added rnn

teng-ml/main.py

@@ -11,10 +11,10 @@ import matplotlib.pyplot as plt
 import pandas as pd
 import torch
 import torch.nn as nn
+import torch.nn.utils.rnn as rnn_utils
 from torch.utils.data import DataLoader
 
-
+from .util.transform import ConstantInterval, Normalize
-from .util.transform import ConstantInterval
 from .util.data_loader import load_datasets, LabelConverter
 
 def test_interpol():
@@ -24,7 +24,7 @@ def test_interpol():
     array = df.to_numpy()
     print(ConstantInterval.get_average_interval(array[:,0]))
     transformer = ConstantInterval(0.05)
-    interp_array = transformer(array[:,0], array[:,2])
+    interp_array = transformer(array[:,[0,2]])
 
     fig1, ax1 = plt.subplots()
     ax1.plot(interp_array[:,0], interp_array[:,1], color="r", label="Interpolated")
@@ -42,15 +42,22 @@ if __name__ == "__main__":
     )
     print(f"Using device: {device}")
 
-    labels = LabelConverter(["foam", "glass", "kapton", "foil"])
+    labels = LabelConverter(["foam", "glass", "kapton", "foil", "cloth", "rigid_foam"])
-    train_set, test_set = load_datasets("/home/matth/data", labels, voltage=8.2)
+    t_const_int = ConstantInterval(0.01)
+    t_norm = Normalize(0, 1)
+    train_set, test_set = load_datasets("/home/matth/Uni/TENG/testdata", labels, voltage=8.2, transforms=[t_const_int], train_to_test_ratio=0.7, random_state=42)
 
     # train_loader = iter(DataLoader(train_set))
     # test_loader = iter(DataLoader(test_set))
-    # sample = next(train_loader)
+    train_loader = iter(DataLoader(train_set, batch_size=3, shuffle=True))
-    # print(sample)
+    test_loader = iter(DataLoader(test_set, batch_size=3, shuffle=True))
-    train_loader = iter(DataLoader(train_set))
+
-    test_loader = iter(DataLoader(test_set))
+    sample = next(train_loader)
+    print(sample)
+
+    feature_count = 1
+
+
     class RNN(nn.Module):
         def __init__(self, input_size, hidden_size, num_layers, num_classes, if_bidirectional):
             super(RNN, self).__init__()
@@ -58,6 +65,7 @@ if __name__ == "__main__":
             self.hidden_size = hidden_size
             self.if_bidirectional = if_bidirectional
             self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True, bidirectional=if_bidirectional)
+            # x = (batch_size, sequence, feature)
 
             if if_bidirectional == True:
               self.fc = nn.Linear(hidden_size * 2, num_classes)
@@ -66,14 +74,21 @@ if __name__ == "__main__":
 
 
         def forward(self, x):
+            print(f"forward pass")
             D = 2 if self.if_bidirectional == True else 1
-            Batch = x.batch_sizes[0]
 
-            h0 = torch.zeros(D * self.num_layers, Batch, self.hidden_size).to(device)
+            print(f"x({x.shape})={x}")
-            c0 = torch.zeros(D * self.num_layers, Batch, self.hidden_size).to(device)
+            batch_size = x.shape[1]
+            print(f"batch_size={batch_size}")
+
+            h0 = torch.zeros(D * self.num_layers, batch_size, self.hidden_size).to(device)
+            print(f"h0={h0}")
+            c0 = torch.zeros(D * self.num_layers, batch_size, self.hidden_size).to(device)
             x.to(device)
             _, (h_n, _) = self.lstm(x, (h0, c0))
-            final_state  = h_n.view(self.num_layers, D, Batch, self.hidden_size)[-1]     # num_layers, num_directions, batch, hidden_size
+            print(f"h_n={h_n}")
+            final_state  = h_n.view(self.num_layers, D, batch_size, self.hidden_size)[-1]     # num_layers, num_directions, batch, hidden_size
+            print(f"final_state={final_state}")
 
             if D == 1:
               X = final_state.squeeze()
@@ -81,8 +96,10 @@ if __name__ == "__main__":
               h_1, h_2 = final_state[0], final_state[1]  # forward & backward pass
               #X = h_1 + h_2                # Add both states
               X = torch.cat((h_1, h_2), 1)         # Concatenate both states, X-size: (Batch, hidden_size * 2）
-
+            else:
+                raise ValueError("D must be 1 or 2")
             output = self.fc(X) # fully-connected layer
+            print(f"out={output}")
 
             return output
 
@@ -99,10 +116,18 @@ if __name__ == "__main__":
         train_total = 0
         val_correct = 0
         val_total = 0
-        for (x, y), length in train_loader: 
+        for data, y in train_loader:
+            # data = batch, seq, features
+            print(ep, "Train")
+            print(f"data({data.shape})={data}")
+            x = data[:,:,2]   # select voltage data
+            print(f"x({x.shape})={x}")
+            length = torch.tensor([x.shape[1] for _ in range(x.shape[0])], dtype=torch.int64)
+            print(f"length({length.shape})={length}")
             batch_size = x.shape[0]
-            v = x.view(batch_size, -1, nFeatrue)
+            print(f"batch_size={batch_size}")
-            data = rnn_utils.pack_padded_sequence(v.type(torch.FloatTensor), length, batch_first=True).to(device)
+            v = x.view(batch_size, -1, feature_count)
+            data = rnn_utils.pack_padded_sequence(v.type(torch.FloatTensor), length, batch_first=True).to(device)[0]
             # print(data.batch_sizes[0])
             # print(data)
             out = model(data)
@@ -117,12 +142,17 @@ if __name__ == "__main__":
             train_total += y.size(0)
             train_correct += (predicted == y).sum().item()
 
-
         scheduler.step()
 
-        for (x, y), length in test_loader: 
+        for data, y in test_loader:
+            print(ep, "Test")
+            x = data[:,2]
+            print(f"x({x.shape})={x}")
+            length = torch.tensor(x.shape[0], dtype=torch.int64)
+            print(f"length={length}")
             batch_size = x.shape[0]
-            v = x.view(batch_size, -1, nFeatrue)
+            print(f"batch_size={batch_size}")
+            v = x.view(batch_size, -1, feature_count)
             data = rnn_utils.pack_padded_sequence(v.type(torch.FloatTensor), length, batch_first=True).to(device)
             out = model(data)
             loss = loss_func(out, y)

teng-ml/util/data_loader.py

@@ -60,18 +60,26 @@ class Dataset:
     """
     Store the whole dataset, compatible with torch.data.Dataloader
     """
-    def __init__(self, datasamples):
+    def __init__(self, datasamples, transforms=None):
         self.datasamples = datasamples
+        self.transforms = transforms
         # self.labels = [ d.label_vec for d in datasamples ]
         # self.data = [ d.get_data() for d in datasamples ]
 
     def __getitem__(self, index):
-        return self.datasamples[index].get_data(), self.datasamples[index].label_vec
+        data, label = self.datasamples[index].get_data(), self.datasamples[index].label_vec
+        if type(self.transforms) == list:
+            for t in self.transforms:
+                data = t(data)
+        elif self.transforms:
+            data = self.transforms(data)
+        # TODO
+        return data[:400], label
 
     def __len__(self):
         return len(self.datasamples)
 
-def load_datasets(datadir, labels: LabelConverter, voltage=None, train_to_test_ratio=0.7, random_state=None):
+def load_datasets(datadir, labels: LabelConverter, transforms=None, voltage=None, train_to_test_ratio=0.7, random_state=None):
     """
     load all data from datadir that are in the format: yyyy-mm-dd_label_x.xV_xxxmm.csv
     """
@@ -90,6 +98,6 @@ def load_datasets(datadir, labels: LabelConverter, voltage=None, train_to_test_r
 
         datasamples.append(Datasample(*match.groups(), labels.get_one_hot(label), datadir + "/" + file))
     train_samples, test_samples = train_test_split(datasamples, train_size=train_to_test_ratio, shuffle=True, random_state=random_state)
-    train_dataset = Dataset(train_samples)
+    train_dataset = Dataset(train_samples, transforms=transforms)
-    test_dataset = Dataset(test_samples)
+    test_dataset = Dataset(test_samples, transforms=transforms)
     return train_dataset, test_dataset

teng-ml/util/transform.py

@@ -25,20 +25,24 @@ class ConstantInterval:
     """
     Interpolate the data to have a constant interval / sample rate,
     so that 1 index step is always equivalent to a certain time step
-    Expects: timestamps, idata, vdata
     """
     def __init__(self, interval):
         self.interval = interval
 
-    def __call__(self, timestamps, data):
+    def __call__(self, a):
-        interp = interp1d(timestamps, data)
+        """
-        new_stamps = np.arange(0, timestamps[-1], self.interval)
+        array: [timestamps, data1, data2...]
-        print(f"old=({timestamps.size}) {timestamps}, new=({new_stamps.size}){new_stamps}")
+        """
-
+        timestamps = a[:,0]
+        new_stamps = np.arange(timestamps[0], timestamps[-1], self.interval)
+        ret = new_stamps
+        for i in range(1, a.shape[1]):  # 
+            interp = interp1d(timestamps, a[:,i])
             new_vals = interp(new_stamps)
-        return np.vstack((new_stamps, new_vals)).T
+            ret = np.vstack((ret, new_vals))
-    @staticmethod
+        return ret.T
 
+    @staticmethod
     def get_average_interval(timestamps):
         avg_interval = np.average([ timestamps[i] - timestamps[i-1] for i in range(1, len(timestamps))])
         return avg_interval