updated NWT file format

David Mayerich
1 parent eccf10ff
Showing 3 changed files with 11 additions and 6 deletions Show diff stats
python/classify.py
python/envi.py
stim/biomodels/nwt_format.pptx
@@ -171,6 +171,7 @@ def envi_batch_predict(E, C, batch=10000):
     plt.ion()
     bar = progressbar.ProgressBar(max_value=numpy.count_nonzero(E.mask))
     while not Fv == []:
+        Fv = numpy.nan_to_num(Fv)                                                     #remove infinite values        
         if i == 0:
             Tv = C.predict(Fv.transpose())
         else:
@@ -181,6 +182,7 @@ def envi_batch_predict(E, C, batch=10000):
         RGB = class2color(Cv)
         plt.imshow(RGB)
         plt.pause(0.05)
-        Fv = E.loadbatch(batch)   
+        Fv = E.loadbatch(batch)
         i = i + 1
-        bar.update(len(Tv))
 \ No newline at end of file
+        bar.update(len(Tv))
+    return RGB
 \ No newline at end of file
@@ -187,8 +187,10 @@ class envi:
         self.open(filename, headername)
         if mask == []:
             self.mask = numpy.ones((self.header.lines, self.header.samples), dtype=numpy.bool)
-        else:
+        elif type(mask) == numpy.ndarray:
             self.mask = mask
+        else:
+            print("ERROR: unrecognized mask format - expecting a boolean array")
         self.idx = 0                                                               #initialize the batch IDX to 0 for batch reading
     def open(self, filename, headername = ""):
@@ -287,7 +289,8 @@ class envi:
     #input: envi file object, stack of class masks C x Y x X
     #output: feature matrix (features x pixels), target matrix (1 x pixels)
     #example: generate_training(("class_coll.bmp", "class_epith.bmp"), (1, 2))
-    def loadtrain(self, classimages):
+    #   verify      verify that there are no NaN or Inf values
+    def loadtrain(self, classimages, verify=True):
         # get number of classes
         C = classimages.shape[0]
@@ -300,8 +303,8 @@ class envi:
             t = numpy.ones((f.shape[1])) * (c+1)         #generate a target array                 
             F.append(f)
             T.append(t)
-
-        return numpy.concatenate(F, 1).transpose(), numpy.concatenate(T)
+        
+        return numpy.nan_to_num(numpy.concatenate(F, 1).transpose()), numpy.concatenate(T)
     #read a batch of data based on the mask
     def loadbatch(self, npixels):