From 328b171e5a48599ed93ecc28aa4313012dfa16ab Mon Sep 17 00:00:00 2001
From: Lewy <pawlew2@st.amu.edu.pl>
Date: Tue, 15 Jun 2021 01:36:18 +0200
Subject: [PATCH] file namechange

- changed name of files to represent inside
- added main to seperate processes
- changed raw code to functions
---
 AI/NN_accuracy.py    | 64 ++++++++++++++++++++++++++++++++++++++++++++
 AI/grader.py         | 56 --------------------------------------
 AI/id3.py            |  6 +++--
 AI/neural_network.py |  3 ++-
 4 files changed, 70 insertions(+), 59 deletions(-)
 create mode 100644 AI/NN_accuracy.py
 delete mode 100644 AI/grader.py

diff --git a/AI/NN_accuracy.py b/AI/NN_accuracy.py
new file mode 100644
index 0000000..9ab14a6
--- /dev/null
+++ b/AI/NN_accuracy.py
@@ -0,0 +1,64 @@
+import PIL
+import torchvision.transforms as transforms
+
+from AI import neural_network
+
+
+# wcześniej grinder.py
+# Get accuracy for neural_network model 'network_model.pth'
+def NN_accuracy():
+    # Create the model
+    model = neural_network.Net()
+
+    # Load state_dict
+    neural_network.load_network_from_structure(model)
+
+    # Create the preprocessing transformation here
+    transform = transforms.Compose([neural_network.Negative(), transforms.ToTensor()])
+
+    # load your image(s)
+    img = PIL.Image.open('../src/test/0_100.jpg')
+    img2 = PIL.Image.open('../src/test/1_100.jpg')
+    img3 = PIL.Image.open('../src/test/4_100.jpg')
+    img4 = PIL.Image.open('../src/test/5_100.jpg')
+
+    # Transform
+    input = transform(img)
+    input2 = transform(img2)
+    input3 = transform(img3)
+    input4 = transform(img4)
+
+    # unsqueeze batch dimension, in case you are dealing with a single image
+    input = input.unsqueeze(0)
+    input2 = input2.unsqueeze(0)
+    input3 = input3.unsqueeze(0)
+    input4 = input4.unsqueeze(0)
+
+    # Set model to eval
+    model.eval()
+
+    # Get prediction
+    output = model(input)
+    output2 = model(input2)
+    output3 = model(input3)
+    output4 = model(input4)
+
+    print(output)
+    index = output.cpu().data.numpy().argmax()
+    print(index)
+
+    print(output2)
+    index = output2.cpu().data.numpy().argmax()
+    print(index)
+
+    print(output3)
+    index = output3.cpu().data.numpy().argmax()
+    print(index)
+
+    print(output4)
+    index = output4.cpu().data.numpy().argmax()
+    print(index)
+
+
+if __name__ == "__main__":
+    NN_accuracy()
diff --git a/AI/grader.py b/AI/grader.py
deleted file mode 100644
index 7b0057a..0000000
--- a/AI/grader.py
+++ /dev/null
@@ -1,56 +0,0 @@
-import PIL
-import torchvision.transforms as transforms
-
-from AI import neural_network
-
-# Create the model
-model = neural_network.Net()
-
-# Load state_dict
-neural_network.load_network_from_structure(model)
-
-# Create the preprocessing transformation here
-transform = transforms.Compose([neural_network.Negative(), transforms.ToTensor()])
-
-# load your image(s)
-img = PIL.Image.open('../src/test/0_100.jpg')
-img2 = PIL.Image.open('../src/test/1_100.jpg')
-img3 = PIL.Image.open('../src/test/4_100.jpg')
-img4 = PIL.Image.open('../src/test/5_100.jpg')
-
-# Transform
-input = transform(img)
-input2 = transform(img2)
-input3 = transform(img3)
-input4 = transform(img4)
-
-# unsqueeze batch dimension, in case you are dealing with a single image
-input = input.unsqueeze(0)
-input2 = input2.unsqueeze(0)
-input3 = input3.unsqueeze(0)
-input4 = input4.unsqueeze(0)
-
-# Set model to eval
-model.eval()
-
-# Get prediction
-output = model(input)
-output2 = model(input2)
-output3 = model(input3)
-output4 = model(input4)
-
-print(output)
-index = output.cpu().data.numpy().argmax()
-print(index)
-
-print(output2)
-index = output2.cpu().data.numpy().argmax()
-print(index)
-
-print(output3)
-index = output3.cpu().data.numpy().argmax()
-print(index)
-
-print(output4)
-index = output4.cpu().data.numpy().argmax()
-print(index)
diff --git a/AI/id3.py b/AI/id3.py
index 68b9348..f7b382d 100644
--- a/AI/id3.py
+++ b/AI/id3.py
@@ -120,5 +120,7 @@ def pretty_print(root, n):
         pretty_print(child[0], n + 1)
 
 
-tree = treelearn(cases, attributes, 0)
-pretty_print(tree, 0)
+# Get view of decision_tree.py
+if __name__ == "__main__":
+    tree = treelearn(cases, attributes, 0)
+    pretty_print(tree, 0)
diff --git a/AI/neural_network.py b/AI/neural_network.py
index 0910476..a2d340e 100644
--- a/AI/neural_network.py
+++ b/AI/neural_network.py
@@ -27,7 +27,7 @@ def plotdigit(image):
 
 
 transform = transforms.Compose([Negative(), transforms.ToTensor()])
-train_set = torchvision.datasets.ImageFolder(root='train', transform=transform)
+train_set = torchvision.datasets.ImageFolder(root='../src/train', transform=transform)
 classes = ("apple", "potato")
 
 BATCH_SIZE = 2
@@ -99,6 +99,7 @@ def load_network_from_structure(network):
     network.load_state_dict(torch.load('network_model.pth'))
 
 
+# Create network_model.pth
 if __name__ == "__main__":
     print(torch.cuda.is_available())
     training_network()