@fabiocarrara
Hi, I try to run the "main.py" under GPU. And I already change the directory to Caffe. But here is a question when I try to run "python main.py":
INFO 2020-05-10 23:47:01: Setting up mAlexNet trained on PKLot_train, validated on PKLot_val, CNRPark-EXT_val, tested on PKLot_test_CNRPark-EXT_test ...
INFO 2020-05-10 23:47:02: Training on PKLot_train while validating on PKLot_val, CNRPark-EXT_val ...
caffe: command line brew
usage: caffe
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
'-gpu all' to run on all available GPUs. The effective training batch
size is multiplied by the number of devices.) type: string default: ""
-iterations (The number of iterations to run.) type: int32 default: 50
-level (Optional; network level.) type: int32 default: 0
-model (The model definition protocol buffer text file.) type: string
default: ""
-phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
type: string default: ""
-sighup_effect (Optional; action to take when a SIGHUP signal is received:
snapshot, stop or none.) type: string default: "snapshot"
-sigint_effect (Optional; action to take when a SIGINT signal is received:
snapshot, stop or none.) type: string default: "stop"
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-stage (Optional; network stages (not to be confused with phase), separated
by ','.) type: string default: ""
-weights (Optional; the pretrained weights to initialize finetuning,
separated by ','. Cannot be set simultaneously with snapshot.)
type: string default: ""
INFO 2020-05-10 23:47:02: Setting up AlexNet trained on PKLot_train, validated on PKLot_val, CNRPark-EXT_val, tested on PKLot_test_CNRPark-EXT_test ...
INFO 2020-05-10 23:47:03: Training on PKLot_train while validating on PKLot_val, CNRPark-EXT_val ...
caffe: command line brew
usage: caffe
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
'-gpu all' to run on all available GPUs. The effective training batch
size is multiplied by the number of devices.) type: string default: ""
-iterations (The number of iterations to run.) type: int32 default: 50
-level (Optional; network level.) type: int32 default: 0
-model (The model definition protocol buffer text file.) type: string
default: ""
-phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
type: string default: ""
-sighup_effect (Optional; action to take when a SIGHUP signal is received:
snapshot, stop or none.) type: string default: "snapshot"
-sigint_effect (Optional; action to take when a SIGINT signal is received:
snapshot, stop or none.) type: string default: "stop"
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-stage (Optional; network stages (not to be confused with phase), separated
by ','.) type: string default: ""
-weights (Optional; the pretrained weights to initialize finetuning,
separated by ','. Cannot be set simultaneously with snapshot.)
type: string default: ""
INFO 2020-05-10 23:47:03: Setting up mAlexNet trained on CNRParkAB_all, validated on CNRPark-EXT_val, PKLot_val, tested on CNRPark-EXT_test_PKLot_test ...
INFO 2020-05-10 23:47:04: Training on CNRParkAB_all while validating on CNRPark-EXT_val, PKLot_val ...
caffe: command line brew
usage: caffe
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
'-gpu all' to run on all available GPUs. The effective training batch
size is multiplied by the number of devices.) type: string default: ""
-iterations (The number of iterations to run.) type: int32 default: 50
-level (Optional; network level.) type: int32 default: 0
-model (The model definition protocol buffer text file.) type: string
default: ""
-phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
type: string default: ""
-sighup_effect (Optional; action to take when a SIGHUP signal is received:
snapshot, stop or none.) type: string default: "snapshot"
-sigint_effect (Optional; action to take when a SIGINT signal is received:
snapshot, stop or none.) type: string default: "stop"
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-stage (Optional; network stages (not to be confused with phase), separated
by ','.) type: string default: ""
-weights (Optional; the pretrained weights to initialize finetuning,
separated by ','. Cannot be set simultaneously with snapshot.)
type: string default: ""
INFO 2020-05-10 23:47:04: Setting up AlexNet trained on CNRParkAB_all, validated on CNRPark-EXT_val, PKLot_val, tested on CNRPark-EXT_test_PKLot_test ...
INFO 2020-05-10 23:47:05: Training on CNRParkAB_all while validating on CNRPark-EXT_val, PKLot_val ...
caffe: command line brew
usage: caffe
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
'-gpu all' to run on all available GPUs. The effective training batch
size is multiplied by the number of devices.) type: string default: ""
-iterations (The number of iterations to run.) type: int32 default: 50
-level (Optional; network level.) type: int32 default: 0
-model (The model definition protocol buffer text file.) type: string
default: ""
-phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
type: string default: ""
-sighup_effect (Optional; action to take when a SIGHUP signal is received:
snapshot, stop or none.) type: string default: "snapshot"
-sigint_effect (Optional; action to take when a SIGINT signal is received:
snapshot, stop or none.) type: string default: "stop"
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-stage (Optional; network stages (not to be confused with phase), separated
by ','.) type: string default: ""
-weights (Optional; the pretrained weights to initialize finetuning,
separated by ','. Cannot be set simultaneously with snapshot.)
type: string default: ""
INFO 2020-05-10 23:47:05: Setting up mAlexNet trained on Combined_CNRParkAB_Ext_train, validated on CNRPark-EXT_val, PKLot_val, tested on CNRPark-EXT_test_PKLot_test ...
INFO 2020-05-10 23:47:07: Training on Combined_CNRParkAB_Ext_train while validating on CNRPark-EXT_val, PKLot_val ...
caffe: command line brew
usage: caffe
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
'-gpu all' to run on all available GPUs. The effective training batch
size is multiplied by the number of devices.) type: string default: ""
-iterations (The number of iterations to run.) type: int32 default: 50
-level (Optional; network level.) type: int32 default: 0
-model (The model definition protocol buffer text file.) type: string
default: ""
-phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
type: string default: ""
-sighup_effect (Optional; action to take when a SIGHUP signal is received:
snapshot, stop or none.) type: string default: "snapshot"
-sigint_effect (Optional; action to take when a SIGINT signal is received:
snapshot, stop or none.) type: string default: "stop"
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-stage (Optional; network stages (not to be confused with phase), separated
by ','.) type: string default: ""
-weights (Optional; the pretrained weights to initialize finetuning,
separated by ','. Cannot be set simultaneously with snapshot.)
type: string default: ""
INFO 2020-05-10 23:47:07: Setting up AlexNet trained on Combined_CNRParkAB_Ext_train, validated on CNRPark-EXT_val, PKLot_val, tested on CNRPark-EXT_test_PKLot_test ...
INFO 2020-05-10 23:47:08: Training on Combined_CNRParkAB_Ext_train while validating on CNRPark-EXT_val, PKLot_val ...
caffe: command line brew
usage: caffe
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
'-gpu all' to run on all available GPUs. The effective training batch
size is multiplied by the number of devices.) type: string default: ""
-iterations (The number of iterations to run.) type: int32 default: 50
-level (Optional; network level.) type: int32 default: 0
-model (The model definition protocol buffer text file.) type: string
default: ""
-phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
type: string default: ""
-sighup_effect (Optional; action to take when a SIGHUP signal is received:
snapshot, stop or none.) type: string default: "snapshot"
-sigint_effect (Optional; action to take when a SIGINT signal is received:
snapshot, stop or none.) type: string default: "stop"
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-stage (Optional; network stages (not to be confused with phase), separated
by ','.) type: string default: ""
-weights (Optional; the pretrained weights to initialize finetuning,
separated by ','. Cannot be set simultaneously with snapshot.)
type: string default: ""
INFO 2020-05-10 23:47:08: Setting up mAlexNet trained on Combined_CNRParkAB_Ext_train_C1C8, validated on CNRPark-EXT_val, PKLot_val, tested on CNRPark-EXT_test_PKLot_test ...
INFO 2020-05-10 23:47:09: Training on Combined_CNRParkAB_Ext_train_C1C8 while validating on CNRPark-EXT_val, PKLot_val ...
caffe: command line brew
usage: caffe
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
'-gpu all' to run on all available GPUs. The effective training batch
size is multiplied by the number of devices.) type: string default: ""
-iterations (The number of iterations to run.) type: int32 default: 50
-level (Optional; network level.) type: int32 default: 0
-model (The model definition protocol buffer text file.) type: string
default: ""
-phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
type: string default: ""
-sighup_effect (Optional; action to take when a SIGHUP signal is received:
snapshot, stop or none.) type: string default: "snapshot"
-sigint_effect (Optional; action to take when a SIGINT signal is received:
snapshot, stop or none.) type: string default: "stop"
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-stage (Optional; network stages (not to be confused with phase), separated
by ','.) type: string default: ""
-weights (Optional; the pretrained weights to initialize finetuning,
separated by ','. Cannot be set simultaneously with snapshot.)
type: string default: ""
INFO 2020-05-10 23:47:09: Setting up AlexNet trained on Combined_CNRParkAB_Ext_train_C1C8, validated on CNRPark-EXT_val, PKLot_val, tested on CNRPark-EXT_test_PKLot_test ...
INFO 2020-05-10 23:47:10: Training on Combined_CNRParkAB_Ext_train_C1C8 while validating on CNRPark-EXT_val, PKLot_val ...
caffe: command line brew
usage: caffe
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
'-gpu all' to run on all available GPUs. The effective training batch
size is multiplied by the number of devices.) type: string default: ""
-iterations (The number of iterations to run.) type: int32 default: 50
-level (Optional; network level.) type: int32 default: 0
-model (The model definition protocol buffer text file.) type: string
default: ""
-phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
type: string default: ""
-sighup_effect (Optional; action to take when a SIGHUP signal is received:
snapshot, stop or none.) type: string default: "snapshot"
-sigint_effect (Optional; action to take when a SIGINT signal is received:
snapshot, stop or none.) type: string default: "stop"
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-stage (Optional; network stages (not to be confused with phase), separated
by ','.) type: string default: ""
-weights (Optional; the pretrained weights to initialize finetuning,
separated by ','. Cannot be set simultaneously with snapshot.)
type: string default: ""
INFO 2020-05-10 23:47:10: Setting up mAlexNet trained on CNRPark-EXT_sunny, validated on CNRPark-EXT_overcast, CNRPark-EXT_rainy, PKLot_val, tested on CNRPark-EXT_overcast_CNRPark-EXT_rainy_PKLot_test ...
INFO 2020-05-10 23:47:11: Training on CNRPark-EXT_sunny while validating on CNRPark-EXT_overcast, CNRPark-EXT_rainy, PKLot_val ...
caffe: command line brew
usage: caffe
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
'-gpu all' to run on all available GPUs. The effective training batch
size is multiplied by the number of devices.) type: string default: ""
-iterations (The number of iterations to run.) type: int32 default: 50
-level (Optional; network level.) type: int32 default: 0
-model (The model definition protocol buffer text file.) type: string
default: ""
-phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
type: string default: ""
-sighup_effect (Optional; action to take when a SIGHUP signal is received:
snapshot, stop or none.) type: string default: "snapshot"
-sigint_effect (Optional; action to take when a SIGINT signal is received:
snapshot, stop or none.) type: string default: "stop"
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-stage (Optional; network stages (not to be confused with phase), separated
by ','.) type: string default: ""
-weights (Optional; the pretrained weights to initialize finetuning,
separated by ','. Cannot be set simultaneously with snapshot.)
type: string default: ""
INFO 2020-05-10 23:47:11: Setting up mAlexNet trained on CNRPark-EXT_overcast, validated on CNRPark-EXT_sunny, CNRPark-EXT_rainy, PKLot_val, tested on CNRPark-EXT_sunny_CNRPark-EXT_rainy_PKLot_test ...
INFO 2020-05-10 23:47:12: Training on CNRPark-EXT_overcast while validating on CNRPark-EXT_sunny, CNRPark-EXT_rainy, PKLot_val ...
caffe: command line brew
usage: caffe
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
'-gpu all' to run on all available GPUs. The effective training batch
size is multiplied by the number of devices.) type: string default: ""
-iterations (The number of iterations to run.) type: int32 default: 50
-level (Optional; network level.) type: int32 default: 0
-model (The model definition protocol buffer text file.) type: string
default: ""
-phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
type: string default: ""
-sighup_effect (Optional; action to take when a SIGHUP signal is received:
snapshot, stop or none.) type: string default: "snapshot"
-sigint_effect (Optional; action to take when a SIGINT signal is received:
snapshot, stop or none.) type: string default: "stop"
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-stage (Optional; network stages (not to be confused with phase), separated
by ','.) type: string default: ""
-weights (Optional; the pretrained weights to initialize finetuning,
separated by ','. Cannot be set simultaneously with snapshot.)
type: string default: ""
INFO 2020-05-10 23:47:12: Setting up mAlexNet trained on CNRPark-EXT_rainy, validated on CNRPark-EXT_sunny, CNRPark-EXT_overcast, PKLot_val, tested on CNRPark-EXT_sunny_CNRPark-EXT_overcast_PKLot_test ...
INFO 2020-05-10 23:47:13: Training on CNRPark-EXT_rainy while validating on CNRPark-EXT_sunny, CNRPark-EXT_overcast, PKLot_val ...
caffe: command line brew
usage: caffe
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
'-gpu all' to run on all available GPUs. The effective training batch
size is multiplied by the number of devices.) type: string default: ""
-iterations (The number of iterations to run.) type: int32 default: 50
-level (Optional; network level.) type: int32 default: 0
-model (The model definition protocol buffer text file.) type: string
default: ""
-phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
type: string default: ""
-sighup_effect (Optional; action to take when a SIGHUP signal is received:
snapshot, stop or none.) type: string default: "snapshot"
-sigint_effect (Optional; action to take when a SIGINT signal is received:
snapshot, stop or none.) type: string default: "stop"
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-stage (Optional; network stages (not to be confused with phase), separated
by ','.) type: string default: ""
-weights (Optional; the pretrained weights to initialize finetuning,
separated by ','. Cannot be set simultaneously with snapshot.)
type: string default: ""
INFO 2020-05-10 23:47:13: Setting up mAlexNet trained on CNRPark-EXT_camera8, validated on CNRPark-EXT_camera1, CNRPark-EXT_camera2, CNRPark-EXT_camera3, CNRPark-EXT_camera4, CNRPark-EXT_camera5, CNRPark-EXT_camera6, CNRPark-EXT_camera7, PKLot_val, CNRPark-EXT_camera9, tested on CNRPark-EXT_camera1_CNRPark-EXT_camera2_CNRPark-EXT_camera3_CNRPark-EXT_camera4_CNRPark-EXT_camera5_CNRPark-EXT_camera6_CNRPark-EXT_camera7_PKLot_test_CNRPark-EXT_camera9 ...
INFO 2020-05-10 23:47:14: Training on CNRPark-EXT_camera8 while validating on CNRPark-EXT_camera1, CNRPark-EXT_camera2, CNRPark-EXT_camera3, CNRPark-EXT_camera4, CNRPark-EXT_camera5, CNRPark-EXT_camera6, CNRPark-EXT_camera7, PKLot_val, CNRPark-EXT_camera9 ...
caffe: command line brew
usage: caffe
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
'-gpu all' to run on all available GPUs. The effective training batch
size is multiplied by the number of devices.) type: string default: ""
-iterations (The number of iterations to run.) type: int32 default: 50
-level (Optional; network level.) type: int32 default: 0
-model (The model definition protocol buffer text file.) type: string
default: ""
-phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
type: string default: ""
-sighup_effect (Optional; action to take when a SIGHUP signal is received:
snapshot, stop or none.) type: string default: "snapshot"
-sigint_effect (Optional; action to take when a SIGINT signal is received:
snapshot, stop or none.) type: string default: "stop"
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-stage (Optional; network stages (not to be confused with phase), separated
by ','.) type: string default: ""
-weights (Optional; the pretrained weights to initialize finetuning,
separated by ','. Cannot be set simultaneously with snapshot.)
type: string default: ""
INFO 2020-05-10 23:47:15: Setting up mAlexNet trained on CNRPark-EXT_camera1, validated on PKLot_val, CNRPark-EXT_camera2, CNRPark-EXT_camera3, CNRPark-EXT_camera4, CNRPark-EXT_camera5, CNRPark-EXT_camera6, CNRPark-EXT_camera7, CNRPark-EXT_camera8, CNRPark-EXT_camera9, tested on PKLot_test_CNRPark-EXT_camera2_CNRPark-EXT_camera3_CNRPark-EXT_camera4_CNRPark-EXT_camera5_CNRPark-EXT_camera6_CNRPark-EXT_camera7_CNRPark-EXT_camera8_CNRPark-EXT_camera9 ...
INFO 2020-05-10 23:47:16: Training on CNRPark-EXT_camera1 while validating on PKLot_val, CNRPark-EXT_camera2, CNRPark-EXT_camera3, CNRPark-EXT_camera4, CNRPark-EXT_camera5, CNRPark-EXT_camera6, CNRPark-EXT_camera7, CNRPark-EXT_camera8, CNRPark-EXT_camera9 ...
caffe: command line brew
usage: caffe
commands:
train train or finetune a model
test score a model
device_query show GPU diagnostic information
time benchmark model execution time
Flags from tools/caffe.cpp:
-gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
'-gpu all' to run on all available GPUs. The effective training batch
size is multiplied by the number of devices.) type: string default: ""
-iterations (The number of iterations to run.) type: int32 default: 50
-level (Optional; network level.) type: int32 default: 0
-model (The model definition protocol buffer text file.) type: string
default: ""
-phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
type: string default: ""
-sighup_effect (Optional; action to take when a SIGHUP signal is received:
snapshot, stop or none.) type: string default: "snapshot"
-sigint_effect (Optional; action to take when a SIGINT signal is received:
snapshot, stop or none.) type: string default: "stop"
-snapshot (Optional; the snapshot solver state to resume training.)
type: string default: ""
-solver (The solver definition protocol buffer text file.) type: string
default: ""
-stage (Optional; network stages (not to be confused with phase), separated
by ','.) type: string default: ""
-weights (Optional; the pretrained weights to initialize finetuning,
separated by ','. Cannot be set simultaneously with snapshot.)
type: string default: ""
DEBUG 2020-05-10 23:47:16: Summarizing mAlexNet-tr_PKLot_train-vl_PKLot_val_CNRPark-EXT_val-ts_PKLot_test_CNRPark-EXT_test ...
Traceback (most recent call last):
File "main.py", line 100, in
pyffe.summarize(exps).to_csv('results.csv')
File "/home/hao/deep-parking/pyffe/experiment.py", line 84, in summarize
r = e.summarize()
File "/home/hao/deep-parking/pyffe/experiment.py", line 42, in decorator
return function(*args, **kwargs)
File "/home/hao/deep-parking/pyffe/experiment.py", line 548, in summarize
last_iter = log_data['train']['iteration'][-1]
IndexError: list index out of range
Could you help me?