--num_worker is the GPUs numbers? about temporal-segment-networks

[yjxiong]

This means the initialization of the networks has failed. Please run with --num_worker 1 to see what is the error.

[wxw420]

I run with --num_worker 1
wang@xs:~/deep-learning/TSN-action$ python tools/eval_net.py ucf101 1 rgb /home/xs/deep-learning/dataset/UCF101_FRAMES/ models/ucf101/tsn_bn_inception_rgb_deploy.prototxt models/ucf101_split_1_tsn_rgb_reference_bn_inception.caffemodel --num_worker 1 --save_scores score_file
Namespace(caffe_path='./lib/caffe-action/', dataset='ucf101', flow_x_prefix='flow_x_', flow_y_prefix='flow_y_', frame_path='/home/xs/deep-learning/dataset/UCF101_FRAMES/', gpus=None, modality='rgb', net_proto='models/ucf101/tsn_bn_inception_rgb_deploy.prototxt', net_weights='models/ucf101_split_1_tsn_rgb_reference_bn_inception.caffemodel', num_frame_per_video=25, num_worker=1, rgb_prefix='img_', save_scores='score_file', split=1)
ucf101
parse frames under folder /home/xs/deep-learning/dataset/UCF101_FRAMES/
0 videos parsed
200 videos parsed
400 videos parsed
600 videos parsed
800 videos parsed
1000 videos parsed
1200 videos parsed
1400 videos parsed
1600 videos parsed
1800 videos parsed
2000 videos parsed
2200 videos parsed
2400 videos parsed
2600 videos parsed
2800 videos parsed
3000 videos parsed
3200 videos parsed
3400 videos parsed
3600 videos parsed
3800 videos parsed
4000 videos parsed
4200 videos parsed
4400 videos parsed
4600 videos parsed
4800 videos parsed
5000 videos parsed
5200 videos parsed
5400 videos parsed
5600 videos parsed
5800 videos parsed
6000 videos parsed
6200 videos parsed
6400 videos parsed
6600 videos parsed
6800 videos parsed
7000 videos parsed
7200 videos parsed
7400 videos parsed
7600 videos parsed
7800 videos parsed
8000 videos parsed
8200 videos parsed
8400 videos parsed
8600 videos parsed
8800 videos parsed
9000 videos parsed
9200 videos parsed
9400 videos parsed
9600 videos parsed
9800 videos parsed
10000 videos parsed
10200 videos parsed
10400 videos parsed
10600 videos parsed
10800 videos parsed
11000 videos parsed
11200 videos parsed
11400 videos parsed
11600 videos parsed
11800 videos parsed
12000 videos parsed
12200 videos parsed
12400 videos parsed
12600 videos parsed
12800 videos parsed
13000 videos parsed
13200 videos parsed
frame folder analysis done
Setting device 0
WARNING: Logging before InitGoogleLogging() is written to STDERR
I1222 18:11:38.224102 3689 net.cpp:46] Initializing net from parameters:
name: "BN-Inception"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 224
input_dim: 224
state {
phase: TEST
}
layer {
name: "conv1/7x7_s2"
type: "Convolution"
bottom: "data"
top: "conv1/7x7_s2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 3
kernel_size: 7
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "conv1/7x7_s2_bn"
type: "BN"
bottom: "conv1/7x7_s2"
top: "conv1/7x7_s2_bn"
param {
lr_mult: 1
decay_mult: 0
}
param {
lr_mult: 1
decay_mult: 0
}
bn_param {
slope_filler {
type: "constant"
value: 1
}
bias_filler {
type: "constant"
value: 0
}
frozen: true
}
}
layer {
name: "conv1/relu_7x7"
type: "ReLU"
bottom: "conv1/7x7_s2_bn"
top: "conv1/7x7_s2_bn"
}
layer {
name: "pool1/3x3_s2"
type: "Pooling"
bottom: "conv1/7x7_s2_bn"
top: "pool1/3x3_s2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2/3x3_reduce"
type: "Convolution"
bottom: "pool1/3x3_s2"
top: "conv2/3x3_reduce"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "conv2/3x3_reduce_bn"
type: "BN"
bottom: "conv2/3x3_reduce"
top: "conv2/3x3_reduce_bn"
param {
lr_mult: 1
decay_mult: 0
}
param {
lr_mult: 1
decay_mult: 0
}
bn_param {
slope_filler {
type: "constant"
value: 1
}
bias_filler {
type: "constant"
value: 0
}
frozen: true
}
}
layer {
name: "conv2/relu_3x3_reduce"
type: "ReLU"
bottom: "conv2/3x3_reduce_bn"
top: "conv2/3x3_reduce_bn"
}
layer {
name: "conv2/3x3"
type: "Convolution"
bottom: "conv2/3x3_reduce_bn"
top: "conv2/3x3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 192
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "conv2/3x3_bn"
type: "BN"
bottom: "conv2/3x3"
top: "conv2/3x3_bn"
param {
lr_mult: 1
decay_mult: 0
}
param {
lr_mult: 1
decay_mult: 0
}
bn_param {
slope_filler {
type: "constant"
value: 1
}
bias_filler {
type: "constant"
value: 0
}
frozen: true
}
}
layer {
name: "conv2/relu_3x3"
type: "ReLU"
bottom: "conv2/3x3_bn"
top: "conv2/3x3_bn"
}
layer {
name: "pool2/3x3_s2"
type: "Pooling"
bottom: "conv2/3x3_bn"
top: "pool2/3x3_s2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "inception_3a/1x1"
type: "Convolution"
bottom: "pool2/3x3_s2"
top: "inception_3a/1x1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "inception_3a/1x1_bn"
type: "BN"
bottom: "inception_3a/1x1"
top: "inception_3a/1x1_bn"
param {
lr_mult: 1
decay_mult: 0
}
param {
lr_mult: 1
decay_mult: 0
}
bn_param {
slope_filler {
type: "constant"
value: 1
}
bias_filler {
type: "constant"
value: 0
}
frozen: true
}
}
layer {
name: "inception_3a/relu_1x1"
type: "ReLU"
bottom: "inception_3a/1x1_bn"
top: "inception_3a/1x1_bn"
}
layer {
name: "inception_3a/3x3_reduce"
type: "Convolution"
bottom: "pool2/3x3_s2"
top: "inception_3a/3x3_reduce"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "inception_3a/3x3_reduce_bn"
type: "BN"
bottom: "inception_3a/3x3_reduce"
top: "inception_3a/3x3_reduce_bn"
param {
lr_mult: 1
decay_mult: 0
}
...
...
I1222 18:11:41.756407 3689 net.cpp:531] Collecting Learning Rate and Weight Decay.
I1222 18:11:41.756465 3689 net.cpp:294] Network initialization done.
I1222 18:11:41.756479 3689 net.cpp:295] Memory required for data: 74005652
段错误 (核心已转储)

非常奇怪，我装好之后，无论--num_worker 1 或者 2 ,一直提示这样的错误，但是，我期间有两次竟然成功的运行了，我并没有改动任何地方

[yjxiong]

In this case, it is probably related to your environments, like library versions and packages installed.

[wxw420]

训练网络时，用rgb输入时可以训练；用flow时又会报错…我需要重新配置一下所有库吗……

[wxw420]

非常感谢，我已经找到问题了，我拷贝的cv2.so出了问题，调整后可以正常运行了。再一次，非常感谢您分享代码

[yjxiong]

Closing this. Please feel free to reopen it if you meet any further problem.