Ultralytics Code Refactor https://ultralytics.com/actions

README.md

@@ -41,7 +41,7 @@ You can run the WAVE models using the following scripts:
 
 Explore the beauty of waveform signals and training process visualization with the images below:
 
-![Waveform Signals](https://github.com/ultralytics/wave/blob/main/data/waveforms.png "Waveform signals captured by the detector.") ![Training Visualization](https://github.com/ultralytics/wave/blob/main/data/wave.png "Visualization of the training process.")
+![Waveform Signals](https://github.com/ultralytics/wave/blob/main/data/waveforms.png%20%22Waveform%20signals%20captured%20by%20the%20detector.%22) ![Training Visualization](https://github.com/ultralytics/wave/blob/main/data/wave.png%20%22Visualization%20of%20the%20training%20process.%22)
 
 # 📜 Citation
 
@@ -51,20 +51,20 @@ If you use this code in your research or wish to refer to the WAVE methodology,
 
 # 🤝 Contribute
 
-We value each contribution and invite you to participate in developing this pioneering ML approach for physics! Whether you're sharpening bugs, proposing new features, or enriching our documentation, find out how to contribute through our [Contributing Guide](https://docs.ultralytics.com/help/contributing). Also, let us know your thoughts by completing our [Survey](https://ultralytics.com/survey?utm_source=github&utm_medium=social&utm_campaign=Survey). A massive thank you 🙏 to everyone involved!
+We value each contribution and invite you to participate in developing this pioneering ML approach for physics! Whether you're sharpening bugs, proposing new features, or enriching our documentation, find out how to contribute through our [Contributing Guide](https://docs.ultralytics.com/help/contributing). Also, let us know your thoughts by completing our [Survey](https://www.ultralytics.com/survey?utm_source=github&utm_medium=social&utm_campaign=Survey). A massive thank you 🙏 to everyone involved!
 
-![Ultralytics Open-Source Contributors](https://github.com/ultralytics/assets/raw/main/im/image-contributors.png "Thanks to our community of contributors!")
+![Ultralytics Open-Source Contributors](https://github.com/ultralytics/assets/raw/main/im/image-contributors.png%20%22Thanks%20to%20our%20community%20of%20contributors!%22)
 
 # 📄 License
 
 Ultralytics is pleased to offer dual licensing options to accommodate a wide range of uses:
 
 - **AGPL-3.0 License**: Our default [open-source license](https://github.com/ultralytics/ultralytics/blob/main/LICENSE), which is OSI-approved and encourages open collaboration and knowledge sharing, is perfect for students, educators, and enthusiasts.
-- **Enterprise License**: For commercial applications that require a more flexible licensing arrangement, our enterprise license allows integration of Ultralytics software into proprietary products and services. Reach out through [Ultralytics Licensing](https://ultralytics.com/license) for more details.
+- **Enterprise License**: For commercial applications that require a more flexible licensing arrangement, our enterprise license allows integration of Ultralytics software into proprietary products and services. Reach out through [Ultralytics Licensing](https://www.ultralytics.com/license) for more details.
 
 # 📬 Contact Us
 
-For bug reports, feature requests, and contributions, head to [GitHub Issues](https://github.com/ultralytics/velocity/issues). For questions and discussions about this project and other Ultralytics endeavors, join us on [Discord](https://ultralytics.com/discord)!
+For bug reports, feature requests, and contributions, head to [GitHub Issues](https://github.com/ultralytics/velocity/issues). For questions and discussions about this project and other Ultralytics endeavors, join us on [Discord](https://discord.com/invite/ultralytics)!
 
 <br>
 <div align="center">

gcp/wave_pytorch_gcp.py

@@ -28,11 +28,11 @@ def runexample(H, model, str, lr=0.001, amsgrad=False):
 
     cuda = torch.cuda.is_available()
     os.makedirs(f"{pathr}models", exist_ok=True)
-    name = (data[:-4] + "%s%glr%s" % (H[:], lr, str)).replace(", ", ".").replace("[", "_").replace("]", "_")
+    name = (data[:-4] + f"{H[:]}{lr:g}lr{str}").replace(", ", ".").replace("[", "_").replace("]", "_")
 
     tica = time.time()
     device = torch.device("cuda:0" if cuda else "cpu")
-    print("Running %s on %s\n%s" % (name, device.type, torch.cuda.get_device_properties(0) if cuda else ""))
+    print("Running {} on {}\n{}".format(name, device.type, torch.cuda.get_device_properties(0) if cuda else ""))
 
     if not os.path.isfile(pathd + data):
         os.system(f"wget -P data/ https://storage.googleapis.com/ultralytics/{data}")
@@ -75,7 +75,7 @@ def runexample(H, model, str, lr=0.001, amsgrad=False):
             if L[i, 1] < best[1]:
                 best = (i, L[i, 1], copy.deepcopy(model.state_dict()))
             if (i - best[0]) > validations:
-                print("\n%g validation checks exceeded at epoch %g." % (validations, i))
+                print(f"\n{validations:g} validation checks exceeded at epoch {i:g}.")
                 break
 
         if i % printInterval == 0:  # print and save progress
@@ -94,11 +94,11 @@ def runexample(H, model, str, lr=0.001, amsgrad=False):
     model.load_state_dict(best[2])
     dt = time.time() - tica
 
-    print("\nFinished %g epochs in %.3fs (%.3f epochs/s)\nBest results from epoch %g:" % (i + 1, dt, i / dt, best[0]))
+    print(f"\nFinished {i + 1:g} epochs in {dt:.3f}s ({i / dt:.3f} epochs/s)\nBest results from epoch {best[0]:g}:")
     loss, std = np.zeros(3), np.zeros((3, ny))
     for i, (xi, yi) in enumerate(((x, y), (xv, yv), (xt, yt))):
         loss[i], std[i] = stdpt(model(xi) - yi, ys)
-        print("%.5f %s %s" % (loss[i], std[i, :], labels[i]))
+        print(f"{loss[i]:.5f} {std[i, :]} {labels[i]}")
     # scipy.io.savemat(pathr + name + '.mat', dict(bestepoch=best[0], loss=loss, std=std, L=L, name=name))
     # files.download(pathr + name + '.mat')
 
@@ -117,11 +117,13 @@ def runexample(H, model, str, lr=0.001, amsgrad=False):
 
 
 class LinearAct(torch.nn.Module):
+    """Applies a linear transformation followed by a Tanh activation to input tensors for neural network layers."""
+
     def __init__(self, nx, ny):
         """Initializes the LinearAct module with input and output dimensions and defines a linear transformation
         followed by a Tanh activation.
         """
-        super(LinearAct, self).__init__()
+        super().__init__()
         self.Linear1 = torch.nn.Linear(nx, ny)
         self.act = torch.nn.Tanh()
 
@@ -131,9 +133,11 @@ def forward(self, x):
 
 
 class WAVE(torch.nn.Module):
+    """A neural network model for processing waveform data using linear layers and activation functions."""
+
     def __init__(self, n):  # n = [512, 108, 23, 5, 1]
         """Initializes the WAVE model with specified linear layers and activation functions."""
-        super(WAVE, self).__init__()
+        super().__init__()
         self.fc0 = LinearAct(n[0], n[1])
         self.fc1 = LinearAct(n[1], n[2])
         self.fc2 = torch.nn.Linear(n[2], n[3])
@@ -156,7 +160,7 @@ def tsact():  # TS activation function
 
         class LinearAct(torch.nn.Module):
             def __init__(self, nx, ny):
-                super(LinearAct, self).__init__()
+                super().__init__()
                 self.Linear1 = torch.nn.Linear(nx, ny)
                 self.act = eval(f"torch.nn.{a}()")
 
@@ -165,7 +169,7 @@ def forward(self, x):
 
         class WAVE(torch.nn.Module):
             def __init__(self, n):  # n = [512, 108, 23, 5, 1]
-                super(WAVE, self).__init__()
+                super().__init__()
                 self.fc0 = LinearAct(n[0], n[1])
                 self.fc1 = LinearAct(n[1], n[2])
                 self.fc2 = torch.nn.Linear(n[2], n[3])
@@ -189,7 +193,7 @@ def tsnoact():  # TS activation function
 
         class WAVE(torch.nn.Module):
             def __init__(self, n):  # n = [512, 108, 23, 5, 1]
-                super(WAVE, self).__init__()
+                super().__init__()
                 self.fc0 = torch.nn.Linear(n[0], n[1])
                 self.fc1 = torch.nn.Linear(n[1], n[2])
                 self.fc2 = torch.nn.Linear(n[2], n[3])
@@ -242,7 +246,7 @@ def tsshape():  # TS network shape
 
     class WAVE(torch.nn.Module):
         def __init__(self, n):  # n = [512, 108, 23, 5, 1]
-            super(WAVE, self).__init__()
+            super().__init__()
             self.fc0 = LinearAct(n[0], n[1])
             self.fc1 = torch.nn.Linear(n[1], n[2])
 
@@ -254,7 +258,7 @@ def forward(self, x):
 
     class WAVE(torch.nn.Module):
         def __init__(self, n):  # n = [512, 108, 23, 5, 1]
-            super(WAVE, self).__init__()
+            super().__init__()
             self.fc0 = LinearAct(n[0], n[1])
             self.fc1 = LinearAct(n[1], n[2])
             self.fc2 = torch.nn.Linear(n[2], n[3])
@@ -269,7 +273,7 @@ def forward(self, x):
 
     class WAVE(torch.nn.Module):
         def __init__(self, n):  # n = [512, 108, 23, 5, 1]
-            super(WAVE, self).__init__()
+            super().__init__()
             self.fc0 = LinearAct(n[0], n[1])
             self.fc1 = LinearAct(n[1], n[2])
             self.fc2 = LinearAct(n[2], n[3])
@@ -285,7 +289,7 @@ def forward(self, x):
 
     class WAVE(torch.nn.Module):
         def __init__(self, n):  # n = [512, 108, 23, 5, 1]
-            super(WAVE, self).__init__()
+            super().__init__()
             self.fc0 = LinearAct(n[0], n[1])
             self.fc1 = LinearAct(n[1], n[2])
             self.fc2 = LinearAct(n[2], n[3])
@@ -302,7 +306,7 @@ def forward(self, x):
 
     class WAVE(torch.nn.Module):
         def __init__(self, n):  # n = [512, 108, 23, 5, 1]
-            super(WAVE, self).__init__()
+            super().__init__()
             self.fc0 = LinearAct(n[0], n[1])
             self.fc1 = LinearAct(n[1], n[2])
             self.fc2 = LinearAct(n[2], n[3])

train.py

@@ -23,7 +23,7 @@ def train(H, model, str, lr=0.001):
 
     cuda = torch.cuda.is_available()
     os.makedirs(f"{pathr}models", exist_ok=True)
-    name = (data[:-4] + "%s%glr%s" % (H[:], lr, str)).replace(", ", ".").replace("[", "_").replace("]", "_")
+    name = (data[:-4] + f"{H[:]}{lr:g}lr{str}").replace(", ", ".").replace("[", "_").replace("]", "_")
     print(f"Running {name}")
 
     device = select_device()
@@ -112,7 +112,7 @@ def train(H, model, str, lr=0.001):
             r = stopper.bestmodel(xi) - yi  # residuals, ().detach?
             loss[i] = (r**2).mean().cpu().item()
             std[i] = r.std(0).cpu().numpy() * ys
-        print("%.5f %s %s" % (loss[i], std[i, :], labels[i]))
+        print(f"{loss[i]:.5f} {std[i, :]} {labels[i]}")
 
     scipy.io.savemat(pathr + name + ".mat", dict(bestepoch=stopper.bestloss, loss=loss, std=std, L=L, name=name))
     # files.download(pathr + name + '.mat')
@@ -122,9 +122,11 @@ def train(H, model, str, lr=0.001):
 
 #       400  5.1498e-05    0.023752      12.484     0.15728  # var 0
 class WAVE(torch.nn.Module):
+    """Implements a neural network model for waveform data processing using a multi-layer perceptron architecture."""
+
     def __init__(self, n=(512, 64, 8, 2)):
         """Initializes the WAVE model architecture with specified layer sizes."""
-        super(WAVE, self).__init__()
+        super().__init__()
         self.fc0 = nn.Linear(n[0], n[1])
         self.fc1 = nn.Linear(n[1], n[2])
         self.fc2 = nn.Linear(n[2], n[3])
@@ -139,9 +141,11 @@ def forward(self, x):  # x.shape = [bs, 512]
 # https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/02-intermediate
 #         121     0.47059      0.0306      14.184      0.1608
 class WAVE4(nn.Module):
+    """Implements a convolutional neural network for waveform data processing with customizable output layers."""
+
     def __init__(self, n_out=2):
         """Initializes the WAVE4 model with specified output layers and configurations for convolutional layers."""
-        super(WAVE4, self).__init__()
+        super().__init__()
         self.layer1 = nn.Sequential(
             nn.Conv2d(1, 32, kernel_size=(1, 9), stride=(1, 2), padding=(0, 4), bias=False),
             nn.BatchNorm2d(32),
@@ -170,11 +174,13 @@ def forward(self, x):  # x.shape = [bs, 512]
 
 #          65    4.22e-05    0.021527      11.883     0.14406
 class WAVE3(nn.Module):
+    """WAVE3 implements a convolutional neural network for feature extraction and classification on waveform data."""
+
     def __init__(self, n_out=2):
         """Initializes the WAVE3 class with neural network layers for feature extraction and classification in a
         sequential manner.
         """
-        super(WAVE3, self).__init__()
+        super().__init__()
         n = 32
         self.layer1 = nn.Sequential(
             nn.Conv2d(in_channels=2, out_channels=n, kernel_size=(1, 33), stride=(1, 2), padding=(0, 16), bias=False),
@@ -215,9 +221,11 @@ def forward(self, x):  # x.shape = [bs, 512]
 
 #       121  2.6941e-05    0.021642      11.923     0.14201  # var 1
 class WAVE2(nn.Module):
+    """Implements a convolutional neural network for waveform data processing with configurable output dimensions."""
+
     def __init__(self, n_out=2):
         """Initializes the WAVE2 model architecture components."""
-        super(WAVE2, self).__init__()
+        super().__init__()
         self.layer1 = nn.Sequential(
             nn.Conv2d(1, 32, kernel_size=(2, 30), stride=(1, 2), padding=(1, 15), bias=False),
             nn.BatchNorm2d(32),

train_tf.py

@@ -25,7 +25,7 @@ def runexample(H, model, str):
     tf.set_random_seed(1)
     path = "data/"
     os.makedirs(f"{path}models", exist_ok=True)
-    name = (data[:-4] + "%s%glr%geps%s" % (H[:], lr, eps, str)).replace(", ", "_").replace("[", "_").replace("]", "_")
+    name = (data[:-4] + f"{H[:]}{lr:g}lr{eps:g}eps{str}").replace(", ", "_").replace("[", "_").replace("]", "_")
 
     tica = time.time()
     device = "/gpu:0" if cuda else "/cpu:0"
@@ -92,7 +92,7 @@ def criteria(y_pred, y):  # MSE
                 if L[i, 1] < best[1]:
                     best = (i, L[i, 1], None)
                 if (i - best[0]) > validations:
-                    print("\n%g validation checks exceeded at epoch %g." % (validations, i))
+                    print(f"\n{validations:g} validation checks exceeded at epoch {i:g}.")
                     break
 
             if i % printInterval == 0:  # print and save progress
@@ -109,11 +109,11 @@ def criteria(y_pred, y):  # MSE
         # model.load_state_dict(best[2])
         dt = time.time() - tica
 
-    print("\nFinished %g epochs in %.3fs (%.3f epochs/s)\nBest results from epoch %g:" % (i + 1, dt, i / dt, best[0]))
+    print(f"\nFinished {i + 1:g} epochs in {dt:.3f}s ({i / dt:.3f} epochs/s)\nBest results from epoch {best[0]:g}:")
     loss, std = np.zeros(3), np.zeros((3, ny))
     for i, (xi, yi) in enumerate(((x, y), (xv, yv), (xt, yt))):
         loss[i], std[i] = stdtf(model(xi) - yi, ys)
-        print("%.5f %s %s" % (loss[i], std[i, :], labels[i]))
+        print(f"{loss[i]:.5f} {std[i, :]} {labels[i]}")
     # scipy.io.savemat(path + name + '.mat', dict(bestepoch=best[0], loss=loss, std=std, L=L, name=name))
     # files.download(path + name + '.mat')
 

utils/utils.py

@@ -68,10 +68,12 @@ def model_info(model):
             "%5g %40s %9s %12g %20s %10.3g %10.3g"
             % (i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std())
         )
-    print("Model Summary: %g layers, %g parameters, %g gradients" % (i + 1, n_p, n_g))
+    print(f"Model Summary: {i + 1:g} layers, {n_p:g} parameters, {n_g:g} gradients")
 
 
-class patienceStopper(object):
+class patienceStopper:
+    """Monitors training loss and metrics to halt early when no improvement is seen for a specified patience period."""
+
     def __init__(self, patience=10, verbose=True, epochs=1000, printerval=10):
         """Initialize a patience stopper with given parameters for early stopping in training."""
         self.patience = patience
@@ -113,10 +115,10 @@ def step(self, loss, metrics=None, model=None):
                     self.bestmodel = copy.deepcopy(model)
 
         if self.num_bad_epochs > self.patience:
-            self.final("%g Patience exceeded at epoch %g." % (self.patience, self.epoch))
+            self.final(f"{self.patience:g} Patience exceeded at epoch {self.epoch:g}.")
             return True
         elif self.epoch >= self.epochs:
-            self.final("WARNING: %g Patience not exceeded by epoch %g (train longer)." % (self.patience, self.epoch))
+            self.final(f"WARNING: {self.patience:g} Patience not exceeded by epoch {self.epoch:g} (train longer).")
             return True
         else:
             return False
@@ -139,7 +141,6 @@ def final(self, msg):
         """Print final results and completion message with total elapsed time and best training epoch details."""
         dt = time.time() - self.t0
         print(
-            "%s\nFinished %g epochs in %.3fs (%.3f epochs/s). Best results:"
-            % (msg, self.epochs + 1, dt, (self.epochs + 1) / dt)
+            f"{msg}\nFinished {self.epochs + 1:g} epochs in {dt:.3f}s ({(self.epochs + 1) / dt:.3f} epochs/s). Best results:"
         )
         self.printepoch(self.bestepoch, self.bestloss, self.bestmetrics)