deepflash2 - pypi Package Compare versions

Comparing version 0.1.7 to 0.1.8

deepflash2.egg-info/PKG-INFO

 Metadata-Version: 2.1
 Name: deepflash2
-Version: 0.1.7
+Version: 0.1.8
 Summary: A Deep learning pipeline for segmentation of fluorescent labels in microscopy images
@@ -22,6 +22,7 @@ Home-page: https://github.com/matjesg/deepflash2
 
-# Title
 
+# Welcome to
 
 
+
 ![deepflash2](https://raw.githubusercontent.com/matjesg/deepflash2/master/nbs/media/logo/deepflash2_logo_medium.png)
@@ -127,10 +128,10 @@
 
-We recommend installation into a clean Python environment (e.g., using [conda](https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html)).
+We recommend installation into a clean Python 3.7, 3.8, or 3.9 environment (e.g., using [conda](https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html)).
 
-#### [conda](https://docs.conda.io/en/latest/)/[mamba](https://github.com/mamba-org/mamba)
+#### [mamba](https://github.com/mamba-org/mamba)/[conda](https://docs.conda.io/en/latest/)
 
-If you replace `conda` with `mamba` the install process will be much faster and more reliable (you need to install [mamba](https://github.com/mamba-org/mamba) first):
+Installation with mamba (installaton [instructions](https://github.com/mamba-org/mamba)) allows a fast and realiable installation process (you can replace `mamba` with `conda` and add the `--update-all` flag to do the installation with conda).
 
 ```bash
-conda install -c fastchan -c conda-forge -c matjesg deepflash2 
+mamba install -c fastchan -c conda-forge -c matjesg deepflash2 
 ```
@@ -137,0 +138,0 @@

deepflash2.egg-info/requires.txt

@@ -12,3 +12,3 @@ pip
 numba>=0.52.0
-opencv-python>=4.0
-segmentation_models_pytorch>=0.2
+segmentation-models-pytorch>=0.2
+opencv-python-headless<4.5.5,>=4.1.1

deepflash2/__init__.py

@@ -1,1 +0,1 @@
-__version__ = "0.1.7"
+__version__ = "0.1.8"

deepflash2/learner.py

@@ -363,7 +363,11 @@ # AUTOGENERATED! DO NOT EDIT! File to edit: nbs/00_learner.ipynb (unless otherwise specified).
                                     preproc_dir=preproc_dir,
-                                    stats=self.stats,
                                     instance_labels=self.instance_labels,
                                     n_classes=self.n_classes,
-                                    sample_mult=self.sample_mult if self.sample_mult>0 else None, verbose=0)
-        self.stats = stats or self.ds.stats
+                                    stats=self.stats,
+                                    normalize = True,
+                                    sample_mult=self.sample_mult if self.sample_mult>0 else None,
+                                    verbose=0,
+                                    **self.add_ds_kwargs)
+
+        self.stats = self.ds.stats
         self.in_channels = self.ds.get_data(max_n=1)[0].shape[-1]
@@ -554,2 +558,3 @@ self.df_val, self.df_ens, self.df_model, self.ood = None,None,None,None
         self.models = {}
+
         for i, m in enumerate(models,1):
@@ -559,7 +564,12 @@ if i==0: self.n_classes = int(m.name.split('_')[2][0])
             self.models[i] = m
-        if len(self.models)>0: self.set_n(len(self.models))
-        print(f'Found {len(self.models)} models in folder {path}')
-        print([m.name for m in self.models.values()])
 
+        if len(self.models)>0:
+            self.set_n(len(self.models))
+            print(f'Found {len(self.models)} models in folder {path}:')
+            print([m.name for m in self.models.values()])
 
+            # Reset stats
+            print(f'Loading stats from {self.models[1].name}')
+            _, self.stats = load_smp_model(self.models[1])
+
     def get_ensemble_results(self, files, zarr_store=None, export_dir=None, filetype='.png', **kwargs):
@@ -729,8 +739,8 @@ ep = EnsemblePredict(models_paths=self.models.values(), zarr_store=zarr_store)
 
-    def clear_tmp(self):
-        try:
-            shutil.rmtree('/tmp/*', ignore_errors=True)
-            shutil.rmtree(self.path/'.tmp')
-            print(f'Deleted temporary files from {self.path/".tmp"}')
-        except: print(f'No temporary files to delete at {self.path/".tmp"}')
+    #def clear_tmp(self):
+    #    try:
+    #        shutil.rmtree('/tmp/*', ignore_errors=True)
+    #        shutil.rmtree(self.path/'.tmp')
+    #        print(f'Deleted temporary files from {self.path/".tmp"}')
+    #    except: print(f'No temporary files to delete at {self.path/".tmp"}')
 
@@ -755,3 +765,3 @@ # Cell
          export_cellpose_rois='Export cellpose predictions to ImageJ ROI Sets in `ouput_folder`',
-         clear_tmp="Clear directory with temporary files"
+         #clear_tmp="Clear directory with temporary files"
 )

deepflash2/models.py

@@ -12,2 +12,3 @@ # AUTOGENERATED! DO NOT EDIT! File to edit: nbs/01_models.ipynb (unless otherwise specified).
 from fastdownload import download_url
+from fastprogress import progress_bar
 from pathlib import Path
@@ -68,3 +69,5 @@ import sys, subprocess
     stats = model_dict.pop('stats')
-    model = create_smp_model(**model_dict)
+    # Ensure that no pretrained encoder weights are loaded
+    model_dict.pop('encoder_weights', None)
+    model = create_smp_model(**model_dict,  encoder_weights=None, **kwargs)
     model.load_state_dict(state, strict=strict)
@@ -122,3 +125,3 @@ return model, stats
     cp_masks = []
-    for prob, mask in zip(probs, masks):
+    for prob, mask in progress_bar(zip(probs, masks), total=len(probs), leave=False):
         cp_pred, _, _, _ = model.eval(prob,
@@ -125,0 +128,0 @@ net_avg=True,

PKG-INFO

 Metadata-Version: 2.1
 Name: deepflash2
-Version: 0.1.7
+Version: 0.1.8
 Summary: A Deep learning pipeline for segmentation of fluorescent labels in microscopy images
@@ -22,6 +22,7 @@ Home-page: https://github.com/matjesg/deepflash2
 
-# Title
 
+# Welcome to
 
 
+
 ![deepflash2](https://raw.githubusercontent.com/matjesg/deepflash2/master/nbs/media/logo/deepflash2_logo_medium.png)
@@ -127,10 +128,10 @@
 
-We recommend installation into a clean Python environment (e.g., using [conda](https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html)).
+We recommend installation into a clean Python 3.7, 3.8, or 3.9 environment (e.g., using [conda](https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html)).
 
-#### [conda](https://docs.conda.io/en/latest/)/[mamba](https://github.com/mamba-org/mamba)
+#### [mamba](https://github.com/mamba-org/mamba)/[conda](https://docs.conda.io/en/latest/)
 
-If you replace `conda` with `mamba` the install process will be much faster and more reliable (you need to install [mamba](https://github.com/mamba-org/mamba) first):
+Installation with mamba (installaton [instructions](https://github.com/mamba-org/mamba)) allows a fast and realiable installation process (you can replace `mamba` with `conda` and add the `--update-all` flag to do the installation with conda).
 
 ```bash
-conda install -c fastchan -c conda-forge -c matjesg deepflash2 
+mamba install -c fastchan -c conda-forge -c matjesg deepflash2 
 ```
@@ -137,0 +138,0 @@

README.md

@@ -1,5 +0,6 @@
-# Title
 
+# Welcome to
 
 
+
 ![deepflash2](https://raw.githubusercontent.com/matjesg/deepflash2/master/nbs/media/logo/deepflash2_logo_medium.png)
@@ -105,10 +106,10 @@
 
-We recommend installation into a clean Python environment (e.g., using [conda](https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html)).
+We recommend installation into a clean Python 3.7, 3.8, or 3.9 environment (e.g., using [conda](https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html)).
 
-#### [conda](https://docs.conda.io/en/latest/)/[mamba](https://github.com/mamba-org/mamba)
+#### [mamba](https://github.com/mamba-org/mamba)/[conda](https://docs.conda.io/en/latest/)
 
-If you replace `conda` with `mamba` the install process will be much faster and more reliable (you need to install [mamba](https://github.com/mamba-org/mamba) first):
+Installation with mamba (installaton [instructions](https://github.com/mamba-org/mamba)) allows a fast and realiable installation process (you can replace `mamba` with `conda` and add the `--update-all` flag to do the installation with conda).
 
 ```bash
-conda install -c fastchan -c conda-forge -c matjesg deepflash2 
+mamba install -c fastchan -c conda-forge -c matjesg deepflash2 
 ```
@@ -115,0 +116,0 @@

settings.ini

@@ -11,3 +11,3 @@ [DEFAULT]
 branch = master
-version = 0.1.7
+version = 0.1.8
 min_python = 3.6
@@ -19,5 +19,5 @@ audience = Developers
 status = 2
-requirements = fastai>=2.1.7 zarr>=2.0 scikit-image imageio ipywidgets openpyxl albumentations>=1.0.0 natsort>=7.1.1 numba>=0.52.0
-pip_requirements = opencv-python>=4.0 segmentation_models_pytorch>=0.2
-conda_requirements = opencv>=4.0 segmentation-models-pytorch>=0.2
+requirements = fastai>=2.1.7 zarr>=2.0 scikit-image imageio ipywidgets openpyxl albumentations>=1.0.0 natsort>=7.1.1 numba>=0.52.0 segmentation-models-pytorch>=0.2 opencv-python-headless>=4.1.1,<4.5.5
+#pip_requirements = 
+#conda_requirements = 
 nbs_path = nbs
@@ -32,3 +32,2 @@ doc_path = docs
 tst_flags = slow
-cell_spacing = 1
-
+cell_spacing = 1

Alert delta unavailable

Currently unable to show alert delta for PyPI packages.

Improved metrics

Total package byte prevSize

223681

0.37%

Lines of code

3548

0.28%