'neural'

ai-wozek/.idea/aws.xml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="accountSettings">
+    <option name="activeRegion" value="us-east-1" />
+    <option name="recentlyUsedRegions">
+      <list>
+        <option value="us-east-1" />
+      </list>
+    </option>
+  </component>
+</project>

ai-wozek/.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.11 (ai-wozek) (2)" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11 (ai-wozek) (2)" project-jdk-type="Python SDK" />
+</project>

ai-wozek/.idea/runConfigurations/wozek.xml

@@ -1,18 +1,24 @@
 <component name="ProjectRunConfigurationManager">
   <configuration default="false" name="wozek" type="PythonConfigurationType" factoryName="Python" nameIsGenerated="true">
     <module name="wozek" />
+    <option name="ENV_FILES" value="" />
     <option name="INTERPRETER_OPTIONS" value="" />
     <option name="PARENT_ENVS" value="true" />
     <envs>
       <env name="PYTHONUNBUFFERED" value="1" />
     </envs>
     <option name="SDK_HOME" value="" />
-    <option name="SDK_NAME" value="Python 3.10" />
+    <option name="SDK_NAME" value="Python 3.11 (ai-wozek) (2)" />
     <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$" />
     <option name="IS_MODULE_SDK" value="false" />
     <option name="ADD_CONTENT_ROOTS" value="true" />
     <option name="ADD_SOURCE_ROOTS" value="true" />
     <EXTENSION ID="PythonCoverageRunConfigurationExtension" runner="coverage.py" />
+    <EXTENSION ID="software.aws.toolkits.jetbrains.core.execution.PythonAwsConnectionExtension">
+      <option name="credential" />
+      <option name="region" />
+      <option name="useCurrentConnection" value="false" />
+    </EXTENSION>
     <option name="SCRIPT_NAME" value="$PROJECT_DIR$/wozek.py" />
     <option name="PARAMETERS" value="" />
     <option name="SHOW_COMMAND_LINE" value="false" />

ai-wozek/.idea/wozek.iml

@@ -1,7 +1,10 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <module type="PYTHON_MODULE" version="4">
   <component name="NewModuleRootManager">
-    <content url="file://$MODULE_DIR$" />
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="jdk" jdkName="Python 3.11 (ai-wozek) (2)" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
 </module>

ai-wozek/.~lock.paczki.csv#

@@ -0,0 +1 @@
+,DESKTOP-REF7T1M/abc,DESKTOP-REF7T1M,16.06.2024 22:58,file:///C:/Users/abc/AppData/Roaming/LibreOffice/4;

ai-wozek/classes.py

@@ -1,12 +1,31 @@
-
+import random
+from glob import glob
+import numpy as np
 
 class Cargo:
-    def __init__(self, name, category, size, weight):
+    def __init__(self, height,width,depth,weight,damage,label_state,content,value,position):
-        self.name = name
+        self.height=height
-        self.size = size
+        self.width=width
-        self.weight = weight
+        self.depth=depth
-        self.category = category
+        self.weight=weight
-
+        self.damage=damage
+        self.label_state=label_state
+        self.content=content
+        self.value=value
+        self.position=position
+    def contentSplit(self):
+        if self.content=='fruits':
+            test=glob('./siec/train/fragile/*')
+            self.image=np.random.choice(test)
+        elif self.content=='nuclear_waste':
+            test=glob('./siec/train/toxic/*')
+            self.image = np.random.choice(test)
+        elif self.content=='clothes':
+            test = glob('./siec/train/flammable/*')
+            self.image = np.random.choice(test)
+        else:
+            self.image='./fruit.png'
+        print(self.image)
 
 class Clothes(Cargo):
     def __init__(self, name, size, weight, fragility):

ai-wozek/siec/dataset.py

@@ -0,0 +1,40 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torch.utils.data import Dataset, DataLoader
+import torchvision
+import torchvision.transforms as transforms
+from torchvision.datasets import ImageFolder
+import timm
+
+import matplotlib.pyplot as plt # For data viz
+import pandas as pd
+import numpy as np
+import sys
+
+class LabelDataset(Dataset):
+    def __init__(self, dataDirectory,transform=None):
+        self.data=ImageFolder(dataDirectory,transform=transform)
+    def __len__(self):
+        return len(self.data)
+    def __getitem__(self, idx):
+        return self.data[idx]
+
+    @property
+    def classes(self):
+        return self.data.classes
+
+classname={v:k for k,v in ImageFolder('./train').class_to_idx.items()}
+
+transform=transforms.Compose([
+    transforms.Resize((128,128)),
+    transforms.ToTensor(),
+])
+
+dataset=LabelDataset('./train',transform)
+dataloader=DataLoader(dataset,batch_size=4, shuffle=True)
+valset=LabelDataset('./val',transform)
+valloader=DataLoader(valset,batch_size=4,shuffle=False)
+
+for images,labels in dataloader:
+    break

ai-wozek/siec/model.py

@@ -0,0 +1,114 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torch.utils.data import Dataset, DataLoader
+import torchvision
+import torchvision.transforms as transforms
+from torchvision.datasets import ImageFolder
+import timm
+from PIL import Image
+
+import matplotlib.pyplot as plt # For data viz
+import pandas as pd
+import numpy as np
+import sys
+from siec import dataset
+from glob import glob
+
+class LabelClassifier(nn.Module):
+    def __init__(self,num_classes=3):
+        super(LabelClassifier, self).__init__()
+        self.model=timm.create_model('efficientnet_b0',pretrained=True)
+        self.features = nn.Sequential(*list(self.model.children())[:-1])
+        out_size=1280
+        self.classifier=nn.Linear(out_size,num_classes)
+    def forward(self,x):
+        x=self.features(x)
+        output=self.classifier(x)
+        return output
+model=torch.load("./model")
+
+criterion=nn.CrossEntropyLoss()
+optimizer=optim.Adam(model.parameters(),lr=0.0005)
+print(criterion(model(dataset.images),dataset.labels))
+
+num_epochs=0
+trainLosses=[]
+valLosses=[]
+
+device=torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+for epoch in range(num_epochs):
+    model.train()
+    runningLoss=0.0
+    for images,labels in dataset.dataloader:
+        images, labels=images.to(device), labels.to(device)
+        optimizer.zero_grad()
+        outputs=model(images)
+        loss=criterion(outputs,labels)
+        loss.backward()
+        optimizer.step()
+        runningLoss+=loss.item()*images.size(0)
+    trainLoss=runningLoss/len(dataset.dataloader.dataset)
+    trainLosses.append(trainLoss)
+
+    model.eval()
+    runningLoss=0.0
+    with torch.no_grad():
+        for images, labels in dataset.valloader:
+            images, labels = images.to(device), labels.to(device)
+            outputs=model(images)
+            loss=criterion(outputs,labels)
+            runningLoss+=loss.item()*images.size(0)
+    valLoss=runningLoss/len(dataset.valloader.dataset)
+    valLosses.append(valLoss)
+    print(f"Epoch {epoch + 1}/{num_epochs} - Train loss: {trainLoss}, Validation loss: {valLoss}")
+modell=torch.jit.script(model)
+modell.save('model.pt')
+
+
+def preprocess_image(image_path, transform):
+    image = Image.open(image_path).convert("RGB")
+    return image, transform(image).unsqueeze(0)
+
+# Predict using the model
+def predict(model, image_tensor, device):
+    model.eval()
+    with torch.no_grad():
+        image_tensor = image_tensor.to(device)
+        outputs = model(image_tensor)
+        probabilities = torch.nn.functional.softmax(outputs, dim=1)
+        print(outputs)
+    return probabilities.cpu().numpy().flatten()
+
+# Visualization
+def visualize_predictions(original_image, probabilities, class_names):
+    fig, axarr = plt.subplots(1, 2, figsize=(14, 7))
+    axarr[0].imshow(original_image)
+    axarr[0].axis("off")
+
+    # Display predictions
+    axarr[1].barh(class_names, probabilities)
+    axarr[1].set_xlabel("Probability")
+    axarr[1].set_title("Class Predictions")
+    axarr[1].set_xlim(0, 1)
+
+    plt.tight_layout()
+    plt.show()
+transform = transforms.Compose([
+    transforms.Resize((128, 128)),
+    transforms.ToTensor()
+])
+test_images = glob('./train/*/*')
+test_examples = np.random.choice(test_images, 10)
+for example in test_examples:
+    model.eval()
+    original_image, image_tensor = preprocess_image(example, transform)
+    probabilities = predict(model, image_tensor, device)
+    print(probabilities)
+
+    # Assuming dataset.classes gives the class names
+    class_names = dataset.dataset.classes
+    visualize_predictions(original_image, probabilities, class_names)
+    model(image_tensor)