Updated project structure, added Dockerfile

Author: rzimmerdev

Dockerfile

@@ -0,0 +1,16 @@
+# Use the official Python image as a base image
+FROM python:3.10-slim
+
+WORKDIR /app
+
+# Install any needed packages specified in requirements.txt
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+
+COPY checkpoints/model_checkpoint.pth checkpoints/
+COPY data/test data/test
+
+COPY src/ src/
+
+RUN pwd && ls -la
+CMD ["python", "src/test.py"]

requirements.txt

@@ -1,83 +1,3 @@
-# This file may be used to create an environment using:
-# $ conda create --name <env> --file <this file>
-# platform: linux-64
-_libgcc_mutex=0.1=conda_forge
-_openmp_mutex=4.5=2_gnu
-aiohttp=3.8.6=pypi_0
-aiosignal=1.3.1=pypi_0
-async-timeout=4.0.3=pypi_0
-attrs=23.1.0=pypi_0
-bzip2=1.0.8=hd590300_5
-ca-certificates=2023.7.22=hbcca054_0
-certifi=2023.7.22=pypi_0
-charset-normalizer=3.3.2=pypi_0
-filelock=3.13.1=pypi_0
-frozenlist=1.4.0=pypi_0
-fsspec=2023.10.0=pypi_0
-idna=3.4=pypi_0
-jinja2=3.1.2=pypi_0
-ld_impl_linux-64=2.40=h41732ed_0
-libblas=3.9.0=19_linux64_openblas
-libcblas=3.9.0=19_linux64_openblas
-libffi=3.4.2=h7f98852_5
-libgcc-ng=13.2.0=h807b86a_3
-libgfortran-ng=13.2.0=h69a702a_3
-libgfortran5=13.2.0=ha4646dd_3
-libgomp=13.2.0=h807b86a_3
-liblapack=3.9.0=19_linux64_openblas
-libnsl=2.0.1=hd590300_0
-libopenblas=0.3.24=pthreads_h413a1c8_0
-libsqlite=3.44.0=h2797004_0
-libstdcxx-ng=13.2.0=h7e041cc_3
-libuuid=2.38.1=h0b41bf4_0
-libzlib=1.2.13=hd590300_5
-lightning=2.1.1=pypi_0
-lightning-utilities=0.9.0=pypi_0
-markupsafe=2.1.3=pypi_0
-mpmath=1.3.0=pypi_0
-multidict=6.0.4=pypi_0
-ncurses=6.4=h59595ed_2
-networkx=3.2.1=pypi_0
-numpy=1.26.2=pypi_0
-nvidia-cublas-cu12=12.1.3.1=pypi_0
-nvidia-cuda-cupti-cu12=12.1.105=pypi_0
-nvidia-cuda-nvrtc-cu12=12.1.105=pypi_0
-nvidia-cuda-runtime-cu12=12.1.105=pypi_0
-nvidia-cudnn-cu12=8.9.2.26=pypi_0
-nvidia-cufft-cu12=11.0.2.54=pypi_0
-nvidia-curand-cu12=10.3.2.106=pypi_0
-nvidia-cusolver-cu12=11.4.5.107=pypi_0
-nvidia-cusparse-cu12=12.1.0.106=pypi_0
-nvidia-nccl-cu12=2.18.1=pypi_0
-nvidia-nvjitlink-cu12=12.3.52=pypi_0
-nvidia-nvtx-cu12=12.1.105=pypi_0
-openssl=3.1.4=hd590300_0
-packaging=23.2=pypi_0
-pandas=2.1.3=py310hcc13569_0
-pip=23.3.1=pyhd8ed1ab_0
-python=3.10.13=hd12c33a_0_cpython
-python-dateutil=2.8.2=pyhd8ed1ab_0
-python-tzdata=2023.3=pyhd8ed1ab_0
-python_abi=3.10=4_cp310
-pytorch-lightning=2.1.1=pypi_0
-pytz=2023.3.post1=pyhd8ed1ab_0
-pyyaml=6.0.1=pypi_0
-readline=8.2=h8228510_1
-requests=2.31.0=pypi_0
-setuptools=68.2.2=pyhd8ed1ab_0
-six=1.16.0=pyh6c4a22f_0
-sympy=1.12=pypi_0
-tk=8.6.13=noxft_h4845f30_101
-torch=2.1.0=pypi_0
-torchmetrics=1.2.0=pypi_0
-tqdm=4.66.1=pypi_0
-triton=2.1.0=pypi_0
-typing-extensions=4.8.0=pypi_0
-tzdata=2023c=h71feb2d_0
-urllib3=2.1.0=pypi_0
-wheel=0.41.3=pyhd8ed1ab_0
-xz=5.2.6=h166bdaf_0
-yarl=1.9.2=pypi_0
 lightning~=2.1.1
 torch~=2.1.0
 plotly~=5.18.0

src/__init__.py

@@ -10,6 +10,7 @@ def __init__(self, input_size, hidden_size, num_heads, num_layers, num_classes,
         self.accuracy = torchmetrics.Accuracy(task='multiclass', num_classes=num_classes)
 
         self.num_classes = num_classes
+        self.confusion_matrix = torch.zeros(num_classes, num_classes)
 
         self.cnn = nn.Sequential(
             nn.Sequential(
@@ -78,24 +79,12 @@ def test_step(self, batch, batch_idx):
         y = torch.argmax(y, dim=1)
         acc = self.accuracy(pred, y)
 
-        cm = torchmetrics.functional.confusion_matrix(pred, y, task='multiclass', num_classes=self.num_classes)
-        # Can't log tensors, and cm is multiclass, so have to log each class separately
         self.log('loss', loss, on_epoch=True, on_step=False)
         self.log('accuracy', acc, on_epoch=True, on_step=False)
 
-        for i in range(self.num_classes):
-            false_positives = torch.sum(cm[:, i]) - cm[i, i]
-            false_negatives = torch.sum(cm[i, :]) - cm[i, i]
-            true_positives = cm[i, i]
-            true_negatives = torch.sum(cm) - (false_positives + false_negatives + true_positives)
-
-            precision = true_positives / (true_positives + false_positives + 1e-8)
-            recall = true_positives / (true_positives + false_negatives + 1e-8)
-            f1 = 2 * (precision * recall) / (precision + recall + 1e-8)
-
-            self.log(f'precision_{i}', precision, on_epoch=True, on_step=False)
-            self.log(f'recall_{i}', recall, on_epoch=True, on_step=False)
-            self.log(f'f1_{i}', f1, on_epoch=True, on_step=False)
+        self.confusion_matrix = (self.confusion_matrix +
+                                 torchmetrics.functional.confusion_matrix(pred.cpu(), y.cpu(), 'multiclass',
+                                                                          num_classes=self.num_classes))
 
         return loss
 

src/model.py

@@ -1,8 +1,8 @@
 import lightning
 import torch
 from torch.utils.data import DataLoader
-from src.model import MultiClassAnomaly
-from src.dataset import SeriesDataset
+from model import MultiClassAnomaly
+from dataset import SeriesDataset
 
 
 from plotly import express as px
@@ -29,7 +29,11 @@ def test(args):
 
     trainer = lightning.Trainer(default_root_dir=hyperparams['checkpoint_dir'], max_epochs=hyperparams['max_epochs'])
 
-    metrics = trainer.test(model=model, dataloaders=dataloader)
+    trainer.test(model=model, dataloaders=dataloader)
+
+    confusion_matrix = model.confusion_matrix
+    heatmap = px.imshow(confusion_matrix, labels=dict(x="Predicted", y="Actual", color="Count"), text_auto=True)
+    heatmap.show()
 
 
 if __name__ == '__main__':

src/test.py

@@ -4,8 +4,8 @@
 from torch.utils.data import DataLoader
 import lightning
 
-from src.model import MultiClassAnomaly
-from src.dataset import SeriesDataset
+from model import MultiClassAnomaly
+from dataset import SeriesDataset
 
 
 def train(args):