Merge branch 'DEV_meetdoshi' into 'DEV'

Dev meetdoshi merged with DEV.

See merge request !1

.gitignore

+*pycache*
+*.pdf
+*.csv
+*.ipynb
+*Logs*

1508.06576/feature_maps.py

 import torch
+import torch.nn as NN
 from logger import Logger
 LOGGER = Logger().logger()
 LOGGER.info("Started Feature Maps")
+device=torch.device( "cuda" if (torch.cuda.is_available()) else 'cpu')
+LOGGER.info("Running the model cuda_available = "+str(torch.cuda.is_available()))
 #Author: @meetdoshi
-class FeatureMaps:
+class FeatureMaps():
     def __init__(self,arch="vgg19"):
         '''
         Init function
         @params
         arch: str {vgg11,vgg13,vgg16,vgg19,vgg19bn}
         '''
+        super()
         try:
             self.model = torch.hub.load('pytorch/vision:v0.10.0',arch,pretrained=True)
-        except:
-            LOGGER.error("Could not load model")
+        except Exception as e:
+            LOGGER.error("Could not load model" + str(e))
         return
     
     def get_model(self):
@@ -33,7 +37,7 @@ class FeatureMaps:
                 LOGGER.error("Could not fetch layer "+str(layer))
         return weights
 
-    def get_fmaps(self,img,layer=[0,5,10,19,28]):
+    def get_fmaps_content(self,img,layer=[21]):
         '''
         Function which will pass the image through the model and get the respective fmaps
         @params
@@ -49,6 +53,22 @@ class FeatureMaps:
             layer_num+=1
         return fmaps
 
+    def get_fmaps_style(self,img,layer=[0,5,10,19,28]):
+        '''
+        Function which will pass the image through the model and get the respective fmaps
+        @params
+        img: numpy image f64
+        layer: list
+        '''
+        fmaps = []
+        layer_num = 0
+        for layer_i in self.model.features:
+            img = layer_i(img)
+            if layer_num in layer:
+                fmaps.append(img)
+            layer_num+=1
+        return fmaps
+'''
 if __name__ == "__main__":
     fmap = FeatureMaps()
     model = fmap.get_model()
@@ -57,3 +77,4 @@ if __name__ == "__main__":
     print(len(weights))
     for weight in weights:
         print(type(weight),weight.shape)
+'''

1508.06576/image2gif.py

+import imageio
+import os
+
+fnames = []
+newNameFolder = 'content-4_2'
+path = 'styled_images/'+newNameFolder
+
+for img in os.listdir(path):
+        fnames.append(os.path.join(path+"/", img))
+
+fnames.sort()
+
+with imageio.get_writer('gifs/'+newNameFolder+".gif", mode='I',duration = 0.2) as writer:
+    for fname in fnames:
+        image = imageio.imread(fname)
+        writer.append_data(image)

1508.06576/logger.py

 import logging
 import os
+from xml.dom.minidom import Identified
 #Author: @meetdoshi
 class Logger:
     '''
@@ -10,11 +11,12 @@ class Logger:
     _formatter = logging.Formatter('%(asctime)s %(levelname)s %(message)s')
     def __new__(cls,*args,**kwargs):
         if not cls._instance:
-            os.system("rm -rf Logs/")
+            identifier = 'content-4_2'
+            if not os.path.isdir("Logs/"):
                 os.mkdir("Logs/")
-            logHandler = logging.FileHandler("Logs/style_transfer.log")
+            logHandler = logging.FileHandler("Logs/style_transfer_"+identifier+".log")
             logHandler.setFormatter(cls._formatter)
-            cls._logHandler = logging.getLogger("Logs/style_transfer.log")
+            cls._logHandler = logging.getLogger("Logs/style_transfer_"+identifier+".log")
             cls._logHandler.setLevel(logging.INFO)
             cls._logHandler.addHandler(logHandler)
             cls._instance = super(Logger, cls).__new__(cls,*args,**kwargs)

1508.06576/loss.py

@@ -14,10 +14,9 @@ class Loss:
         Author: @meetdoshi
         '''
         l2_norm_sq = None
-        for i in range(len(F)):
         try:
-                diff = F[i]-P[i]
-                l2_norm_sq = torch.mean(diff**2)
+            diff = F-P
+            l2_norm_sq = torch.mean((diff)**2)
         except Exception as e:
             LOGGER.error("Error computing loss",e)
         return l2_norm_sq
@@ -41,24 +40,33 @@ class Loss:
         @params
         Author: @soumyagupta
         '''
-        for i in range(len(F)):
-            num_channels = F[i][1]
-            h = F[i][2]
-            w = F[i][3]
-            style_gram_matrix = Loss.gram_matrix(F[i])
-            target_gram_matrix = Loss.gram_matrix(A[i])
-            loss_s = torch.sum((style_gram_matrix-target_gram_matrix)**2)
-            constant = 1/(4.0*(num_channels**2)*((h*w)**2))
-        return constant*loss_s
+        num_channels = F.shape[1]
+        h = F.shape[2]
+        w = F.shape[3]
+        style_gram_matrix = Loss.gram_matrix(F)
+        target_gram_matrix = Loss.gram_matrix(A)
+        loss_s = torch.mean((style_gram_matrix-target_gram_matrix)**2)
+        #constant = 1/(4.0*(num_channels**2)*((h*w)**2))
+        return loss_s
 
     @staticmethod
-    def total_loss(alpha,beta,cont_fmap_real,cont_fmap_noise,style_fmap_real,style_fmap_noise):
+    def total_loss(alpha,beta,cont_fmap_real,style_fmap_real,generated_fmaps_content,generated_fmaps_style):
         '''
         Function which computes total loss and returns it
         @params
         Author: @jiteshg
         '''
-        content_loss = Loss.content_loss(cont_fmap_real, cont_fmap_noise)
-        style_loss = Loss.style_loss(style_fmap_real, style_fmap_noise)
-        loss_t = alpha*content_loss + beta*style_loss
-        return loss_t
\ No newline at end of file
+        loss_t = 0.0
+        a = 0.0
+        b = 0.0
+
+        for cont,gen_cont in zip(cont_fmap_real,generated_fmaps_content):
+                loss_cont = Loss.content_loss(cont,gen_cont)
+                a+= loss_cont
+
+        for gen_style,sty in zip(generated_fmaps_style,style_fmap_real):
+                loss_style = Loss.style_loss(sty,gen_style)
+                b+= loss_style
+
+        loss_t += alpha*a + beta*b
+        return loss_t,a,b
\ No newline at end of file

1508.06576/optimizer.py

 from loss import Loss
-from feature_maps import FeatureMaps
+from feature_maps import LOGGER, FeatureMaps
 import torch.optim as optim
 from torchvision.utils import save_image
-
+import matplotlib.pyplot as plt
+import os
+plt.ion()
 class Optimizer:
     @staticmethod
     def gradient_descent(content_img, style_img, content_img_clone):
@@ -14,24 +16,28 @@ class Optimizer:
         content_img_clone: Copy of Original Image
         Author: @gaurangathavale
         '''
-        epoch = 1000
-        learning_rate = 0.001
-        alpha = 10
-        beta = 100
+        LOGGER.info("Running gradient descent with the following parameters")
+        epoch = 4000
+        learning_rate = 0.01
+        alpha = 1
+        beta = 0.01 
+        identifier = "content-4_2"
+        os.mkdir("styled_images/"+identifier)
+        LOGGER.info(f"{epoch},{learning_rate},{alpha},{beta}")
 
         optimizer=optim.Adam([content_img_clone],lr=learning_rate)
-        print(optimizer)
-
+        LOGGER.info("Optimizer = " + str(optimizer))
+        #fig = plt.figure()
+        #ax = fig.add_subplot(111)
+        feature_maps = FeatureMaps()
         for e in range(epoch):
     
-            feature_maps = FeatureMaps()
-            content_fmaps = feature_maps.get_fmaps(content_img)
-            style_fmaps = feature_maps.get_fmaps(style_img)
-            # content_clone_fmaps = feature_maps.get_fmaps(content_img_clone)
-            content_white_noise_fmaps = feature_maps.get_fmaps(content_img, [21])
-            style_white_noise_fmaps = feature_maps.get_fmaps(style_img, [21])
+            content_fmaps = feature_maps.get_fmaps_content(content_img)
+            style_fmaps = feature_maps.get_fmaps_style(style_img)
+            generated_fmaps_content = feature_maps.get_fmaps_content(content_img_clone)
+            generated_fmaps_style = feature_maps.get_fmaps_style(content_img_clone)
             
-            total_loss = Loss.total_loss(alpha, beta, content_fmaps, content_white_noise_fmaps, style_fmaps, style_white_noise_fmaps)
+            total_loss,total_cont_loss,total_style_loss = Loss.total_loss(alpha, beta, content_fmaps, style_fmaps,generated_fmaps_content,generated_fmaps_style)
             
             # clears x.grad for every parameter x in the optimizer. 
             # It’s important to call this before total_loss.backward(), otherwise it will accumulate the gradients from multiple passes.
@@ -42,8 +48,9 @@ class Optimizer:
             
             # Optimization Step / Update Rule
             optimizer.step()
-            
-            if(not (e%100)):
-                print(total_loss)
-                
-                save_image(content_img_clone,"styled.png")
\ No newline at end of file
+            #plt.clf()
+            #plt.plot(content_img_clone)
+            if(e%10 == 0):
+                LOGGER.info(f"Epoch = {e} Total Loss = {total_loss} content Loss = {total_cont_loss} style Loss = {total_style_loss}")
+                name = "styled_images/"+identifier+"/styled_" + str(e) +".png"
+                save_image(content_img_clone,name)
\ No newline at end of file

1508.06576/preprocess.py

+from os import device_encoding
 from logger import Logger
-from torch import transforms
+import torch
+import torchvision.transforms as transforms
 from PIL import Image
 import numpy as np
 LOGGER = Logger().logger()
+device=torch.device( "cuda" if (torch.cuda.is_available()) else 'cpu')
 #Author: @meetdoshi
 class Preprocessor:
     @staticmethod
@@ -32,9 +35,11 @@ class Preprocessor:
         @params
         img: 3d numpy array
         '''
-        loader = transforms.Compose([transforms.ToTensor(),transforms.Resize([224,224]),transforms.Normalize(mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225],),])
+        #loader = transforms.Compose([transforms.ToTensor(),transforms.Resize([224,224]),transforms.Normalize(mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225],),])
+        loader = transforms.Compose([transforms.ToTensor(),transforms.Resize([224,224])])
         img = loader(img).unsqueeze(0)
-        return img
+        #assert img.shape == (1,3,224,224)
+        return img.to(device,torch.float)
 
 
     @staticmethod
@@ -46,15 +51,12 @@ class Preprocessor:
         '''
         img = Preprocessor.load_image(path)
         img = Preprocessor.reshape_img(img)
-        img = Preprocessor.subtract_mean(img)
+        #img = Preprocessor.subtract_mean(img)
         return img
 
+'''
 if __name__=="__main__":
     prec = Preprocessor()
     img = np.zeros(shape=(4,4,3))
-    print(img.shape)
-    for i in range(img.shape[2]):
-        print(img[:,:,i])
-    img = prec.subtract_mean(img)
-    for i in range(img.shape[2]):
-        print(img[:,:,i])
+    img = prec.process('test/sem8.jpeg')
+'''

1508.06576/requirements.txt

+matplotlib==3.5.1
+numpy==1.21.5
+Pillow==9.2.0
+torch==1.12.1+cpu
+torchvision==0.13.1+cpu

1508.06576/style_transfer.py

-import os
  
+import os
+import warnings
 from optimizer import Optimizer
 from loss import Loss
 from preprocess import Preprocessor
@@ -11,10 +12,10 @@ import argparse
 import torchvision.models as models
 import torch.optim as optim
 from torchvision.utils import save_image
+warnings.filterwarnings('ignore')
 from logger import Logger
 LOGGER = Logger().logger()
 LOGGER.info("Started Style Transfer")
-
 class StyleTransfer:
     '''
     Style Transfer Base Class
@@ -32,8 +33,8 @@ class StyleTransfer:
 
         device = torch.device( "cuda" if (torch.cuda.is_available()) else 'cpu')
 
-        content_img_path = 'Nikola-Tesla.jpg'
-        style_img_path = 'style-Image.jpg'
+        content_img_path = 'test/content.jpg'
+        style_img_path = 'test/style.jpg'
 
         content_img = Preprocessor.process(content_img_path)
         style_img = Preprocessor.process(style_img_path)
@@ -41,3 +42,10 @@ class StyleTransfer:
         content_img_clone = content_img.clone().requires_grad_(True)
 
         Optimizer.gradient_descent(content_img, style_img, content_img_clone)
+
+if __name__ == "__main__":
+    stf = StyleTransfer()
+    stf.pipeline()
+        
+
+    
\ No newline at end of file

1703.10593/logger.py

+import logging
+import os
+#Author: @meetdoshi
+class Logger:
+    '''
+    Singleton logger class
+    '''
+    _instance = None
+    _logHandler = None
+    _formatter = logging.Formatter('%(asctime)s %(levelname)s %(message)s')
+    def __new__(cls,*args,**kwargs):
+        if not cls._instance:
+            os.system("rm -rf Logs/")
+            os.mkdir("Logs/")
+            logHandler = logging.FileHandler("Logs/style_transfer.log")
+            logHandler.setFormatter(cls._formatter)
+            cls._logHandler = logging.getLogger("Logs/style_transfer.log")
+            cls._logHandler.setLevel(logging.INFO)
+            cls._logHandler.addHandler(logHandler)
+            cls._instance = super(Logger, cls).__new__(cls,*args,**kwargs)
+        return cls._instance
+
+    def logger(self):
+        return self._logHandler
+
+'''
+#Demo use
+if __name__ == "__main__":
+    a = Logger()
+    b = Logger()
+    print(a is b)
+    INFO = a.logger()
+    ERROR = b.logger()
+    INFO.info("TEST")
+    ERROR.info("ERROR")
+'''

1703.10593/loss.py

+import numpy as np
+import torch
+from logger import Logger
+LOGGER = Logger().logger()
+
+class Loss:
+    @staticmethod
+    def adversarial_G():
+        '''
+        L_gan(G,Dy,X,Y) = 
+        '''
\ No newline at end of file