Comments (3)
Hi,
Can you tell us exactly the command line that you entered and the error message that you got it?
In the meanwhile try to verify the following items:
- You are running
clinicadl
with the most recent commit from the master branch of the repository. - Add the option
--use_extracted_patches
to your command line.
Thanks,
from clinicadl.
Hi,
Can you tell us exactly the command line that you entered and the error message that you got it?
In the meanwhile try to verify the following items:
- You are running
clinicadl
with the most recent commit from the master branch of the repository.- Add the option
--use_extracted_patches
to your command line.Thanks,
This is the command I entered:
clinicadl train patch cnn /home/geng/ADNI2/caps t1-linear /home/geng/ADNI2/tsv /home/geng/ADNI2/resault "Conv4_FC3" --batch_size 12 --evaluation_steps 20 --diagnoses sMCI pMCI --n_splits 5 --split 3 --accumulation_steps 1 --epochs 200 --learning_rate 1e-5 --weight_decay 1e-3 --patience 20 --use_extracted_patches --selection_threshold 0.7 --dropout 0.5
After completing your suggestion, there is still an error:
FileNotFoundError: [Errno 2] No such file or directory: '/home/geng/ADNI2/caps/subjects/sub-ADNI002S4229/ses-M06/deeplearning_prepare_data/image_based/t1_linear/sub-ADNI002S4229_ses-M06_T1w_space-MNI152NLin2009cSym_desc-Crop_res-1x1x1_T1w.pt'
image_based? I only have patch_based folder 。 image_based should be the entire brain MRI folder。
from clinicadl.
Hi,
Actually the Dataset which prepares patches needs the full image to find automatically the number of patches based on the size of the full image + the patch size + the patch stride. This is why it is looking for the full image.
In https://github.com/aramis-lab/AD-DL/pull/58 it will look for the original nifti file if it does not find the tensor (right now it is only looking for the tensor). It should fix the problem.
from clinicadl.
Related Issues (20)
- data augmentation issues HOT 1
- unsupported operand type(s) for +=: 'PosixPath' and 'str' HOT 5
- categorical split variable flag HOT 1
- Subject: Inquiry on Using Pre-trained Models for Transfer Learning with ClinicaDL HOT 7
- Retrocompatibility problem with maps.json
- Issue with Limited Number of Samples in BIDS Conversion Using ClinicaDL
- Requirement for 'diagnosis' Column in Generalization Testing with ClinicaDL HOT 1
- T1-Volume quality check tsv are empty
- Clinica T1-Linear Pipeline Fails: FileNotFoundError for 'bias_image' in N4BiasFieldCorrection Node HOT 4
- Add option to save model for each epochs
- Expanding Modality Support for ML Classification in ClinicaDL HOT 1
- Clarification needed on `TSV_DIRECTORY` for Training after using `prepare-experiment` HOT 2
- Documentation copyright is outdated
- Use `parent` or `parents` attributes of Pathlib Path object instead of chaining ".." strings
- Use `setdefault()` method instead of looping over default dict
- No Hippocampus Mask Available/Compatible HOT 3
- File format not BIDS compliant
- get-progression turns 2-digits session labels to 3 digits HOT 1
- TypeError: can only concatenate str (not "PosixPath") to str
- MapsManager uses a different CAPS folder in predict than the one provided by the user HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from clinicadl.