Replies: 2 comments 1 reply
-
|
Dear @nms6 this is likely due to a lack of pinning of numpy on our end. |
Beta Was this translation helpful? Give feedback.
-
|
Thank you so much for the prompt response! I really appreciate it! I have tried what was suggested and still could not get it :( Is there something I might be doing wrong? (decode_env) C:\WINDOWS\system32>conda list packages in environment at C:\ProgramData\anaconda3\envs\decode_env:Name Version Build Channelabsl-py 2.1.0 pyhd8ed1ab_0 conda-forge (decode_env) C:\WINDOWS\system32>conda install numpy=1.19.5
All requested packages already installed.(decode_env) C:\WINDOWS\system32>python -m decode.neuralfitter.train.live_engine -p C:\Users\LabUser\Desktop\DECODE\Model_2.2_um_range_High_Background\20240514_2.2umrangemode_diffbackground.yaml (decode_env) C:\WINDOWS\system32> |
Beta Was this translation helpful? Give feedback.
-
|
Sorry, I overlooked this. I guess this is no longer active. |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Hi,
I was able to use DECODE to train using the following param file yesterday:
Camera:
baseline: 477
e_per_adu: 4.4
em_gain: 200
px_size:
read_sigma: 47.7
spur_noise: 0.0
InOut:
calibration_file: C:\Users\LabUser\Desktop\DECODE\Model_2.2_um_range_High_Background\Calibration\Correct_3dcal.mat
experiment_out: C:\Users\LabUser\Desktop\DECODE\Model_2.2_um_range_High_Background
Simulation:
bg_uniform:
emitter_av: 25
emitter_extent:
intensity_mu_sig:
lifetime_avg: 1
Hardware:
device: cuda:0
device_simulation: cuda:0
num_worker_train: 0
torch_multiprocessing_sharing_strategy: null
torch_threads: 1
unix_niceness: 0
Connect:
remote_workstation: null
remote_decode_path: null
local_decode_path: null
When I try to fit the data today, the jupyter notebooks fit notebook just crashes at the "fit" cell.
I tried to train another model today, and keep getting the following error:
Cannot set niceness on platform win32. You probably do not need to worry.
Model instantiated.
Model initialised as specified in the constructor.
Sampled dataset in 0.56s. 249760 emitters on 10001 frames.
Sampled dataset in 0.03s. 13181 emitters on 513 frames.
C:\ProgramData\anaconda3\envs\decode_env\lib\site-packages\torch\functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\TensorShape.cpp:2895.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
(Test) E: 0 - T: 0.62: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:00<00:00, 12.19it/s]
Traceback (most recent call last):
File "C:\ProgramData\anaconda3\envs\decode_env\lib\runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\ProgramData\anaconda3\envs\decode_env\lib\runpy.py", line 87, in run_code
exec(code, run_globals)
File "C:\ProgramData\anaconda3\envs\decode_env\lib\site-packages\decode\neuralfitter\train\live_engine.py", line 491, in
live_engine_setup(args.param_file, args.device, args.debug, args.no_log,
File "C:\ProgramData\anaconda3\envs\decode_env\lib\site-packages\decode\neuralfitter\train\live_engine.py", line 239, in live_engine_setup
log_train_val_progress.post_process_log_test(loss_cmp=test_out.loss,
File "C:\ProgramData\anaconda3\envs\decode_env\lib\site-packages\decode\neuralfitter\utils\log_train_val_progress.py", line 161, in post_process_log_test
log_dists(tp=tp, tp_match=tp_match, pred=em_out, px_border=px_border, px_size=px_size, logger=logger, step=step)
File "C:\ProgramData\anaconda3\envs\decode_env\lib\site-packages\decode\neuralfitter\utils\log_train_val_progress.py", line 112, in log_dists
predict_dist.emitter_deviations(tp, tp_match,
File "C:\ProgramData\anaconda3\envs\decode_env\lib\site-packages\decode\evaluation\predict_dist.py", line 65, in emitter_deviations
sns.distplot(px_pointer_dist(tp.xyz_px[:, 0], px_border=px_border, px_size=px_size), norm_hist=True, ax=axes[0], bins=50)
File "C:\ProgramData\anaconda3\envs\decode_env\lib\site-packages\seaborn\distributions.py", line 177, in distplot
a = np.asarray(a, np.float)
File "C:\Users\LabUser\AppData\Roaming\Python\Python38\site-packages\numpy_init.py", line 305, in getattr
raise AttributeError(former_attrs[attr])
AttributeError: module 'numpy' has no attribute 'float'.
np.floatwas a deprecated alias for the builtinfloat. To avoid this error in existing code, usefloatby itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, usenp.float64here.The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at:
https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
Not sure what is going on as I was able to use it just fine yesterday to train? We have DECODE set up on another computer and it is still working just fine on that one as well. I also tried using decode_v0_10_1rc1 and I also could not get it to work.
Thanks so much for your help!
Beta Was this translation helpful? Give feedback.
All reactions