Compare commits
No commits in common. "0fb1f69b1f6f0813120e6fd0d2a8086c1bb70f78" and "30feb25e942f211c9c171793fa22bb64c93be788" have entirely different histories.
0fb1f69b1f
...
30feb25e94
2 changed files with 131 additions and 292 deletions
|
|
@ -2,7 +2,7 @@
|
|||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -37,7 +37,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -61,25 +61,6 @@
|
|||
"X_train, X_val = X_train.T, X_val.T"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"Data shapes:\")\n",
|
||||
"print(f\"X_train shape: {X_train.shape}\")\n",
|
||||
"print(f\"Y_train shape: {Y_train.shape}\")\n",
|
||||
"print(f\"X_test shape: {X_test.shape}\")\n",
|
||||
"print(f\"Y_test shape: {Y_test.shape}\")\n",
|
||||
"\n",
|
||||
"print(\"\\nData statistics:\")\n",
|
||||
"print(f\"X_train mean: {xp.mean(X_train)}, std: {xp.std(X_train)}\")\n",
|
||||
"print(f\"X_test mean: {xp.mean(X_test)}, std: {xp.std(X_test)}\")\n",
|
||||
"print(f\"Unique Y_train values: {xp.unique(Y_train)}\")\n",
|
||||
"print(f\"Unique Y_test values: {xp.unique(Y_test)}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
|
|
@ -96,7 +77,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 26,
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -107,7 +88,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -124,7 +105,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 28,
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -132,8 +113,8 @@
|
|||
" return xp.maximum(Z, 0)\n",
|
||||
"\n",
|
||||
"def softmax(Z):\n",
|
||||
" exp_Z = xp.exp(Z - xp.max(Z, axis=0, keepdims=True))\n",
|
||||
" return exp_Z / xp.sum(exp_Z, axis=0, keepdims=True)\n",
|
||||
" A = xp.exp(Z) / sum(xp.exp(Z))\n",
|
||||
" return A\n",
|
||||
"\n",
|
||||
"def forward_prop(X, params):\n",
|
||||
" caches = []\n",
|
||||
|
|
@ -209,7 +190,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -232,10 +213,6 @@
|
|||
" val_accuracy = get_accuracy(val_predictions, Y_val)\n",
|
||||
" \n",
|
||||
" print(f\"Iteration {i}: Train Accuracy: {train_accuracy:.4f}, Validation Accuracy: {val_accuracy:.4f}\")\n",
|
||||
" print(f\"Sample predictions: {train_predictions[:10]}\")\n",
|
||||
" print(f\"Sample true labels: {Y_train[:10]}\")\n",
|
||||
" \n",
|
||||
" print(f\"Iteration {i}: Train Accuracy: {train_accuracy:.4f}, Validation Accuracy: {val_accuracy:.4f}\")\n",
|
||||
" acc_store.append((train_accuracy, val_accuracy))\n",
|
||||
" \n",
|
||||
" if val_accuracy > best_val_accuracy:\n",
|
||||
|
|
@ -252,7 +229,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -271,7 +248,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"execution_count": 17,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -307,24 +284,15 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 32,
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"hidden_layers = [1, 2]\n",
|
||||
"neurons_per_layer = [64, 128, 256, 512]\n",
|
||||
"hidden_layers = [1, 2, 3, 4]\n",
|
||||
"neurons_per_layer = [64, 128, 256]\n",
|
||||
"layer_configs = list(product(*[neurons_per_layer] * max(hidden_layers)))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(layer_configs)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
|
|
@ -347,17 +315,6 @@
|
|||
"print(f\"Best validation accuracy: {best_accuracy:.4f}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(\"\\nModel Architecture:\")\n",
|
||||
"for i in range(1, len(best_params)//2 + 1):\n",
|
||||
" print(f\"Layer {i}: {best_params[f'W{i}'].shape}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
|
|
|
|||
|
|
@ -2,21 +2,15 @@
|
|||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import torch\n",
|
||||
"import net.modules\n",
|
||||
"\n",
|
||||
"import torch.nn as nn\n",
|
||||
"import torch.optim as optim\n",
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"\n",
|
||||
"from torch.utils.data import DataLoader, TensorDataset\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"from tqdm import tqdm"
|
||||
"from net.transcoder import Transcoder"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -25,170 +19,10 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Check if CUDA is available\n",
|
||||
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
|
||||
"print(f\"Using device: {device}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = pd.read_csv('data/bel_data_test.csv')\n",
|
||||
"# Load the data\n",
|
||||
"data = np.array(data)\n",
|
||||
"filepath = 'data/bel_data_test.csv'\n",
|
||||
"train_loader, test_loader, input_size = load_and_prepare_data(file_path=filepath)\n",
|
||||
"\n",
|
||||
"# Split features and labels\n",
|
||||
"X = data[:, 1:] # All columns except the first one\n",
|
||||
"y = data[:, 0].astype(int) # First column as labels\n",
|
||||
"\n",
|
||||
"# Split the data into training and testing sets\n",
|
||||
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Convert to PyTorch tensors\n",
|
||||
"X_train_tensor = torch.FloatTensor(X_train)\n",
|
||||
"y_train_tensor = torch.LongTensor(y_train)\n",
|
||||
"X_test_tensor = torch.FloatTensor(X_test)\n",
|
||||
"y_test_tensor = torch.LongTensor(y_test)\n",
|
||||
"\n",
|
||||
"# Create DataLoader objects\n",
|
||||
"train_dataset = TensorDataset(X_train_tensor, y_train_tensor)\n",
|
||||
"test_dataset = TensorDataset(X_test_tensor, y_test_tensor)\n",
|
||||
"\n",
|
||||
"train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)\n",
|
||||
"test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Define the MLP\n",
|
||||
"class MLP(nn.Module):\n",
|
||||
" def __init__(self):\n",
|
||||
" super(MLP, self).__init__()\n",
|
||||
" self.input_layer = nn.Linear(1024, 512)\n",
|
||||
" self.h1_layer = nn.Linear(512, 64)\n",
|
||||
" self.h2_layer = nn.Linear(64, 62)\n",
|
||||
" self.relu = nn.ReLU()\n",
|
||||
"\n",
|
||||
" def forward(self, x):\n",
|
||||
" x = self.relu(self.input_layer(x))\n",
|
||||
" x = self.h1_layer(x)\n",
|
||||
" x = self.h2_layer(x)\n",
|
||||
" return x\n",
|
||||
"\n",
|
||||
"# Define the Decoder\n",
|
||||
"class Decoder(nn.Module):\n",
|
||||
" def __init__(self):\n",
|
||||
" super(Decoder, self).__init__()\n",
|
||||
" self.h2_h1 = nn.Linear(64, 512)\n",
|
||||
" self.h1_input = nn.Linear(512, 1024)\n",
|
||||
" self.relu = nn.ReLU()\n",
|
||||
"\n",
|
||||
" def forward(self, x):\n",
|
||||
" x = self.relu(self.h2_h1(x))\n",
|
||||
" x = self.h1_input(x)\n",
|
||||
" return x\n",
|
||||
"\n",
|
||||
"class MLPWithDecoder(nn.Module):\n",
|
||||
" def __init__(self):\n",
|
||||
" super(MLPWithDecoder, self).__init__()\n",
|
||||
" self.mlp = MLP()\n",
|
||||
" self.decoder = Decoder()\n",
|
||||
"\n",
|
||||
" def forward(self, x):\n",
|
||||
" # MLP forward pass\n",
|
||||
" h1 = self.mlp.relu(self.mlp.input_layer(x))\n",
|
||||
" h2 = self.mlp.relu(self.mlp.h1_layer(h1))\n",
|
||||
" output = self.mlp.h2_layer(h2)\n",
|
||||
" \n",
|
||||
" # Reconstruction\n",
|
||||
" reconstruction = self.decoder(h2)\n",
|
||||
" \n",
|
||||
" return output, reconstruction"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Function to reconstruct an image\n",
|
||||
"def reconstruct_image(model, image):\n",
|
||||
" model.eval()\n",
|
||||
" with torch.no_grad():\n",
|
||||
" _, reconstruction = model(image.unsqueeze(0))\n",
|
||||
" return reconstruction.squeeze(0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def show_image_comparison(original, reconstructed, label, prediction):\n",
|
||||
" \"\"\"\n",
|
||||
" Display the original and reconstructed images side by side.\n",
|
||||
" \n",
|
||||
" :param original: Original image (1D tensor of 1024 elements)\n",
|
||||
" :param reconstructed: Reconstructed image (1D tensor of 1024 elements)\n",
|
||||
" :param label: True label of the image\n",
|
||||
" :param prediction: Predicted label of the image\n",
|
||||
" \"\"\"\n",
|
||||
" # Convert to numpy arrays and move to CPU if they're on GPU\n",
|
||||
" original = original.cpu().numpy()\n",
|
||||
" reconstructed = reconstructed.cpu().numpy()\n",
|
||||
" \n",
|
||||
" # Reshape the 1D arrays to 32x32 images\n",
|
||||
" original_img = original.reshape(32, 32)\n",
|
||||
" reconstructed_img = reconstructed.reshape(32, 32)\n",
|
||||
" \n",
|
||||
" # Create a figure with two subplots side by side\n",
|
||||
" fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 5))\n",
|
||||
" \n",
|
||||
" # Show original image\n",
|
||||
" ax1.imshow(original_img, cmap='gray')\n",
|
||||
" ax1.set_title(f'Original (Label: {label})')\n",
|
||||
" ax1.axis('off')\n",
|
||||
" \n",
|
||||
" # Show reconstructed image\n",
|
||||
" ax2.imshow(reconstructed_img, cmap='gray')\n",
|
||||
" ax2.set_title(f'Reconstructed (Predicted: {prediction})')\n",
|
||||
" ax2.axis('off')\n",
|
||||
" \n",
|
||||
" plt.tight_layout()\n",
|
||||
" plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Initialize the model, loss function, and optimizer\n",
|
||||
"model = MLPWithDecoder()\n",
|
||||
"criterion = nn.CrossEntropyLoss()\n",
|
||||
"reconstruction_criterion = nn.MSELoss()\n",
|
||||
"optimizer = optim.Adam(model.parameters())\n",
|
||||
"\n",
|
||||
"model = model.to(device)\n",
|
||||
"criterion = criterion.to(device)\n",
|
||||
"reconstruction_criterion = reconstruction_criterion.to(device)"
|
||||
"print(\"X_train shape:\", input_size.shape)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -197,36 +31,19 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"num_epochs = 250\n",
|
||||
"for epoch in range(num_epochs):\n",
|
||||
" model.train() # Set the model to training mode\n",
|
||||
" running_loss = 0.0\n",
|
||||
"# input_size = X_train.shape[0]\n",
|
||||
"# hidden_size = 128\n",
|
||||
"# output_size = 61\n",
|
||||
"\n",
|
||||
" # Use tqdm for a progress bar\n",
|
||||
" with tqdm(train_loader, unit=\"batch\") as tepoch:\n",
|
||||
" for images, labels in tepoch:\n",
|
||||
" tepoch.set_description(f\"Epoch {epoch+1}\")\n",
|
||||
" \n",
|
||||
" images, labels = images.to(device), labels.to(device)\n",
|
||||
" \n",
|
||||
" optimizer.zero_grad()\n",
|
||||
" \n",
|
||||
" outputs, reconstructions = model(images)\n",
|
||||
" \n",
|
||||
" classification_loss = criterion(outputs, labels)\n",
|
||||
" reconstruction_loss = reconstruction_criterion(reconstructions, images)\n",
|
||||
" total_loss = classification_loss + reconstruction_loss\n",
|
||||
" \n",
|
||||
" total_loss.backward()\n",
|
||||
" optimizer.step()\n",
|
||||
" \n",
|
||||
" running_loss += total_loss.item()\n",
|
||||
" \n",
|
||||
" tepoch.set_postfix(loss=total_loss.item())\n",
|
||||
" \n",
|
||||
" epoch_loss = running_loss / len(train_loader)\n",
|
||||
" \n",
|
||||
" # print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {epoch_loss:.4f}')"
|
||||
"architecture = [input_size, [128], 61]\n",
|
||||
"activations = ['leaky_relu','softmax']"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Initialize transcoder"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -235,40 +52,105 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model.eval() # Set the model to evaluation mode\n",
|
||||
"with torch.no_grad():\n",
|
||||
" try:\n",
|
||||
" # Get a batch of test data\n",
|
||||
" images, labels = next(iter(test_loader))\n",
|
||||
"# bl_transcoder = Transcoder(input_size, hidden_size, output_size, 'leaky_relu', 'softmax')\n",
|
||||
"bl_transcoder = Transcoder(architecture, hidden_activation='relu', output_activation='softmax')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train Encoders and save weights\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# # Train the encoder if need\n",
|
||||
"\n",
|
||||
" # Move data to the same device as the model\n",
|
||||
" images = images.to(device)\n",
|
||||
" labels = labels.to(device)\n",
|
||||
"bl_transcoder.train_model(train_loader, test_loader, learning_rate=0.001, epochs=1000)\n",
|
||||
"# bl_transcoder.train_with_validation(X_train, Y_train, alpha=0.1, iterations=1000)\n",
|
||||
"bl_transcoder.save_results('bt_1h128n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load weights"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"bl_transcoder.load_weights('weights/bt_1h128n_leaky_relu_weights.pth')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Analysis"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Plot learning curves\n",
|
||||
"bl_transcoder.plot_learning_curves()\n",
|
||||
"\n",
|
||||
" # Forward pass through the model\n",
|
||||
" outputs, reconstructions = model(images)\n",
|
||||
"# Visualize encoded space\n",
|
||||
"bl_transcoder.plot_encoded_space(X_test, Y_test)\n",
|
||||
"\n",
|
||||
" # Get predicted labels\n",
|
||||
" _, predicted = torch.max(outputs.data, 1)\n",
|
||||
"print(X_test.shape)\n",
|
||||
"print(X_train.shape)\n",
|
||||
"# Check reconstructions\n",
|
||||
"bl_transcoder.plot_reconstructions(X_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Transcode images"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"num_images = 2\n",
|
||||
"indices = np.random.choice(X_test.shape[1], num_images, replace=False)\n",
|
||||
"\n",
|
||||
" # Display the first few images in the batch\n",
|
||||
" num_images_to_show = min(5, len(images))\n",
|
||||
" for i in range(num_images_to_show):\n",
|
||||
" show_image_comparison(\n",
|
||||
" images[i], \n",
|
||||
" reconstructions[i], \n",
|
||||
" labels[i].item(), \n",
|
||||
" predicted[i].item()\n",
|
||||
" )\n",
|
||||
"for idx in indices:\n",
|
||||
" original_image = X_test[:, idx]\n",
|
||||
" \n",
|
||||
" # Calculate and print accuracy\n",
|
||||
" correct = (predicted == labels).sum().item()\n",
|
||||
" total = labels.size(0)\n",
|
||||
" accuracy = 100 * correct / total\n",
|
||||
" print(f'Test Accuracy: {accuracy:.2f}%')\n",
|
||||
" # Encode the image\n",
|
||||
" encoded = bl_transcoder.encode_image(original_image.reshape(-1, 1))\n",
|
||||
" \n",
|
||||
" except Exception as e:\n",
|
||||
" print(f\"An error occurred during evaluation: {str(e)}\")"
|
||||
" # Decode the image\n",
|
||||
" decoded = bl_transcoder.decode_image(encoded)\n",
|
||||
"\n",
|
||||
" # Visualize original, encoded, and decoded images\n",
|
||||
" visualize_transcoding(original_image, encoded, decoded, idx)\n",
|
||||
"\n",
|
||||
" print(f\"Image {idx}:\")\n",
|
||||
" print(\"Original shape:\", original_image.shape)\n",
|
||||
" print(\"Encoded shape:\", encoded.shape)\n",
|
||||
" print(\"Decoded shape:\", decoded.shape)\n",
|
||||
" print(\"Encoded vector:\", encoded.flatten()) # Print flattened encoded vector\n",
|
||||
" print(\"\\n\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue