added kaggle comp solution for facial keypoint

Author: aladdinpersson

ML/Kaggles/Facial Keypoint Detection Competition/config.py

@@ -0,0 +1,61 @@
+import torch
+import albumentations as A
+from albumentations.pytorch import ToTensorV2
+import cv2
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+LEARNING_RATE = 1e-4
+WEIGHT_DECAY = 5e-4
+BATCH_SIZE = 64
+NUM_EPOCHS = 100
+NUM_WORKERS = 4
+CHECKPOINT_FILE = "b0_4.pth.tar"
+PIN_MEMORY = True
+SAVE_MODEL = True
+LOAD_MODEL = True
+
+# Data augmentation for images
+train_transforms = A.Compose(
+    [
+        A.Resize(width=96, height=96),
+        A.Rotate(limit=15, border_mode=cv2.BORDER_CONSTANT, p=0.8),
+        A.IAAAffine(shear=15, scale=1.0, mode="constant", p=0.2),
+        A.RandomBrightnessContrast(contrast_limit=0.5, brightness_limit=0.5, p=0.2),
+        A.OneOf([
+            A.GaussNoise(p=0.8),
+            A.CLAHE(p=0.8),
+            A.ImageCompression(p=0.8),
+            A.RandomGamma(p=0.8),
+            A.Posterize(p=0.8),
+            A.Blur(p=0.8),
+        ], p=1.0),
+        A.OneOf([
+            A.GaussNoise(p=0.8),
+            A.CLAHE(p=0.8),
+            A.ImageCompression(p=0.8),
+            A.RandomGamma(p=0.8),
+            A.Posterize(p=0.8),
+            A.Blur(p=0.8),
+        ], p=1.0),
+        A.ShiftScaleRotate(shift_limit=0.1, scale_limit=0.1, rotate_limit=0, p=0.2, border_mode=cv2.BORDER_CONSTANT),
+        A.Normalize(
+            mean=[0.4897, 0.4897, 0.4897],
+            std=[0.2330, 0.2330, 0.2330],
+            max_pixel_value=255.0,
+        ),
+        ToTensorV2(),
+    ], keypoint_params=A.KeypointParams(format="xy", remove_invisible=False),
+)
+
+
+val_transforms = A.Compose(
+    [
+        A.Resize(height=96, width=96),
+        A.Normalize(
+            mean=[0.4897, 0.4897, 0.4897],
+            std=[0.2330, 0.2330, 0.2330],
+            max_pixel_value=255.0,
+        ),
+        ToTensorV2(),
+    ], keypoint_params=A.KeypointParams(format="xy", remove_invisible=False),
+)

ML/Kaggles/Facial Keypoint Detection Competition/dataset.py

@@ -0,0 +1,50 @@
+import pandas as pd
+import numpy as np
+import config
+import matplotlib.pyplot as plt
+from torch.utils.data import DataLoader, Dataset
+
+
+class FacialKeypointDataset(Dataset):
+    def __init__(self, csv_file, train=True, transform=None):
+        super().__init__()
+        self.data = pd.read_csv(csv_file)
+        self.category_names = ['left_eye_center_x', 'left_eye_center_y', 'right_eye_center_x', 'right_eye_center_y', 'left_eye_inner_corner_x', 'left_eye_inner_corner_y', 'left_eye_outer_corner_x', 'left_eye_outer_corner_y', 'right_eye_inner_corner_x', 'right_eye_inner_corner_y', 'right_eye_outer_corner_x', 'right_eye_outer_corner_y', 'left_eyebrow_inner_end_x', 'left_eyebrow_inner_end_y', 'left_eyebrow_outer_end_x', 'left_eyebrow_outer_end_y', 'right_eyebrow_inner_end_x', 'right_eyebrow_inner_end_y', 'right_eyebrow_outer_end_x', 'right_eyebrow_outer_end_y', 'nose_tip_x', 'nose_tip_y', 'mouth_left_corner_x', 'mouth_left_corner_y', 'mouth_right_corner_x', 'mouth_right_corner_y', 'mouth_center_top_lip_x', 'mouth_center_top_lip_y', 'mouth_center_bottom_lip_x', 'mouth_center_bottom_lip_y']
+        self.transform = transform
+        self.train = train
+
+    def __len__(self):
+        return self.data.shape[0]
+
+    def __getitem__(self, index):
+        if self.train:
+            image = np.array(self.data.iloc[index, 30].split()).astype(np.float32)
+            labels = np.array(self.data.iloc[index, :30].tolist())
+            labels[np.isnan(labels)] = -1
+        else:
+            image = np.array(self.data.iloc[index, 1].split()).astype(np.float32)
+            labels = np.zeros(30)
+
+        ignore_indices = labels == -1
+        labels = labels.reshape(15, 2)
+
+        if self.transform:
+            image = np.repeat(image.reshape(96, 96, 1), 3, 2).astype(np.uint8)
+            augmentations = self.transform(image=image, keypoints=labels)
+            image = augmentations["image"]
+            labels = augmentations["keypoints"]
+
+        labels = np.array(labels).reshape(-1)
+        labels[ignore_indices] = -1
+
+        return image, labels.astype(np.float32)
+
+
+if __name__ == "__main__":
+    ds = FacialKeypointDataset(csv_file="data/train_4.csv", train=True, transform=config.train_transforms)
+    loader = DataLoader(ds, batch_size=1, shuffle=True, num_workers=0)
+
+    for idx, (x, y) in enumerate(loader):
+        plt.imshow(x[0][0].detach().cpu().numpy(), cmap='gray')
+        plt.plot(y[0][0::2].detach().cpu().numpy(), y[0][1::2].detach().cpu().numpy(), "go")
+        plt.show()

ML/Kaggles/Facial Keypoint Detection Competition/extract_images_from_csv.py

@@ -0,0 +1,19 @@
+import numpy as np
+import pandas as pd
+import os
+from PIL import Image
+
+
+def extract_images_from_csv(csv, column, save_folder, resize=(96, 96)):
+    if not os.path.exists(save_folder):
+        os.makedirs(save_folder)
+
+    for idx, image in enumerate(csv[column]):
+        image = np.array(image.split()).astype(np.uint8)
+        image = image.reshape(resize[0], resize[1])
+        img = Image.fromarray(image, 'L')
+        img.save(save_folder+f"img_{idx}.png")
+
+
+csv = pd.read_csv("test.csv")
+extract_images_from_csv(csv, "Image", "data/test/")