Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

I Can't get the results of the paper which report on the kth action task #9

Closed
demeiyan opened this issue Dec 22, 2019 · 5 comments
Closed

I Can't get the results of the paper which report on the kth action task #9

demeiyan opened this issue Dec 22, 2019 · 5 comments

Comments

@demeiyan
Copy link

demeiyan commented Dec 22, 2019 •
edited
Loading

Hi yunbo,
I'm very sorry for interrupting you.

I run the test on the kth action dataset according to your script, but the results I get are very different from those in your paper.

Maybe it's my parameters or I am not running it the right way?

Below is my running command.

python -u run.py \
    --is_training False\
    --dataset_name action \
    --train_data_paths ~/codes/e3d_lstm/data/kth_action \
    --valid_data_paths ~/codes/e3d_lstm/data/kth_action \
    --pretrained_model pretrain_model/kth_e3d_lstm_pretrain/model.ckpt-200000 \
    --save_dir checkpoints/_kth_e3d_lstm \
    --gen_frm_dir results/_kth_e3d_lstm \
    --model_name e3d_lstm \
    --allow_gpu_growth True \
    --img_channel 1 \
    --img_width 128 \
    --input_length 10 \
    --total_length 30 \
    --filter_size 5 \
    --num_hidden 64,64,64,64 \
    --patch_size 8 \
    --layer_norm True \
    --reverse_input False \
    --sampling_stop_iter 100000 \
    --sampling_start_value 1.0 \
    --sampling_delta_per_iter 0.00001 \
    --lr 0.001 \
    --n_gpu 1 \
    --batch_size 2 \
    --max_iterations 1 \
    --display_interval 1 \
    --test_interval 1 \
    --snapshot_interval 5000

Below is my running log.

WARNING:tensorflow:From run.py:186: The name tf.app.run is deprecated. Please use tf.compat.v1.app.run instead.

WARNING:tensorflow:From run.py:77: The name tf.gfile.Exists is deprecated. Please use tf.io.gfile.exists instead.

W1222 21:52:35.771336 140271583331904 deprecation_wrapper.py:119] From run.py:77: The name tf.gfile.Exists is deprecated. Please use tf.io.gfile.exists instead.

WARNING:tensorflow:From run.py:78: The name tf.gfile.DeleteRecursively is deprecated. Please use tf.io.gfile.rmtree instead.

W1222 21:52:35.771526 140271583331904 deprecation_wrapper.py:119] From run.py:78: The name tf.gfile.DeleteRecursively is deprecated. Please use tf.io.gfile.rmtree instead.

WARNING:tensorflow:From run.py:79: The name tf.gfile.MakeDirs is deprecated. Please use tf.io.gfile.makedirs instead.

W1222 21:52:35.771702 140271583331904 deprecation_wrapper.py:119] From run.py:79: The name tf.gfile.MakeDirs is deprecated. Please use tf.io.gfile.makedirs instead.

Initializing models
WARNING:tensorflow:From /home/dmyan/codes/e3d_lstm/src/models/model_factory.py:65: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.

W1222 21:52:35.778021 140271583331904 deprecation_wrapper.py:119] From /home/dmyan/codes/e3d_lstm/src/models/model_factory.py:65: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.

WARNING:tensorflow:From /home/dmyan/codes/e3d_lstm/src/models/model_factory.py:87: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.

W1222 21:52:35.780277 140271583331904 deprecation_wrapper.py:119] From /home/dmyan/codes/e3d_lstm/src/models/model_factory.py:87: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.

WARNING:tensorflow:From /home/dmyan/codes/e3d_lstm/src/models/model_factory.py:88: The name tf.get_variable_scope is deprecated. Please use tf.compat.v1.get_variable_scope instead.

W1222 21:52:35.780394 140271583331904 deprecation_wrapper.py:119] From /home/dmyan/codes/e3d_lstm/src/models/model_factory.py:88: The name tf.get_variable_scope is deprecated. Please use tf.compat.v1.get_variable_scope instead.

WARNING:tensorflow:From /home/dmyan/codes/e3d_lstm/src/layers/rnn_cell.py:168: conv3d (from tensorflow.python.layers.convolutional) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.keras.layers.Conv3D` instead.
W1222 21:52:35.789141 140271583331904 deprecation.py:323] From /home/dmyan/codes/e3d_lstm/src/layers/rnn_cell.py:168: conv3d (from tensorflow.python.layers.convolutional) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.keras.layers.Conv3D` instead.
WARNING:tensorflow:From /home/dmyan/.conda/envs/py_27/lib/python2.7/site-packages/tensorflow/python/ops/init_ops.py:1251: calling __init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
W1222 21:52:35.791179 140271583331904 deprecation.py:506] From /home/dmyan/.conda/envs/py_27/lib/python2.7/site-packages/tensorflow/python/ops/init_ops.py:1251: calling __init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
WARNING:tensorflow:From /home/dmyan/codes/e3d_lstm/src/layers/rnn_cell.py:96: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.

W1222 21:52:35.942549 140271583331904 deprecation_wrapper.py:119] From /home/dmyan/codes/e3d_lstm/src/layers/rnn_cell.py:96: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.

WARNING:tensorflow:From /home/dmyan/codes/e3d_lstm/src/models/model_factory.py:97: The name tf.trainable_variables is deprecated. Please use tf.compat.v1.trainable_variables instead.

W1222 21:52:44.186022 140271583331904 deprecation_wrapper.py:119] From /home/dmyan/codes/e3d_lstm/src/models/model_factory.py:97: The name tf.trainable_variables is deprecated. Please use tf.compat.v1.trainable_variables instead.

WARNING:tensorflow:From /home/dmyan/.conda/envs/py_27/lib/python2.7/site-packages/tensorflow/python/training/moving_averages.py:433: initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts.
W1222 21:53:13.805632 140271583331904 deprecation.py:323] From /home/dmyan/.conda/envs/py_27/lib/python2.7/site-packages/tensorflow/python/training/moving_averages.py:433: initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts.
WARNING:tensorflow:From /home/dmyan/codes/e3d_lstm/src/models/model_factory.py:122: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.

W1222 21:53:16.815418 140271583331904 deprecation_wrapper.py:119] From /home/dmyan/codes/e3d_lstm/src/models/model_factory.py:122: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.

2019-12-22 21:53:17.006586: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 AVX512F FMA
2019-12-22 21:53:17.031369: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 3800000000 Hz
2019-12-22 21:53:17.032462: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x563521ce8aa0 executing computations on platform Host. Devices:
2019-12-22 21:53:17.032494: I tensorflow/compiler/xla/service/service.cc:175]   StreamExecutor device (0): <undefined>, <undefined>
2019-12-22 21:53:17.033555: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcuda.so.1
2019-12-22 21:53:17.048990: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties: 
name: TITAN RTX major: 7 minor: 5 memoryClockRate(GHz): 1.77
pciBusID: 0000:1d:00.0
2019-12-22 21:53:17.049160: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0
2019-12-22 21:53:17.050196: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0
2019-12-22 21:53:17.051319: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcufft.so.10.0
2019-12-22 21:53:17.051549: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcurand.so.10.0
2019-12-22 21:53:17.052788: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusolver.so.10.0
2019-12-22 21:53:17.053794: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusparse.so.10.0
2019-12-22 21:53:17.056837: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7
2019-12-22 21:53:17.059303: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0
2019-12-22 21:53:17.059342: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0
2019-12-22 21:53:17.158900: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1181] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-12-22 21:53:17.158936: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1187]      0 
2019-12-22 21:53:17.158945: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 0:   N 
2019-12-22 21:53:17.162652: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 22845 MB memory) -> physical GPU (device: 0, name: TITAN RTX, pci bus id: 0000:1d:00.0, compute capability: 7.5)
2019-12-22 21:53:17.164135: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x563544d5aca0 executing computations on platform CUDA. Devices:
2019-12-22 21:53:17.164153: I tensorflow/compiler/xla/service/service.cc:175]   StreamExecutor device (0): TITAN RTX, Compute Capability 7.5
WARNING:tensorflow:From /home/dmyan/.conda/envs/py_27/lib/python2.7/site-packages/tensorflow/python/training/saver.py:1276: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
W1222 21:53:20.888210 140271583331904 deprecation.py:323] From /home/dmyan/.conda/envs/py_27/lib/python2.7/site-packages/tensorflow/python/training/saver.py:1276: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
INFO:tensorflow:Restoring parameters from pretrain_model/kth_e3d_lstm_pretrain/model.ckpt-200000
I1222 21:53:20.888901 140271583331904 saver.py:1280] Restoring parameters from pretrain_model/kth_e3d_lstm_pretrain/model.ckpt-200000
load model: pretrain_model/kth_e3d_lstm_pretrain/model.ckpt-200000
INFO:tensorflow:Restoring parameters from pretrain_model/kth_e3d_lstm_pretrain/model.ckpt-200000
I1222 21:53:22.366884 140271583331904 saver.py:1280] Restoring parameters from pretrain_model/kth_e3d_lstm_pretrain/model.ckpt-200000
begin load data/home/dmyan/codes/e3d_lstm/data/kth_action
there are 127271 pictures
there are 5200 sequences
I1222 21:54:30.102876 140271583331904 kth_action.py:49] Initialization for read data 
begin load data/home/dmyan/codes/e3d_lstm/data/kth_action
there are 74833 pictures
there are 3167 sequences
I1222 21:55:07.155915 140271583331904 kth_action.py:49] Initialization for read data 
2019-12-22 21:56:00.419773: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7
2019-12-22 21:56:01.487206: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0
2019-12-22 21:56:03 itr: 1
training loss: 13579.5546875
2019-12-22 21:56:03 test...
I1222 21:56:03.320033 140271583331904 kth_action.py:49] Initialization for read data 
mse per seq: 1693.4428418943269
79.28188222763437
70.02298803082465
72.65927987692105
73.55713736220244
75.19940400018167
76.14778310711897
77.5233913718035
78.97197559522965
80.70456069493248
82.5432857120632
84.30587631678627
86.22168846636427
88.00625679994488
89.80391043435903
91.70583107828416
93.60850595991143
95.47444786365772
97.46097950263635
99.30191913828847
100.94173835518235
psnr per frame: 23.059969
23.26729
23.797897
23.652412
23.607574
23.519243
23.468027
23.394089
23.319853
23.23082
23.140533
23.055035
22.963602
22.880823
22.799498
22.714308
22.632303
22.553648
22.470747
22.396952
22.334736
@demeiyan demeiyan changed the title I Can't run the results of the paper which report on the kth action task I Can't get the results of the paper which report on the kth action task Dec 22, 2019
@toddwyl
Copy link

toddwyl commented Mar 2, 2020

I cannot get the result too.

2 similar comments
@xiaomingdujin
Copy link

I cannot get the result too.

@xiaomingdujin
Copy link

I cannot get the result too.

@xiaomingdujin
Copy link

Maybe I find the reason, in rnn_cell.py, when calculating the output_gate, new_ global_ memory should be returned, but the code returns global memory，which is not updated, but even if I return new_ global_ memory, the result is even worse, so I suspect there is a problem in the transmission of time information

@roadjiang
Copy link
Contributor

Duplicated issue. Please refer to for future discussions
#1

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@demeiyan @roadjiang @toddwyl @xiaomingdujin