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

What is the cause for 'ValueError: Dimensions must be equal'? #19

Closed
richelbilderbeek opened this issue Nov 30, 2021 · 3 comments
Closed

What is the cause for 'ValueError: Dimensions must be equal'? #19

richelbilderbeek opened this issue Nov 30, 2021 · 3 comments

Comments

@richelbilderbeek
Copy link
Contributor

richelbilderbeek commented Nov 30, 2021 •
edited
Loading

Dear GenoCAE maintainers, hi @kausmees and @cnettel,

When I run the GenCAE experimental Pheno branch, I get an error of which I have no idea what to do with. Below the reprex.

Currently, the GitHub Actions script runs GenoCAE with the --help flag, showing the help successfully.

On my fork of GenoCAE in the GitHub Actions 'check.yaml' script, I added the following command to run:

python3 run_gcae.py train --datadir example_tiny --data issue_2_bin --model_id M1  --epochs 20 --save_interval 2  --train_opts_id ex3  --data_opts_id b_0_4 --pheno_model_id=p1

The --data issue_2_bin are the data files I supplied to Carl at this Issue and are already put in the example_tiny folder of my 'GenoCAE' fork.

GitHub Actions gives the following error:

ValueError: in user code:

    File "/home/richel/GitHubs/GenoCAE/run_gcae.py", line 424, in run_optimization  *
        loss_value += tf.math.reduce_sum(((-y_pred) * y_true)) * 1e-6

    ValueError: Dimensions must be equal, but are 2 and 4 for '{{node mul_21}} = Mul[T=DT_FLOAT](Neg_2, one_hot_2)' with input shapes: [2,4], [2,4,3].

Below is the full error log, which can also be found in this GitHub Actions log.

What does the error mean?

Thanks and cheers, Richel

Full error log

richel@N141CU:~/GitHubs/GenoCAE$ python3 run_gcae.py train --datadir example_tiny --data issue_2_bin --model_id M1  --epochs 20 --save_interval 2  --train_opts_id ex3  --data_opts_id b_0_4 --pheno_model_id=p1
2021-11-30 13:41:10.460286: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2021-11-30 13:41:10.460312: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2021-11-30 13:41:13.244831: E tensorflow/stream_executor/cuda/cuda_driver.cc:271] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected
2021-11-30 13:41:13.244903: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (N141CU): /proc/driver/nvidia/version does not exist
2021-11-30 13:41:13.245186: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
tensorflow version 2.7.0

______________________________ arguments ______________________________
train : True
datadir : example_tiny
data : issue_2_bin
model_id : M1
train_opts_id : ex3
data_opts_id : b_0_4
save_interval : 2
epochs : 20
resume_from : None
trainedmodeldir : None
pheno_model_id : p1
project : False
superpops : None
epoch : None
pdata : None
trainedmodelname : None
plot : False
animate : False
evaluate : False
metrics : None

______________________________ data opts ______________________________
sparsifies : [0.0, 0.1, 0.2, 0.3, 0.4]
norm_opts : {'flip': False, 'missing_val': -1.0}
norm_mode : genotypewise01
impute_missing : True
validation_split : 0.2

______________________________ train opts ______________________________
learning_rate : 0.00032
batch_size : 10
noise_std : 0.0032
n_samples : -1
loss : {'module': 'tf.keras.losses', 'class': 'CategoricalCrossentropy', 'args': {'from_logits': False}}
regularizer : {'reg_factor': 1e-07, 'module': 'tf.keras.regularizers', 'class': 'l2'}
lr_scheme : {'module': 'tf.keras.optimizers.schedules', 'class': 'ExponentialDecay', 'args': {'decay_rate': 0.96, 'decay_steps': 100, 'staircase': False}}
______________________________
Imputing originally missing genotypes to most common value.
Reading ind pop list from /home/richel/GitHubs/GenoCAE/example_tiny/issue_2_bin.fam
Reading ind pop list from /home/richel/GitHubs/GenoCAE/example_tiny/issue_2_bin.fam
Mapping files: 100%|███████████████████████████████████████████████████████████████| 3/3 [00:00<00:00, 362.20it/s]
Using learning rate schedule tf.keras.optimizers.schedules.ExponentialDecay with {'decay_rate': 0.96, 'decay_steps': 100, 'staircase': False}

______________________________ Data ______________________________
N unique train samples: 800
--- training on : 800
N valid samples: 200
N markers: 4


______________________________ Building model ______________________________
Adding layer: Conv1D: {'filters': 8, 'kernel_size': 5, 'padding': 'same', 'strides': 1}
Adding layer: BatchNormalization: {}
Adding layer: ResidualBlock2: {'filters': 8, 'kernel_size': 5}
--- conv1d  filters: 8 kernel_size: 5
--- batch normalization
--- conv1d  filters: 8 kernel_size: 5
--- batch normalization
Adding layer: MaxPooling1D: {'pool_size': 5, 'strides': 2, 'padding': 'same'}
Adding layer: Conv1D: {'filters': 8, 'kernel_size': 5, 'padding': 'same', 'activation': 'elu'}
Adding layer: BatchNormalization: {}
Adding layer: Flatten: {}
Adding layer: Dropout: {'rate': 0.01}
Adding layer: Dense: {'units': 75}
Adding layer: Dropout: {'rate': 0.01}
Adding layer: Dense: {'units': 75, 'activation': 'elu'}
Adding layer: Dense: {'units': 2, 'name': 'encoded'}
Adding layer: Dense: {'units': 75, 'activation': 'elu'}
Adding layer: Dropout: {'rate': 0.01}
Adding layer: Dense: {'units': 75, 'activation': 'elu'}
Adding layer: Dropout: {'rate': 0.01}
Adding layer: Dense: {'units': 16}
Adding layer: Reshape: {'target_shape': (2, 8), 'name': 'i_msvar'}
Adding layer: Conv1D: {'filters': 8, 'kernel_size': 5, 'padding': 'same', 'activation': 'elu'}
Adding layer: BatchNormalization: {}
Adding layer: Reshape: {'target_shape': (2, 1, 8)}
Adding layer: UpSampling2D: {'size': (2, 1)}
Adding layer: Reshape: {'target_shape': (4, 8)}
Adding layer: ResidualBlock2: {'filters': 8, 'kernel_size': 5}
--- conv1d  filters: 8 kernel_size: 5
--- batch normalization
--- conv1d  filters: 8 kernel_size: 5
--- batch normalization
Adding layer: Conv1D: {'filters': 8, 'kernel_size': 5, 'padding': 'same', 'activation': 'elu', 'name': 'nms'}
Adding layer: BatchNormalization: {}
Adding layer: Conv1D: {'filters': 1, 'kernel_size': 1, 'padding': 'same'}
Adding layer: Flatten: {'name': 'logits'}

______________________________ Building model ______________________________
Adding layer: Conv1D: {'filters': 8, 'kernel_size': 5, 'padding': 'same', 'strides': 1}
Adding layer: BatchNormalization: {}
Adding layer: ResidualBlock2: {'filters': 8, 'kernel_size': 5}
--- conv1d  filters: 8 kernel_size: 5
--- batch normalization
--- conv1d  filters: 8 kernel_size: 5
--- batch normalization
Adding layer: MaxPooling1D: {'pool_size': 5, 'strides': 2, 'padding': 'same'}
Adding layer: Conv1D: {'filters': 8, 'kernel_size': 5, 'padding': 'same'}
Adding layer: BatchNormalization: {}
Adding layer: Flatten: {}
Adding layer: Dropout: {'rate': 0.01}
Adding layer: Dense: {'units': 75}
Adding layer: Dropout: {'rate': 0.01}
Adding layer: Dense: {'units': 75}
Adding layer: Dense: {'units': 2, 'name': 'encoded'}
Adding layer: Dense: {'units': 75}
Adding layer: Dropout: {'rate': 0.01}
Adding layer: Dense: {'units': 75}
Adding layer: Dropout: {'rate': 0.01}
Adding layer: Dense: {'units': 16}
Adding layer: Reshape: {'target_shape': (2, 8), 'name': 'i_msvar'}
Adding layer: Conv1D: {'filters': 8, 'kernel_size': 5, 'padding': 'same'}
Adding layer: BatchNormalization: {}
Adding layer: Reshape: {'target_shape': (2, 1, 8)}
Adding layer: UpSampling2D: {'size': (2, 1)}
Adding layer: Reshape: {'target_shape': (4, 8)}
Adding layer: ResidualBlock2: {'filters': 8, 'kernel_size': 5}
--- conv1d  filters: 8 kernel_size: 5
--- batch normalization
--- conv1d  filters: 8 kernel_size: 5
--- batch normalization
Adding layer: Conv1D: {'filters': 8, 'kernel_size': 5, 'padding': 'same', 'name': 'nms'}
Adding layer: BatchNormalization: {}
Adding layer: Conv1D: {'filters': 1, 'kernel_size': 1, 'padding': 'same'}
Adding layer: Flatten: {'name': 'logits'}

______________________________ Building model ______________________________
Adding layer: Dense: {'units': 75}
Adding layer: LeakyReLU: {}
Adding layer: Dropout: {'rate': 0.01}
Adding layer: Dense: {'units': 75}
Adding layer: LeakyReLU: {}
Adding layer: Dense: {'units': 75}
Adding layer: LeakyReLU: {}
Adding layer: Dropout: {'rate': 0.01}
Adding layer: Dense: {'units': 75}
Adding layer: LeakyReLU: {}
Adding layer: Dense: {'units': 1}
No marker specific variable.
ALLVARS [<tf.Variable 'autoencoder/conv1d/kernel:0' shape=(5, 3, 8) dtype=float32>, <tf.Variable 'autoencoder/conv1d/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/batch_normalization/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/batch_normalization/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/residual_block2/conv1d_1/kernel:0' shape=(5, 8, 8) dtype=float32>, <tf.Variable 'autoencoder/residual_block2/conv1d_1/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/residual_block2/batch_normalization_1/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/residual_block2/batch_normalization_1/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/residual_block2/conv1d_2/kernel:0' shape=(5, 8, 8) dtype=float32>, <tf.Variable 'autoencoder/residual_block2/conv1d_2/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/residual_block2/batch_normalization_2/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/residual_block2/batch_normalization_2/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/conv1d_3/kernel:0' shape=(5, 8, 8) dtype=float32>, <tf.Variable 'autoencoder/conv1d_3/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/batch_normalization_3/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/batch_normalization_3/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/dense/kernel:0' shape=(16, 75) dtype=float32>, <tf.Variable 'autoencoder/dense/bias:0' shape=(75,) dtype=float32>, <tf.Variable 'autoencoder/dense_1/kernel:0' shape=(75, 75) dtype=float32>, <tf.Variable 'autoencoder/dense_1/bias:0' shape=(75,) dtype=float32>, <tf.Variable 'autoencoder/encoded/kernel:0' shape=(75, 2) dtype=float32>, <tf.Variable 'autoencoder/encoded/bias:0' shape=(2,) dtype=float32>, <tf.Variable 'autoencoder/dense_2/kernel:0' shape=(2, 75) dtype=float32>, <tf.Variable 'autoencoder/dense_2/bias:0' shape=(75,) dtype=float32>, <tf.Variable 'autoencoder/dense_3/kernel:0' shape=(75, 75) dtype=float32>, <tf.Variable 'autoencoder/dense_3/bias:0' shape=(75,) dtype=float32>, <tf.Variable 'autoencoder/dense_4/kernel:0' shape=(75, 16) dtype=float32>, <tf.Variable 'autoencoder/dense_4/bias:0' shape=(16,) dtype=float32>, <tf.Variable 'autoencoder/conv1d_4/kernel:0' shape=(5, 10, 8) dtype=float32>, <tf.Variable 'autoencoder/conv1d_4/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/batch_normalization_4/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/batch_normalization_4/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/residual_block2_1/conv1d_5/kernel:0' shape=(5, 8, 8) dtype=float32>, <tf.Variable 'autoencoder/residual_block2_1/conv1d_5/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/residual_block2_1/batch_normalization_5/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/residual_block2_1/batch_normalization_5/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/residual_block2_1/conv1d_6/kernel:0' shape=(5, 8, 8) dtype=float32>, <tf.Variable 'autoencoder/residual_block2_1/conv1d_6/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/residual_block2_1/batch_normalization_6/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/residual_block2_1/batch_normalization_6/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/nms/kernel:0' shape=(5, 8, 8) dtype=float32>, <tf.Variable 'autoencoder/nms/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder/batch_normalization_7/gamma:0' shape=(9,) dtype=float32>, <tf.Variable 'autoencoder/batch_normalization_7/beta:0' shape=(9,) dtype=float32>, <tf.Variable 'autoencoder/conv1d_7/kernel:0' shape=(1, 9, 1) dtype=float32>, <tf.Variable 'autoencoder/conv1d_7/bias:0' shape=(1,) dtype=float32>, <tf.Variable 'Variable:0' shape=(1, 4) dtype=float32>, <tf.Variable 'Variable:0' shape=(1, 4) dtype=float32>, <tf.Variable 'autoencoder_1/conv1d_8/kernel:0' shape=(5, 3, 8) dtype=float32>, <tf.Variable 'autoencoder_1/conv1d_8/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/batch_normalization_8/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/batch_normalization_8/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_2/conv1d_9/kernel:0' shape=(5, 8, 8) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_2/conv1d_9/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_2/batch_normalization_9/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_2/batch_normalization_9/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_2/conv1d_10/kernel:0' shape=(5, 8, 8) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_2/conv1d_10/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_2/batch_normalization_10/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_2/batch_normalization_10/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/conv1d_11/kernel:0' shape=(5, 8, 8) dtype=float32>, <tf.Variable 'autoencoder_1/conv1d_11/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/batch_normalization_11/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/batch_normalization_11/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/dense_5/kernel:0' shape=(16, 75) dtype=float32>, <tf.Variable 'autoencoder_1/dense_5/bias:0' shape=(75,) dtype=float32>, <tf.Variable 'autoencoder_1/dense_6/kernel:0' shape=(75, 75) dtype=float32>, <tf.Variable 'autoencoder_1/dense_6/bias:0' shape=(75,) dtype=float32>, <tf.Variable 'autoencoder_1/encoded/kernel:0' shape=(75, 2) dtype=float32>, <tf.Variable 'autoencoder_1/encoded/bias:0' shape=(2,) dtype=float32>, <tf.Variable 'autoencoder_1/dense_7/kernel:0' shape=(2, 75) dtype=float32>, <tf.Variable 'autoencoder_1/dense_7/bias:0' shape=(75,) dtype=float32>, <tf.Variable 'autoencoder_1/dense_8/kernel:0' shape=(75, 75) dtype=float32>, <tf.Variable 'autoencoder_1/dense_8/bias:0' shape=(75,) dtype=float32>, <tf.Variable 'autoencoder_1/dense_9/kernel:0' shape=(75, 16) dtype=float32>, <tf.Variable 'autoencoder_1/dense_9/bias:0' shape=(16,) dtype=float32>, <tf.Variable 'autoencoder_1/conv1d_12/kernel:0' shape=(5, 10, 8) dtype=float32>, <tf.Variable 'autoencoder_1/conv1d_12/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/batch_normalization_12/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/batch_normalization_12/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_3/conv1d_13/kernel:0' shape=(5, 8, 8) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_3/conv1d_13/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_3/batch_normalization_13/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_3/batch_normalization_13/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_3/conv1d_14/kernel:0' shape=(5, 8, 8) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_3/conv1d_14/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_3/batch_normalization_14/gamma:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/residual_block2_3/batch_normalization_14/beta:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/nms/kernel:0' shape=(5, 8, 8) dtype=float32>, <tf.Variable 'autoencoder_1/nms/bias:0' shape=(8,) dtype=float32>, <tf.Variable 'autoencoder_1/batch_normalization_15/gamma:0' shape=(9,) dtype=float32>, <tf.Variable 'autoencoder_1/batch_normalization_15/beta:0' shape=(9,) dtype=float32>, <tf.Variable 'autoencoder_1/conv1d_15/kernel:0' shape=(1, 9, 1) dtype=float32>, <tf.Variable 'autoencoder_1/conv1d_15/bias:0' shape=(1,) dtype=float32>, <tf.Variable 'Variable:0' shape=(1, 4) dtype=float32>, <tf.Variable 'Variable:0' shape=(1, 4) dtype=float32>, <tf.Variable 'autoencoder_2/dense_10/kernel:0' shape=(2, 75) dtype=float32>, <tf.Variable 'autoencoder_2/dense_10/bias:0' shape=(75,) dtype=float32>, <tf.Variable 'autoencoder_2/dense_11/kernel:0' shape=(75, 75) dtype=float32>, <tf.Variable 'autoencoder_2/dense_11/bias:0' shape=(75,) dtype=float32>, <tf.Variable 'autoencoder_2/dense_12/kernel:0' shape=(75, 75) dtype=float32>, <tf.Variable 'autoencoder_2/dense_12/bias:0' shape=(75,) dtype=float32>, <tf.Variable 'autoencoder_2/dense_13/kernel:0' shape=(75, 75) dtype=float32>, <tf.Variable 'autoencoder_2/dense_13/bias:0' shape=(75,) dtype=float32>, <tf.Variable 'autoencoder_2/dense_14/kernel:0' shape=(75, 1) dtype=float32>, <tf.Variable 'autoencoder_2/dense_14/bias:0' shape=(1,) dtype=float32>] ###
Traceback (most recent call last):
  File "/home/richel/GitHubs/GenoCAE/run_gcae.py", line 1616, in <module>
    main()
  File "/home/richel/GitHubs/GenoCAE/run_gcae.py", line 1014, in main
    run_optimization(autoencoder, autoencoder2, optimizer, optimizer2, loss_func, input_init, targets_init, True, phenomodel=pheno_model, phenotargets=phenotargets_init)
  File "/home/richel/miniconda3/lib/python3.9/site-packages/tensorflow/python/util/traceback_utils.py", line 153, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "/home/richel/miniconda3/lib/python3.9/site-packages/tensorflow/python/framework/func_graph.py", line 1129, in autograph_handler
    raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:

    File "/home/richel/GitHubs/GenoCAE/run_gcae.py", line 424, in run_optimization  *
        loss_value += tf.math.reduce_sum(((-y_pred) * y_true)) * 1e-6

    ValueError: Dimensions must be equal, but are 2 and 4 for '{{node mul_21}} = Mul[T=DT_FLOAT](Neg_2, one_hot_2)' with input shapes: [2,4], [2,4,3].
@cnettel
Copy link
Collaborator

cnettel commented Nov 30, 2021 via email

richelbilderbeek pushed a commit to richelbilderbeek/GenoCAE that referenced this issue Nov 30, 2021
Comment out lines, as suggested at kausmees#19 (comment)
021b91f
@richelbilderbeek
Copy link
Contributor Author

Thanks for the answer! I commented out the lines you mentioned. Let's see what the build does now :-)

@richelbilderbeek
Copy link
Contributor Author

It works! Thanks @cnettel !

This was referenced Dec 3, 2021
Closed
Closed
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
2 participants
@richelbilderbeek @cnettel