Initial commit

config.py

@@ -0,0 +1,50 @@
+import albumentations as A
+import cv2
+import torch
+
+from albumentations.pytorch import ToTensorV2
+
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+ACTIVATION = 'lrelu'
+IMAGE_SIZE = 416
+transforms = A.Compose(
+    [
+        A.LongestMaxSize(max_size=IMAGE_SIZE),
+        A.PadIfNeeded(
+            min_height=IMAGE_SIZE, min_width=IMAGE_SIZE, border_mode=cv2.BORDER_CONSTANT
+        ),
+        A.Normalize(mean=[0, 0, 0], std=[1, 1, 1], max_pixel_value=255,),
+        ToTensorV2(),
+    ],
+)
+ANCHORS = [
+    [(0.28, 0.22), (0.38, 0.48), (0.9, 0.78)],
+    [(0.07, 0.15), (0.15, 0.11), (0.14, 0.29)],
+    [(0.02, 0.03), (0.04, 0.07), (0.08, 0.06)],
+]  # Note these have been rescaled to be between [0, 1]
+S = [IMAGE_SIZE // 32, IMAGE_SIZE // 16, IMAGE_SIZE // 8]
+
+PASCAL_CLASSES = [
+    "aeroplane",
+    "bicycle",
+    "bird",
+    "boat",
+    "bottle",
+    "bus",
+    "car",
+    "cat",
+    "chair",
+    "cow",
+    "diningtable",
+    "dog",
+    "horse",
+    "motorbike",
+    "person",
+    "pottedplant",
+    "sheep",
+    "sofa",
+    "train",
+    "tvmonitor"
+]

detection.py

@@ -0,0 +1,62 @@
+from typing import List
+import cv2
+import torch
+import numpy as np
+import config as modelConfig
+from pytorch_grad_cam.utils.image import show_cam_on_image
+
+from yolo3 import YOLOv3
+from utils import cells_to_bboxes, non_max_suppression, draw_prediction_boxes, YoloGradCAM
+
+
+model = YOLOv3(num_classes=20)
+
+model.load_state_dict(torch.load("yolo3_model_trained1.pth", map_location="cpu"))
+model.eval()
+print("Yolov3 Model Loaded..")
+
+scaled_anchors = (
+    torch.tensor(modelConfig.ANCHORS)
+    * torch.tensor(modelConfig.S).unsqueeze(1).unsqueeze(1).repeat(1, 3, 2)
+).to(modelConfig.DEVICE)
+
+yolo_grad_cam = YoloGradCAM(model=model, target_layers=[model.layers[-2]], use_cuda=True)
+
+
+@torch.inference_mode()
+def detect_objects(image: np.ndarray, iou_thresh: float = 0.5, thresh: float = 0.4, enable_grad_cam: bool = False, transparency: float = 0.5) -> List[np.ndarray]:
+    transformed_image = modelConfig.transforms(image=image)["image"].unsqueeze(0)
+    transformed_image = transformed_image.cuda()
+    output = model(transformed_image)
+    
+    bboxes = [[] for _ in range(1)]
+    for i in range(3):
+        batch_size, A, S, _, _ = output[i].shape
+        anchor = scaled_anchors[i]
+        boxes_scale_i = cells_to_bboxes(
+            output[i], anchor, S=S, is_preds=True
+        )
+        for idx, (box) in enumerate(boxes_scale_i):
+            bboxes[idx] += box
+
+    nms_boxes = non_max_suppression(
+        bboxes[0], iou_threshold=iou_thresh, threshold=thresh, box_format="midpoint",
+    )
+    plot_img = draw_prediction_boxes(image.copy(), nms_boxes, class_labels=modelConfig.PASCAL_CLASSES)
+    if not enable_grad_cam:
+        return [plot_img]
+    
+    grayscale_cam = yolo_grad_cam(transformed_image, scaled_anchors)[0, :, :]
+    img = cv2.resize(image, (416, 416))
+    img = np.float32(img) / 255
+    grad_cam_image = show_cam_on_image(img, grayscale_cam, use_rgb=True, image_weight=transparency)
+    return [plot_img, grad_cam_image]
+
+
+if __name__=="__main__":
+    image = cv2.imread("images/001155.jpg")
+    image = predict(image)
+
+    cv2.imshow("image", image)
+    cv2.waitKey(0)
+    cv2.destroyAllWindows()

requirements.txt

@@ -0,0 +1,11 @@
+torch==2.0.1
+torchvision==0.15.2
+torchinfo
+torchsummary
+matplotlib
+albumentations
+numpy
+grad-cam
+opencv-python
+albumentations==1.3.1
+gradio

utils.py

@@ -0,0 +1,268 @@
+from typing import List
+import torch
+import numpy as np
+import cv2
+import random
+
+from pytorch_grad_cam.base_cam import BaseCAM
+from pytorch_grad_cam.utils.svd_on_activations import get_2d_projection
+from pytorch_grad_cam.utils.model_targets import ClassifierOutputTarget
+
+
+def cells_to_bboxes(predictions, anchors, S, is_preds=True):
+    """
+    Scales the predictions coming from the model to
+    be relative to the entire image such that they for example later
+    can be plotted or.
+    INPUT:
+    predictions: tensor of size (N, 3, S, S, num_classes+5)
+    anchors: the anchors used for the predictions
+    S: the number of cells the image is divided in on the width (and height)
+    is_preds: whether the input is predictions or the true bounding boxes
+    OUTPUT:
+    converted_bboxes: the converted boxes of sizes (N, num_anchors, S, S, 1+5) with class index,
+                      object score, bounding box coordinates
+    """
+    BATCH_SIZE = predictions.shape[0]
+    num_anchors = len(anchors)
+    box_predictions = predictions[..., 1:5]
+    if is_preds:
+        anchors = anchors.reshape(1, len(anchors), 1, 1, 2)
+        box_predictions[..., 0:2] = torch.sigmoid(box_predictions[..., 0:2])
+        box_predictions[..., 2:] = torch.exp(box_predictions[..., 2:]) * anchors
+        scores = torch.sigmoid(predictions[..., 0:1])
+        best_class = torch.argmax(predictions[..., 5:], dim=-1).unsqueeze(-1)
+    else:
+        scores = predictions[..., 0:1]
+        best_class = predictions[..., 5:6]
+
+    cell_indices = (
+        torch.arange(S)
+        .repeat(predictions.shape[0], 3, S, 1)
+        .unsqueeze(-1)
+        .to(predictions.device)
+    )
+    x = 1 / S * (box_predictions[..., 0:1] + cell_indices)
+    y = 1 / S * (box_predictions[..., 1:2] + cell_indices.permute(0, 1, 3, 2, 4))
+    w_h = 1 / S * box_predictions[..., 2:4]
+    converted_bboxes = torch.cat((best_class, scores, x, y, w_h), dim=-1).reshape(BATCH_SIZE, num_anchors * S * S, 6)
+    return converted_bboxes.tolist()
+
+
+
+def intersection_over_union(boxes_preds, boxes_labels, box_format="midpoint"):
+    """
+    Video explanation of this function:
+    https://youtu.be/XXYG5ZWtjj0
+
+    This function calculates intersection over union (iou) given pred boxes
+    and target boxes.
+
+    Parameters:
+        boxes_preds (tensor): Predictions of Bounding Boxes (BATCH_SIZE, 4)
+        boxes_labels (tensor): Correct labels of Bounding Boxes (BATCH_SIZE, 4)
+        box_format (str): midpoint/corners, if boxes (x,y,w,h) or (x1,y1,x2,y2)
+
+    Returns:
+        tensor: Intersection over union for all examples
+    """
+
+    if box_format == "midpoint":
+        box1_x1 = boxes_preds[..., 0:1] - boxes_preds[..., 2:3] / 2
+        box1_y1 = boxes_preds[..., 1:2] - boxes_preds[..., 3:4] / 2
+        box1_x2 = boxes_preds[..., 0:1] + boxes_preds[..., 2:3] / 2
+        box1_y2 = boxes_preds[..., 1:2] + boxes_preds[..., 3:4] / 2
+        box2_x1 = boxes_labels[..., 0:1] - boxes_labels[..., 2:3] / 2
+        box2_y1 = boxes_labels[..., 1:2] - boxes_labels[..., 3:4] / 2
+        box2_x2 = boxes_labels[..., 0:1] + boxes_labels[..., 2:3] / 2
+        box2_y2 = boxes_labels[..., 1:2] + boxes_labels[..., 3:4] / 2
+
+    if box_format == "corners":
+        box1_x1 = boxes_preds[..., 0:1]
+        box1_y1 = boxes_preds[..., 1:2]
+        box1_x2 = boxes_preds[..., 2:3]
+        box1_y2 = boxes_preds[..., 3:4]
+        box2_x1 = boxes_labels[..., 0:1]
+        box2_y1 = boxes_labels[..., 1:2]
+        box2_x2 = boxes_labels[..., 2:3]
+        box2_y2 = boxes_labels[..., 3:4]
+
+    x1 = torch.max(box1_x1, box2_x1)
+    y1 = torch.max(box1_y1, box2_y1)
+    x2 = torch.min(box1_x2, box2_x2)
+    y2 = torch.min(box1_y2, box2_y2)
+
+    intersection = (x2 - x1).clamp(0) * (y2 - y1).clamp(0)
+    box1_area = abs((box1_x2 - box1_x1) * (box1_y2 - box1_y1))
+    box2_area = abs((box2_x2 - box2_x1) * (box2_y2 - box2_y1))
+
+    return intersection / (box1_area + box2_area - intersection + 1e-6)
+
+def non_max_suppression(bboxes, iou_threshold, threshold, box_format="corners"):
+    """
+    Video explanation of this function:
+    https://youtu.be/YDkjWEN8jNA
+
+    Does Non Max Suppression given bboxes
+
+    Parameters:
+        bboxes (list): list of lists containing all bboxes with each bboxes
+        specified as [class_pred, prob_score, x1, y1, x2, y2]
+        iou_threshold (float): threshold where predicted bboxes is correct
+        threshold (float): threshold to remove predicted bboxes (independent of IoU)
+        box_format (str): "midpoint" or "corners" used to specify bboxes
+
+    Returns:
+        list: bboxes after performing NMS given a specific IoU threshold
+    """
+
+    assert type(bboxes) == list
+
+    bboxes = [box for box in bboxes if box[1] > threshold]
+    bboxes = sorted(bboxes, key=lambda x: x[1], reverse=True)
+    bboxes_after_nms = []
+
+    while bboxes:
+        chosen_box = bboxes.pop(0)
+
+        bboxes = [
+            box
+            for box in bboxes
+            if box[0] != chosen_box[0]
+            or intersection_over_union(
+                torch.tensor(chosen_box[2:]),
+                torch.tensor(box[2:]),
+                box_format=box_format,
+            )
+            < iou_threshold
+        ]
+
+        bboxes_after_nms.append(chosen_box)
+
+    return bboxes_after_nms
+
+
+
+
+def draw_prediction_boxes(image: np.ndarray, boxes: List[List], class_labels: List[str]) -> np.ndarray:
+    """Plots predicted bounding boxes on the image"""
+
+    colors = [[random.randint(0, 255) for _ in range(3)] for name in class_labels]
+
+    im = np.array(image)
+    height, width, _ = im.shape
+    bbox_thick = int(0.6 * (height + width) / 600)
+
+    # Create a Rectangle patch
+    for box in boxes:
+        assert len(box) == 6, "box should contain class pred, confidence, x, y, width, height"
+        class_pred = box[0]
+        conf = box[1]
+        box = box[2:]
+        upper_left_x = box[0] - box[2] / 2
+        upper_left_y = box[1] - box[3] / 2
+        
+        x1  = int(upper_left_x * width)
+        y1 = int(upper_left_y * height)
+        
+        x2 = x1 + int(box[2] * width)
+        y2 = y1 + int(box[3] * height)
+        
+        cv2.rectangle(
+            image,
+            (x1, y1), (x2, y2),
+            color=colors[int(class_pred)],
+            thickness=bbox_thick
+        )
+        text = f"{class_labels[int(class_pred)]}: {conf:.2f}"
+        t_size = cv2.getTextSize(text, 0, 0.7, thickness=bbox_thick // 2)[0]
+        c3 = (x1 + t_size[0], y1 - t_size[1] - 3)
+
+        cv2.rectangle(image, (x1, y1), c3, colors[int(class_pred)], -1)
+        cv2.putText(
+            image,
+            text,
+            (x1, y1 - 2),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.7,
+            (0, 0, 0),
+            bbox_thick // 2,
+            lineType=cv2.LINE_AA,
+        )
+
+    return image
+
+
+class YoloGradCAM(BaseCAM):
+    def __init__(self, model, target_layers, use_cuda=False,
+                 reshape_transform=None):
+        super(YoloGradCAM, self).__init__(model,
+                                       target_layers,
+                                       use_cuda,
+                                       reshape_transform,
+                                       uses_gradients=False)
+
+    def forward(self,
+                input_tensor: torch.Tensor,
+                scaled_anchors: torch.Tensor,
+                targets: List[torch.nn.Module],
+                eigen_smooth: bool = False) -> np.ndarray:
+
+        if self.cuda:
+            input_tensor = input_tensor.cuda()
+
+        if self.compute_input_gradient:
+            input_tensor = torch.autograd.Variable(input_tensor,
+                                                   requires_grad=True)
+
+        outputs = self.activations_and_grads(input_tensor)
+        if targets is None:
+            bboxes = [[] for _ in range(1)]
+            for i in range(3):
+                batch_size, A, S, _, _ = outputs[i].shape
+                anchor = scaled_anchors[i]
+                boxes_scale_i = cells_to_bboxes(
+                    outputs[i], anchor, S=S, is_preds=True
+                )
+                for idx, (box) in enumerate(boxes_scale_i):
+                    bboxes[idx] += box
+            
+            nms_boxes = non_max_suppression(
+                bboxes[0], iou_threshold=0.5, threshold=0.4, box_format="midpoint",
+            )
+            # target_categories = np.argmax(outputs.cpu().data.numpy(), axis=-1)
+            target_categories = [box[0] for box in nms_boxes]
+            targets = [ClassifierOutputTarget(
+                category) for category in target_categories]
+
+        if self.uses_gradients:
+            self.model.zero_grad()
+            loss = sum([target(output)
+                       for target, output in zip(targets, outputs)])
+            loss.backward(retain_graph=True)
+
+        # In most of the saliency attribution papers, the saliency is
+        # computed with a single target layer.
+        # Commonly it is the last convolutional layer.
+        # Here we support passing a list with multiple target layers.
+        # It will compute the saliency image for every image,
+        # and then aggregate them (with a default mean aggregation).
+        # This gives you more flexibility in case you just want to
+        # use all conv layers for example, all Batchnorm layers,
+        # or something else.
+        cam_per_layer = self.compute_cam_per_layer(input_tensor,
+                                                   targets,
+                                                   eigen_smooth)
+        return self.aggregate_multi_layers(cam_per_layer)
+    
+    def get_cam_image(self,
+                      input_tensor,
+                      target_layer,
+                      target_category,
+                      activations,
+                      grads,
+                      eigen_smooth):
+        return get_2d_projection(activations)
+
+
+

yolo3.py

@@ -0,0 +1,181 @@
+"""Implementation of YOLOv3 architecture."""
+from typing import Any, List
+
+import torch
+import torch.nn as nn
+
+"""
+Information about architecture config:
+Tuple is structured by (filters, kernel_size, stride)
+Every conv is a same convolution.
+List is structured by "B" indicating a residual block followed by the number of repeats
+"S" is for scale prediction block and computing the yolo loss
+"U" is for upsampling the feature map and concatenating with a previous layer
+"""
+config = [
+    (32, 3, 1),
+    (64, 3, 2),
+    ["B", 1],
+    (128, 3, 2),
+    ["B", 2],
+    (256, 3, 2),
+    ["B", 8],
+    (512, 3, 2),
+    ["B", 8],
+    (1024, 3, 2),
+    ["B", 4],  # To this point is Darknet-53
+    (512, 1, 1),
+    (1024, 3, 1),
+    "S",
+    (256, 1, 1),
+    "U",
+    (256, 1, 1),
+    (512, 3, 1),
+    "S",
+    (128, 1, 1),
+    "U",
+    (128, 1, 1),
+    (256, 3, 1),
+    "S",
+]
+
+
+class CNNBlock(nn.Module):
+    def __init__(self, in_channels, out_channels, bn_act=True, **kwargs):
+        super().__init__()
+        self.conv = nn.Conv2d(in_channels, out_channels, bias=not bn_act, **kwargs)
+        self.bn = nn.BatchNorm2d(out_channels)
+        self.leaky = nn.LeakyReLU(0.1)
+        self.use_bn_act = bn_act
+
+    def forward(self, x):
+        if self.use_bn_act:
+            return self.leaky(self.bn(self.conv(x)))
+        else:
+            return self.conv(x)
+
+
+class ResidualBlock(nn.Module):
+    def __init__(self, channels, use_residual=True, num_repeats=1):
+        super().__init__()
+        self.layers = nn.ModuleList()
+        for repeat in range(num_repeats):
+            self.layers += [
+                nn.Sequential(
+                    CNNBlock(channels, channels // 2, kernel_size=1),
+                    CNNBlock(channels // 2, channels, kernel_size=3, padding=1),
+                )
+            ]
+
+        self.use_residual = use_residual
+        self.num_repeats = num_repeats
+
+    def forward(self, x):
+        for layer in self.layers:
+            if self.use_residual:
+                x = x + layer(x)
+            else:
+                x = layer(x)
+
+        return x
+
+
+class ScalePrediction(nn.Module):
+    def __init__(self, in_channels, num_classes):
+        super().__init__()
+        self.pred = nn.Sequential(
+            CNNBlock(in_channels, 2 * in_channels, kernel_size=3, padding=1),
+            CNNBlock(2 * in_channels, (num_classes + 5) * 3, bn_act=False, kernel_size=1),
+        )
+        self.num_classes = num_classes
+
+    def forward(self, x):
+        return (
+            self.pred(x)
+            .reshape(x.shape[0], 3, self.num_classes + 5, x.shape[2], x.shape[3])
+            .permute(0, 1, 3, 4, 2)
+        )
+
+
+class YOLOv3(nn.Module):
+    def __init__(self, load_config: List[Any] = config, in_channels=3, num_classes=80):
+        super().__init__()
+        self.load_config = load_config
+        self.num_classes = num_classes
+        self.in_channels = in_channels
+        self.layers = self._create_conv_layers()
+
+    def forward(self, x):
+        outputs = []  # for each scale
+        route_connections = []
+        for layer in self.layers:
+            if isinstance(layer, ScalePrediction):
+                outputs.append(layer(x))
+                continue
+
+            x = layer(x)
+
+            if isinstance(layer, ResidualBlock) and layer.num_repeats == 8:
+                route_connections.append(x)
+
+            elif isinstance(layer, nn.Upsample):
+                x = torch.cat([x, route_connections[-1]], dim=1)
+                route_connections.pop()
+
+        return outputs
+
+    def _create_conv_layers(self):
+        layers = nn.ModuleList()
+        in_channels = self.in_channels
+
+        for module in self.load_config:
+            if isinstance(module, tuple):
+                out_channels, kernel_size, stride = module
+                layers.append(
+                    CNNBlock(
+                        in_channels,
+                        out_channels,
+                        kernel_size=kernel_size,
+                        stride=stride,
+                        padding=1 if kernel_size == 3 else 0,
+                    )
+                )
+                in_channels = out_channels
+
+            elif isinstance(module, list):
+                num_repeats = module[1]
+                layers.append(
+                    ResidualBlock(
+                        in_channels,
+                        num_repeats=num_repeats,
+                    )
+                )
+
+            elif isinstance(module, str):
+                if module == "S":
+                    layers += [
+                        ResidualBlock(in_channels, use_residual=False, num_repeats=1),
+                        CNNBlock(in_channels, in_channels // 2, kernel_size=1),
+                        ScalePrediction(in_channels // 2, num_classes=self.num_classes),
+                    ]
+                    in_channels = in_channels // 2
+
+                elif module == "U":
+                    layers.append(
+                        nn.Upsample(scale_factor=2),
+                    )
+                    in_channels = in_channels * 3
+
+        return layers
+
+
+if __name__ == "__main__":
+    num_classes = 20
+    IMAGE_SIZE = 416
+    model = YOLOv3(load_config=config, num_classes=num_classes)
+    x = torch.randn((2, 3, IMAGE_SIZE, IMAGE_SIZE))
+    out = model(x)
+    assert out[0].shape == (2, 3, IMAGE_SIZE // 32, IMAGE_SIZE // 32, num_classes + 5)
+    assert out[1].shape == (2, 3, IMAGE_SIZE // 16, IMAGE_SIZE // 16, num_classes + 5)
+    assert out[2].shape == (2, 3, IMAGE_SIZE // 8, IMAGE_SIZE // 8, num_classes + 5)
+    print("Success!")

yolo3_model_trained1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ff99e551f716430c54b85a75f4de060acf504afae0bf34801894859619aaf89
+size 246869879