983655 6452 net.cpp:155] Setting up size-block
I0314 15:42:40.983660 6452 net.cpp:163] Top shape: 24 4 120 160 (1843200)
I0314 15:42:40.983664 6452 layer_factory.hpp:76] Creating layer size-block_size-block_0_split
I0314 15:42:40.983670 6452 net.cpp:110] Creating Layer size-block_size-block_0_split
I0314 15:42:40.983677 6452 net.cpp:476] size-block_size-block_0_split <- size-block
I0314 15:42:40.983682 6452 net.cpp:432] size-block_size-block_0_split -> size-block_size-block_0_split_0
I0314 15:42:40.983688 6452 net.cpp:432] size-block_size-block_0_split -> size-block_size-block_0_split_1
I0314 15:42:40.983693 6452 net.cpp:155] Setting up size-block_size-block_0_split
I0314 15:42:40.983698 6452 net.cpp:163] Top shape: 24 4 120 160 (1843200)
I0314 15:42:40.983701 6452 net.cpp:163] Top shape: 24 4 120 160 (1843200)
I0314 15:42:40.983705 6452 layer_factory.hpp:76] Creating layer norm-block
I0314 15:42:40.983711 6452 net.cpp:110] Creating Layer norm-block
I0314 15:42:40.983714 6452 net.cpp:476] norm-block <- norm-label_slice-label_3_split_0
I0314 15:42:40.983718 6452 net.cpp:476] norm-block <- norm-label_slice-label_3_split_1
I0314 15:42:40.983723 6452 net.cpp:476] norm-block <- norm-label_slice-label_3_split_2
I0314 15:42:40.983727 6452 net.cpp:476] norm-block <- norm-label_slice-label_3_split_3
I0314 15:42:40.983732 6452 net.cpp:432] norm-block -> norm-block
I0314 15:42:40.983737 6452 net.cpp:155] Setting up norm-block
I0314 15:42:40.983742 6452 net.cpp:163] Top shape: 24 4 120 160 (1843200)
I0314 15:42:40.983745 6452 layer_factory.hpp:76] Creating layer norm-block_norm-block_0_split
I0314 15:42:40.983749 6452 net.cpp:110] Creating Layer norm-block_norm-block_0_split
I0314 15:42:40.983753 6452 net.cpp:476] norm-block_norm-block_0_split <- norm-block
I0314 15:42:40.983757 6452 net.cpp:432] norm-block_norm-block_0_split -> norm-block_norm-block_0_split_0
I0314 15:42:40.983762 6452 net.cpp:432] norm-block_norm-block_0_split -> norm-block_norm-block_0_split_1
I0314 15:42:40.983767 6452 net.cpp:155] Setting up norm-block_norm-block_0_split
I0314 15:42:40.983772 6452 net.cpp:163] Top shape: 24 4 120 160 (1843200)
I0314 15:42:40.983777 6452 net.cpp:163] Top shape: 24 4 120 160 (1843200)
I0314 15:42:40.983779 6452 layer_factory.hpp:76] Creating layer bb-label-size-normalization
I0314 15:42:40.983784 6452 net.cpp:110] Creating Layer bb-label-size-normalization
I0314 15:42:40.983788 6452 net.cpp:476] bb-label-size-normalization <- bb-label
I0314 15:42:40.983793 6452 net.cpp:476] bb-label-size-normalization <- size-block_size-block_0_split_0
I0314 15:42:40.983796 6452 net.cpp:432] bb-label-size-normalization -> bb-label-sn
I0314 15:42:40.983804 6452 net.cpp:155] Setting up bb-label-size-normalization
I0314 15:42:40.983809 6452 net.cpp:163] Top shape: 24 4 120 160 (1843200)
I0314 15:42:40.983813 6452 layer_factory.hpp:76] Creating layer bb-label-num-pixel-normalization
I0314 15:42:40.983816 6452 net.cpp:110] Creating Layer bb-label-num-pixel-normalization
I0314 15:42:40.983820 6452 net.cpp:476] bb-label-num-pixel-normalization <- bb-label-sn
I0314 15:42:40.983824 6452 net.cpp:476] bb-label-num-pixel-normalization <- norm-block_norm-block_0_split_0
I0314 15:42:40.983829 6452 net.cpp:432] bb-label-num-pixel-normalization -> bb-label-sn-nn
I0314 15:42:40.983834 6452 net.cpp:155] Setting up bb-label-num-pixel-normalization
I0314 15:42:40.983839 6452 net.cpp:163] Top shape: 24 4 120 160 (1843200)
I0314 15:42:40.983841 6452 layer_factory.hpp:76] Creating layer L0
I0314 15:42:40.983849 6452 net.cpp:110] Creating Layer L0
I0314 15:42:40.983852 6452 net.cpp:476] L0 <- data
I0314 15:42:40.983857 6452 net.cpp:432] L0 -> L0
*** Aborted at 1552549361 (unix time) try "date -d @1552549361" if you are using GNU date ***
PC: @ 0x7f65c6316e7c caffe::CuDNNConvolutionLayer<>::LayerSetUp()
*** SIGSEGV (@0xEA) received by PID 6452 (TID 0x7f65c6a09740) from PID 234; stack trace: ***
@ 0x7f65c4ac4390 (unknown)
@ 0x7f65c6316e7c caffe::CuDNNConvolutionLayer<>::LayerSetUp()
@ 0x7f65c63e6614 caffe::Net<>::Init()
@ 0x7f65c63e8491 caffe::Net<>::Net()
@ 0x7f65c62644ba caffe::Solver<>::InitTrainNet()
@ 0x7f65c62657af caffe::Solver<>::Init()
@ 0x7f65c6265b29 caffe::Solver<>::Solver()
@ 0x41503d caffe::GetSolver<>()
@ 0x40b721 train()
@ 0x408840 main
@ 0x7f65c4709830 __libc_start_main
@ 0x408f99 _start
@ 0x0 (unknown)
from vpgnet.
@screamdw same problem, did you solve the problem?
from vpgnet.
@SeokjuLee @screamdw @ycdhqzhiai
same problem.
from vpgnet.
Related Issues (20)
- facing a problem when make all HOT 2
- face a problem when caffe compile HOT 1
- Request for a license HOT 1
- IPM corner points
- Nobody cares this project?
- ENet-Label-Torch is available now (a light-weight and effective lane detection model)
- Test code on other data sets HOT 1
- the dataset and pre-trained model HOT 2
- A good value for test result
- about multi label grid box and object mask some problem HOT 1
- Make runtest failed on Ubuntu 16.04 and CUDA 10.0
- Dataset HOT 14
- Bounding Box Regression task not learning, it has constant loss
- Training on VPGNet dataset. HOT 3
- Make error : src/caffe/util/io.cpp:73:34: error: ‘CV_LOAD_IMAGE_HDR’ was not declared in this scope HOT 2
- Inference scripts using pretrained model
- Could you provide me how you split training set and testing set in your dataset like Table 1 HOT 1
- Could you provide the camera parameters?
- the loss of vp
- no image
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from vpgnet.