foscat 3.0.24__tar.gz → 3.0.26__tar.gz

{foscat-3.0.24 → foscat-3.0.26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: foscat
-Version: 3.0.24
+Version: 3.0.26
 Summary: Generate synthetic Healpix or 2D data using Cross Scattering Transform
 Home-page: https://github.com/jmdelouis/FOSCAT
 Author: Jean-Marc DELOUIS
@@ -9,6 +9,12 @@ Maintainer: Theo Foulquier
 Maintainer-email: theo.foulquier@ifremer.fr
 License: MIT
 Keywords: Scattering transform,Component separation,denoising
+Requires-Dist: imageio
+Requires-Dist: imagecodecs
+Requires-Dist: matplotlib
+Requires-Dist: numpy
+Requires-Dist: tensorflow
+Requires-Dist: healpy
 
 Utilize the Cross Scattering Transform (described in https://arxiv.org/abs/2207.12527) to synthesize Healpix or 2D data that is suitable for component separation purposes, such as denoising. 
  A demo package for this process can be found at https://github.com/jmdelouis/FOSCAT_DEMO. 

{foscat-3.0.24 → foscat-3.0.26}/setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='foscat',
-    version='3.0.24',
+    version='3.0.26',
     description='Generate synthetic Healpix or 2D data using Cross Scattering Transform' ,
     long_description='Utilize the Cross Scattering Transform (described in https://arxiv.org/abs/2207.12527) to synthesize Healpix or 2D data that is suitable for component separation purposes, such as denoising. \n A demo package for this process can be found at https://github.com/jmdelouis/FOSCAT_DEMO. \n Complete doc can be found at https://foscat-documentation.readthedocs.io/en/latest/index.html. \n\n List of developers : J.-M. Delouis, T. Foulquier, L. Mousset, T. Odaka, F. Paul, E. Allys ' ,
     license='MIT',

{foscat-3.0.24 → foscat-3.0.26}/src/foscat/FoCUS.py

@@ -32,7 +32,7 @@ class FoCUS:
                  mpi_size=1,
                  mpi_rank=0):
 
-        self.__version__ = '3.0.24'
+        self.__version__ = '3.0.26'
         # P00 coeff for normalization for scat_cov
         self.TMPFILE_VERSION=TMPFILE_VERSION
         self.P1_dic = None

{foscat-3.0.24 → foscat-3.0.26}/src/foscat/Softmax.py

@@ -16,7 +16,7 @@ class SoftmaxClassifier:
         Nhidden (int, optional): Number of neurons in the hidden layer. Defaults to 10.
     """
 
-    def __init__(self, Nval, Nclass, Nhidden=10):
+    def __init__(self, Nval, Nclass, Nhidden=10,Nlevel=1):
         """
         Initializes the SoftmaxClassifier with a specified number of input features, classes, and hidden neurons.
         
@@ -28,11 +28,15 @@ class SoftmaxClassifier:
             Nhidden (int): Number of neurons in the hidden layer.
         """
         # Create the model
-        self.model = Sequential([
-            Dense(units=Nhidden, activation='relu', input_shape=(Nval,)),  # A hidden layer with Nhidden neurons
-            Dense(units=Nclass),  # The output layer with Nclass neurons (for Nclass classes)
-            Softmax()  # Softmax activation for classification
-        ])
+        TheModel=[Dense(units=Nhidden, activation='relu', input_shape=(Nval,))]
+        
+        for k in range(1,Nlevel):
+            TheModel=TheModel+[Dense(units=Nhidden, activation='relu', input_shape=(Nhidden,))]
+            
+        TheModel=TheModel+[Dense(units=Nclass),  # The output layer with Nclass neurons (for Nclass classes)
+                           Softmax()  # Softmax activation for classification
+        ]
+        self.model = Sequential(TheModel)
 
         # Model compilation
         self.model.compile(

{foscat-3.0.24 → foscat-3.0.26}/src/foscat/scat1D.py

@@ -42,10 +42,10 @@ class scat1D:
     def flatten(self,S2L=False):
         if not S2L:
             if isinstance(self.P00,np.ndarray):
-                return np.concatenate([self.build_flat(lf.S0),
-                                       self.build_flat(lf.S1),
-                                       self.build_flat(lf.P00),
-                                       self.build_flat(lf.S2)],1)
+                return np.concatenate([self.build_flat(self.S0),
+                                       self.build_flat(self.S1),
+                                       self.build_flat(self.P00),
+                                       self.build_flat(self.S2)],1)
             else:
                 return self.backend.bk_concat([self.build_flat(self.S0),
                                                self.build_flat(self.S1),
@@ -53,11 +53,11 @@ class scat1D:
                                                self.build_flat(self.S2)],1)  
         else:
             if isinstance(self.P00,np.ndarray):
-                return np.concatenate([self.build_flat(lf.S0),
-                                       self.build_flat(lf.S1),
-                                       self.build_flat(lf.P00),
-                                       self.build_flat(lf.S2),
-                                       self.build_flat(lf.S2L)],1)
+                return np.concatenate([self.build_flat(self.S0),
+                                       self.build_flat(self.S1),
+                                       self.build_flat(self.P00),
+                                       self.build_flat(self.S2),
+                                       self.build_flat(self.S2L)],1)
             else:
                 return self.backend.bk_concat([self.build_flat(self.S0),
                                                self.build_flat(self.S1),

{foscat-3.0.24 → foscat-3.0.26}/src/foscat/scat_cov1D.py

@@ -375,14 +375,15 @@ class scat_cov1D:
                             (self.C01 - other),
                             c11,
                             s1=s1, c10=c10,backend=self.backend)
-        def domult(self,x,y):
+
+    def domult(self,x,y):
         try:
             return x*y
         except:
             if x.dtype==y.dtype:
                 return x*y
             if self.backend.bk_is_complex(x):
-
+                
                 return self.backend.bk_complex(self.backend.bk_real(x)*y,self.backend.bk_imag(x)*y)
             else:
                 return self.backend.bk_complex(self.backend.bk_real(y)*x,self.backend.bk_imag(y)*x)

{foscat-3.0.24 → foscat-3.0.26}/src/foscat.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: foscat
-Version: 3.0.24
+Version: 3.0.26
 Summary: Generate synthetic Healpix or 2D data using Cross Scattering Transform
 Home-page: https://github.com/jmdelouis/FOSCAT
 Author: Jean-Marc DELOUIS
@@ -9,6 +9,12 @@ Maintainer: Theo Foulquier
 Maintainer-email: theo.foulquier@ifremer.fr
 License: MIT
 Keywords: Scattering transform,Component separation,denoising
+Requires-Dist: imageio
+Requires-Dist: imagecodecs
+Requires-Dist: matplotlib
+Requires-Dist: numpy
+Requires-Dist: tensorflow
+Requires-Dist: healpy
 
 Utilize the Cross Scattering Transform (described in https://arxiv.org/abs/2207.12527) to synthesize Healpix or 2D data that is suitable for component separation purposes, such as denoising. 
  A demo package for this process can be found at https://github.com/jmdelouis/FOSCAT_DEMO.