search

andreariba / DeepCycle

Cell cycle inference in single-cell RNA-seq
https://www.nature.com/articles/s41467-022-30545-8
GNU General Public License v3.0
38 stars 7 forks source link

Error in rerun DeepCycle.py on the mESC dataset #12

Closed bhyu0217 closed 1 year ago

bhyu0217 commented 1 year ago

Dear @andreariba, Thank you for developing a fascinating tool.

When I executed DeepCycle.py with the mESC data on the conda environment, I got this error:

2023-02-15 05:21:08.109312: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 3: N N Y N 2023-02-15 05:21:08.116922: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 11326 MB memory) -> physical GPU (device: 0, name: TITAN Xp, pci bus id: 0000:02:00.0, compute capability: 6.1) 2023-02-15 05:21:08.119515: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:1 with 11326 MB memory) -> physical GPU (device: 1, name: TITAN Xp, pci bus id: 0000:04:00.0, compute capability: 6.1) 2023-02-15 05:21:08.121884: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:2 with 11326 MB memory) -> physical GPU (device: 2, name: TITAN Xp, pci bus id: 0000:83:00.0, compute capability: 6.1) 2023-02-15 05:21:08.124222: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:3 with 11326 MB memory) -> physical GPU (device: 3, name: TITAN Xp, pci bus id: 0000:84:00.0, compute capability: 6.1) 2023-02-15 05:21:08.127325: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x56180aed31e0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2023-02-15 05:21:08.127360: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): TITAN Xp, Compute Capability 6.1 2023-02-15 05:21:08.127375: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (1): TITAN Xp, Compute Capability 6.1 2023-02-15 05:21:08.127399: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (2): TITAN Xp, Compute Capability 6.1 2023-02-15 05:21:08.127418: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (3): TITAN Xp, Compute Capability 6.1 Traceback (most recent call last): File "/home/hyun/DeepCycle/DeepCycle.py", line 418, in n_batches_to_validation = math.ceil(len(e_dataset)*fraction_of_cells_to_validation) TypeError: object of type 'BatchDataset' has no len()

Do you have any idea how I can fix this error? (I used the conda environment built with DeepCycle_env.yml file)

Thank you. Bohyeon

Hsu-Che-Wei commented 1 year ago

I also run into the exact same problem, is there any fix?

Thank you!

Best, Che-Wei

andreariba commented 1 year ago

Hi, i'm sorry but it looks you have some issue with the version of TF on your system but i cannot figure out why. since I'm not able to reproduce your error, I cannot help you

augustinas1 commented 1 year ago

It seems that I have introduced this bug in a PR fixing the training/validation split as I used a newer tensorflow version that did not give me any errors, my bad! I'm unable to install tensorflow 2.2, but could you try either changing the corresponding line 418 in DeepCycle.py to n_batches_to_validation = math.ceil(tf.data.experimental.cardinality(e_dataset).numpy() * fraction_of_cells_to_validation) or updating tensorflow to the most recent version?

Hsu-Che-Wei commented 1 year ago

Ok, I'll check it out. Thank you.

Augustinas Sukys @.***>於 2023年4月25日 週二，04:07寫道：

It seems that I have introduced this bug in a PR fixing the training/validation split as I used a newer tensorflow version that did not give me any errors, my bad! I'm unable to install tensorflow 2.2, but could you try either changing the corresponding line 418 in DeepCycle.py to n_batches_to_validation = math.ceil(tf.data.experimental.cardinality(e_dataset).numpy() * fraction_of_cells_to_validation) or updating tensorflow to the most recent version?

— Reply to this email directly, view it on GitHub https://github.com/andreariba/DeepCycle/issues/12#issuecomment-1520759810, or unsubscribe https://github.com/notifications/unsubscribe-auth/AKW2WXABLI37O2IVCRDM2E3XC3MO5ANCNFSM6AAAAAAU4VUD3A . You are receiving this because you commented.Message ID: @.***>