HPC FOLDER

Co-Authored-By: Dong Han <dong.han@uconn.edu>

HPC/final_project/active_learning/ss_active_learning.py

@@ -0,0 +1,86 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Dec 18 18:23:23 2023
+
+@author: lrm22005
+"""
+import numpy as np
+import random
+import torch
+from torch.utils.data import DataLoader
+from sklearn.cluster import MiniBatchKMeans
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+def label_samples(uncertain_samples, validation_data):
+    labels = [validation_data[sample_id]['label'] for sample_id in uncertain_samples]
+    return uncertain_samples, labels
+
+def stochastic_uncertainty_sampling(gp_model, gp_likelihood, val_loader, n_samples, n_batches, n_components=2):
+    gp_model.eval()
+    gp_likelihood.eval()
+    uncertain_sample_indices = []
+    sampled_batches = random.sample(list(val_loader), n_batches)  # Randomly sample n_batches from val_loader
+
+    with torch.no_grad():
+        for batch in sampled_batches:
+            # reduced_data = apply_tsne(batch['data'].reshape(batch['data'].size(0), -1), n_components=n_components)
+            # reduced_data_tensor = torch.Tensor(reduced_data).to(device)
+            reduced_data_tensor = batch['data'].view(batch['data'].size(0), -1).to(device)
+            predictions = gp_likelihood(gp_model(reduced_data_tensor))
+            var = predictions.variance
+            top_indices = torch.argsort(-var.flatten())[:n_samples]
+            uncertain_sample_indices.extend(top_indices.cpu().numpy())
+
+    return uncertain_sample_indices[:n_samples]
+
+# def uncertainty_sampling(gp_model, gp_likelihood, val_loader, n_samples, n_components=2):
+#     gp_model.eval()
+#     gp_likelihood.eval()
+#     uncertain_sample_indices = []
+#     with torch.no_grad():
+#         for batch_idx, batch in tqdm(enumerate(val_loader), desc='Uncertainty Sampling', unit='batch'):
+#             reduced_data_tensor = batch['data'].view(batch['data'].size(0), -1).to(device)
+#             predictions = gp_likelihood(gp_model(reduced_data_tensor))
+#             var = predictions.variance
+#             top_indices = torch.argsort(-var.flatten())[:n_samples]
+#             batch_uncertain_indices = [batch_idx * val_loader.batch_size + idx for idx in top_indices]
+#             uncertain_sample_indices.extend(batch_uncertain_indices)
+#     return uncertain_sample_indices[:n_samples]
+
+def run_minibatch_kmeans(data_loader, n_clusters, device, batch_size=100):
+    # Initialize MiniBatchKMeans
+    minibatch_kmeans = MiniBatchKMeans(n_clusters=n_clusters, random_state=0, batch_size=batch_size)
+
+    # Iterate through data_loader and fit MiniBatchKMeans
+    for batch in data_loader:
+        data = batch['data'].view(batch['data'].size(0), -1).to(device).cpu().numpy()
+        minibatch_kmeans.partial_fit(data)
+
+    return minibatch_kmeans
+
+# def compare_kmeans_gp_predictions(kmeans_model, gp_model, data_loader, device):
+#     # Compare K-Means with GP model predictions
+#     all_data, all_labels = [], []
+#     for batch in data_loader:
+#         data = batch['data'].view(batch['data'].size(0), -1).to(device)
+#         labels = batch['label'].to(device)
+#         gp_predictions = gp_model(data).mean.argmax(dim=0).cpu().numpy()
+#         kmeans_predictions = kmeans_model.predict(data.cpu().numpy())
+#         all_labels.append(labels.cpu().numpy())
+#         all_data.append((gp_predictions, kmeans_predictions))
+#     return all_data, np.concatenate(all_labels)
+
+def stochastic_compare_kmeans_gp_predictions(kmeans_model, gp_model, data_loader, n_batches, device):
+    all_data, all_labels = [], []
+    sampled_batches = random.sample(list(data_loader), n_batches)  # Randomly sample n_batches from data_loader
+
+    for batch in sampled_batches:
+        data = batch['data'].view(batch['data'].size(0), -1).to(device)
+        labels = batch['label'].to(device)
+        gp_predictions = gp_model(data).mean.argmax(dim=0).cpu().numpy()
+        kmeans_predictions = kmeans_model.predict(data.cpu().numpy())
+        all_labels.append(labels.cpu().numpy())
+        all_data.append((gp_predictions, kmeans_predictions))
+
+    return all_data, np.concatenate(all_labels)