diff --git a/ML/PaperReviews/efficientnet/EfficientNet.pdf b/ML/PaperReviews/efficientnet/EfficientNet.pdf
new file mode 100644
index 0000000..d1aeb91
Binary files /dev/null and b/ML/PaperReviews/efficientnet/EfficientNet.pdf differ
diff --git a/ML/PaperReviews/efficientnet/inverted_residual.png b/ML/PaperReviews/efficientnet/inverted_residual.png
new file mode 100644
index 0000000..9debff7
Binary files /dev/null and b/ML/PaperReviews/efficientnet/inverted_residual.png differ
diff --git a/ML/PaperReviews/efficientnet/squeezeexcitation.png b/ML/PaperReviews/efficientnet/squeezeexcitation.png
new file mode 100644
index 0000000..2a6c36c
Binary files /dev/null and b/ML/PaperReviews/efficientnet/squeezeexcitation.png differ
diff --git a/ML/PaperReviews/efficientnet/stochastic_depth.png b/ML/PaperReviews/efficientnet/stochastic_depth.png
new file mode 100644
index 0000000..77a1dcd
Binary files /dev/null and b/ML/PaperReviews/efficientnet/stochastic_depth.png differ
diff --git a/ML/Pytorch/CNN_architectures/pytorch_efficientnet.py b/ML/Pytorch/CNN_architectures/pytorch_efficientnet.py
new file mode 100644
index 0000000..576696b
--- /dev/null
+++ b/ML/Pytorch/CNN_architectures/pytorch_efficientnet.py
@@ -0,0 +1,182 @@
+import torch
+import torch.nn as nn
+from math import ceil
+
+base_model = [
+    # expand_ratio, channels, repeats, stride, kernel_size
+    [1, 16, 1, 1, 3],
+    [6, 24, 2, 2, 3],
+    [6, 40, 2, 2, 5],
+    [6, 80, 3, 2, 3],
+    [6, 112, 3, 1, 5],
+    [6, 192, 4, 2, 5],
+    [6, 320, 1, 1, 3],
+]
+
+phi_values = {
+    # tuple of: (phi_value, resolution, drop_rate)
+    "b0": (0, 224, 0.2),  # alpha, beta, gamma, depth = alpha ** phi
+    "b1": (0.5, 240, 0.2),
+    "b2": (1, 260, 0.3),
+    "b3": (2, 300, 0.3),
+    "b4": (3, 380, 0.4),
+    "b5": (4, 456, 0.4),
+    "b6": (5, 528, 0.5),
+    "b7": (6, 600, 0.5),
+}
+
+class CNNBlock(nn.Module):
+    def __init__(
+            self, in_channels, out_channels, kernel_size, stride, padding, groups=1
+    ):
+        super(CNNBlock, self).__init__()
+        self.cnn = nn.Conv2d(
+            in_channels,
+            out_channels,
+            kernel_size,
+            stride,
+            padding,
+            groups=groups,
+            bias=False,
+        )
+        self.bn = nn.BatchNorm2d(out_channels)
+        self.silu = nn.SiLU() # SiLU <-> Swish
+
+    def forward(self, x):
+        return self.silu(self.bn(self.cnn(x)))
+
+class SqueezeExcitation(nn.Module):
+    def __init__(self, in_channels, reduced_dim):
+        super(SqueezeExcitation, self).__init__()
+        self.se = nn.Sequential(
+            nn.AdaptiveAvgPool2d(1), # C x H x W -> C x 1 x 1
+            nn.Conv2d(in_channels, reduced_dim, 1),
+            nn.SiLU(),
+            nn.Conv2d(reduced_dim, in_channels, 1),
+            nn.Sigmoid(),
+        )
+
+    def forward(self, x):
+        return x * self.se(x)
+
+class InvertedResidualBlock(nn.Module):
+    def __init__(
+            self,
+            in_channels,
+            out_channels,
+            kernel_size,
+            stride,
+            padding,
+            expand_ratio,
+            reduction=4, # squeeze excitation
+            survival_prob=0.8, # for stochastic depth
+    ):
+        super(InvertedResidualBlock, self).__init__()
+        self.survival_prob = 0.8
+        self.use_residual = in_channels == out_channels and stride == 1
+        hidden_dim = in_channels * expand_ratio
+        self.expand = in_channels != hidden_dim
+        reduced_dim = int(in_channels / reduction)
+
+        if self.expand:
+            self.expand_conv = CNNBlock(
+                in_channels, hidden_dim, kernel_size=3, stride=1, padding=1,
+            )
+
+        self.conv = nn.Sequential(
+            CNNBlock(
+                hidden_dim, hidden_dim, kernel_size, stride, padding, groups=hidden_dim,
+            ),
+            SqueezeExcitation(hidden_dim, reduced_dim),
+            nn.Conv2d(hidden_dim, out_channels, 1, bias=False),
+            nn.BatchNorm2d(out_channels),
+        )
+
+    def stochastic_depth(self, x):
+        if not self.training:
+            return x
+
+        binary_tensor = torch.rand(x.shape[0], 1, 1, 1, device=x.device) < self.survival_prob
+        return torch.div(x, self.survival_prob) * binary_tensor
+
+    def forward(self, inputs):
+        x = self.expand_conv(inputs) if self.expand else inputs
+
+        if self.use_residual:
+            return self.stochastic_depth(self.conv(x)) + inputs
+        else:
+            return self.conv(x)
+
+
+class EfficientNet(nn.Module):
+    def __init__(self, version, num_classes):
+        super(EfficientNet, self).__init__()
+        width_factor, depth_factor, dropout_rate = self.calculate_factors(version)
+        last_channels = ceil(1280 * width_factor)
+        self.pool = nn.AdaptiveAvgPool2d(1)
+        self.features = self.create_features(width_factor, depth_factor, last_channels)
+        self.classifier = nn.Sequential(
+            nn.Dropout(dropout_rate),
+            nn.Linear(last_channels, num_classes),
+        )
+
+    def calculate_factors(self, version, alpha=1.2, beta=1.1):
+        phi, res, drop_rate = phi_values[version]
+        depth_factor = alpha ** phi
+        width_factor = beta ** phi
+        return width_factor, depth_factor, drop_rate
+
+    def create_features(self, width_factor, depth_factor, last_channels):
+        channels = int(32 * width_factor)
+        features = [CNNBlock(3, channels, 3, stride=2, padding=1)]
+        in_channels = channels
+
+        for expand_ratio, channels, repeats, stride, kernel_size in base_model:
+            out_channels = 4*ceil(int(channels*width_factor) / 4)
+            layers_repeats = ceil(repeats * depth_factor)
+
+            for layer in range(layers_repeats):
+                features.append(
+                    InvertedResidualBlock(
+                        in_channels,
+                        out_channels,
+                        expand_ratio=expand_ratio,
+                        stride = stride if layer == 0 else 1,
+                        kernel_size=kernel_size,
+                        padding=kernel_size//2, # if k=1:pad=0, k=3:pad=1, k=5:pad=2
+                    )
+                )
+                in_channels = out_channels
+
+        features.append(
+            CNNBlock(in_channels, last_channels, kernel_size=1, stride=1, padding=0)
+        )
+
+        return nn.Sequential(*features)
+
+    def forward(self, x):
+        x = self.pool(self.features(x))
+        return self.classifier(x.view(x.shape[0], -1))
+
+
+def test():
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    version = "b0"
+    phi, res, drop_rate = phi_values[version]
+    num_examples, num_classes = 4, 10
+    x = torch.randn((num_examples, 3, res, res)).to(device)
+    model = EfficientNet(
+        version=version,
+        num_classes=num_classes,
+    ).to(device)
+
+    print(model(x).shape) # (num_examples, num_classes)
+
+test()
+
+
+
+
+
+
+
diff --git a/ML/Pytorch/image_segmentation/semantic_segmentation_unet/__pycache__/dataset.cpython-38.pyc b/ML/Pytorch/image_segmentation/semantic_segmentation_unet/__pycache__/dataset.cpython-38.pyc
new file mode 100644
index 0000000..77534a0
Binary files /dev/null and b/ML/Pytorch/image_segmentation/semantic_segmentation_unet/__pycache__/dataset.cpython-38.pyc differ
diff --git a/ML/Pytorch/image_segmentation/semantic_segmentation_unet/__pycache__/model.cpython-38.pyc b/ML/Pytorch/image_segmentation/semantic_segmentation_unet/__pycache__/model.cpython-38.pyc
new file mode 100644
index 0000000..2ee7f20
Binary files /dev/null and b/ML/Pytorch/image_segmentation/semantic_segmentation_unet/__pycache__/model.cpython-38.pyc differ
diff --git a/ML/Pytorch/image_segmentation/semantic_segmentation_unet/__pycache__/utils.cpython-38.pyc b/ML/Pytorch/image_segmentation/semantic_segmentation_unet/__pycache__/utils.cpython-38.pyc
new file mode 100644
index 0000000..1ad0880
Binary files /dev/null and b/ML/Pytorch/image_segmentation/semantic_segmentation_unet/__pycache__/utils.cpython-38.pyc differ
diff --git a/ML/Pytorch/image_segmentation/semantic_segmentation_unet/data/note.txt b/ML/Pytorch/image_segmentation/semantic_segmentation_unet/data/note.txt
new file mode 100644
index 0000000..5a20fd9
--- /dev/null
+++ b/ML/Pytorch/image_segmentation/semantic_segmentation_unet/data/note.txt
@@ -0,0 +1,7 @@
+download the data from kaggle and put in folders similar to the video, specifically you should have 4
+folders:
+
+- train_images
+- train_masks
+- val_images
+- val_masks
diff --git a/ML/Pytorch/image_segmentation/semantic_segmentation_unet/saved_images/note.txt b/ML/Pytorch/image_segmentation/semantic_segmentation_unet/saved_images/note.txt
new file mode 100644
index 0000000..c883881
--- /dev/null
+++ b/ML/Pytorch/image_segmentation/semantic_segmentation_unet/saved_images/note.txt
@@ -0,0 +1 @@
+it will put some saved preds here so you can see how it looks like
\ No newline at end of file
diff --git a/ML/Pytorch/image_segmentation/semantic_segmentation_unet/train.py b/ML/Pytorch/image_segmentation/semantic_segmentation_unet/train.py
index fed782a..a160cb1 100644
--- a/ML/Pytorch/image_segmentation/semantic_segmentation_unet/train.py
+++ b/ML/Pytorch/image_segmentation/semantic_segmentation_unet/train.py
@@ -22,7 +22,7 @@ NUM_WORKERS = 2
 IMAGE_HEIGHT = 160  # 1280 originally
 IMAGE_WIDTH = 240  # 1918 originally
 PIN_MEMORY = True
-LOAD_MODEL = True
+LOAD_MODEL = False
 TRAIN_IMG_DIR = "data/train_images/"
 TRAIN_MASK_DIR = "data/train_masks/"
 VAL_IMG_DIR = "data/val_images/"