How csbdeep/csbdeep works
CSBDeep is a Python toolbox for CARE deep-learning restoration of fluorescence microscopy images. Its main workflow prepares image pairs and patches, trains a configured CARE model, then predicts restored images; model variants support isotropic, projection, and upsampling use cases. The graph includes the model-building and prediction internals, pretrained-model support, and the command-line interface. Relationships are limited to those documented in the README or visible in the supplied excerpts and SOURCE INDEX; unsampled details are not inferred.
Main entry points: care_standard.py CARE training and prediction · care_predict.py Prediction CLI · predict.py Tiled prediction · care_isotropic.py Isotropic CARE
Components 21
Data preparation
- Raw image pairs
csbdeep/data/rawdata.py - Image transforms
csbdeep/data/transform.py - Patch generation
csbdeep/data/generate.py - Data preparation
csbdeep/data/prepare.py
CARE models
- Model configuration
csbdeep/models/config.py - Model lifecycle
csbdeep/models/base_model.py - CARE training and prediction
csbdeep/models/care_standard.py - Isotropic CARE
csbdeep/models/care_isotropic.py - Projection CARE
csbdeep/models/care_projection.py - Upsampling CARE
csbdeep/models/care_upsampling.py - Pretrained models
csbdeep/models/pretrained.py
Model internals
- Network builders
csbdeep/internals/nets.py - Network blocks
csbdeep/internals/blocks.py - Training engine
csbdeep/internals/train.py - Training losses
csbdeep/internals/losses.py - Tiled prediction
csbdeep/internals/predict.py - Probabilistic output
csbdeep/internals/probability.py
Input and interfaces
- Image file I/O
csbdeep/io/__init__.py - Prediction CLI
csbdeep/scripts/care_predict.py - Restored images
csbdeep/io/__init__.py
Other components
- Microscopy user
Connections 27
- Microscopy user → Raw image pairs: provides images
- Raw image pairs → Patch generation: supplies image pairs
- Patch generation → Image transforms: applies transforms
csbdeep/data/generate.py - Patch generation → Image file I/O: saves patches
csbdeep/data/generate.py - Microscopy user → Model configuration: configures model
- Model configuration → Model lifecycle: configures lifecycle
csbdeep/models/base_model.py - Model lifecycle → Pretrained models: uses pretrained support
csbdeep/models/base_model.py - CARE training and prediction → Model lifecycle: extends lifecycle
csbdeep/models/care_standard.py - CARE training and prediction → Model configuration: uses configuration
csbdeep/models/care_standard.py - CARE training and prediction → Network builders: builds network
csbdeep/models/care_standard.py - CARE training and prediction → Training engine: trains with
csbdeep/models/care_standard.py - CARE training and prediction → Tiled prediction: predicts with
csbdeep/models/care_standard.py - CARE training and prediction → Probabilistic output: returns distributions
csbdeep/models/care_standard.py - Network builders → Network blocks: uses blocks
csbdeep/internals/nets.py - Training engine → Training losses: uses losses
csbdeep/internals/train.py - Isotropic CARE → CARE training and prediction: extends CARE
csbdeep/models/care_isotropic.py - Isotropic CARE → Tiled prediction: uses prediction
csbdeep/models/care_isotropic.py - Isotropic CARE → Probabilistic output: uses distributions
csbdeep/models/care_isotropic.py - Projection CARE → CARE training and prediction: extends CARE
csbdeep/models/care_projection.py - Projection CARE → Network builders: uses network builder
csbdeep/models/care_projection.py - Projection CARE → Tiled prediction: uses prediction
csbdeep/models/care_projection.py - Upsampling CARE → CARE training and prediction: extends CARE
csbdeep/models/care_upsampling.py - Prediction CLI → Image file I/O: reads and writes images
csbdeep/scripts/care_predict.py - Prediction CLI → Restored images: writes results
csbdeep/scripts/care_predict.py - Prediction CLI → CARE training and prediction: invokes model
csbdeep/scripts/care_predict.py - Prediction CLI → Data preparation: loads data
- Tiled prediction → Restored images: produces predictions