Spaces:
Sleeping
Sleeping
File size: 4,518 Bytes
0afe8bf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 |
"""
Creates a Pytorch dataset to load the Pascal VOC & MS COCO datasets
"""
import config
import numpy as np
import os
import pandas as pd
import torch
from PIL import Image, ImageFile
from torch.utils.data import Dataset, DataLoader
from utils import (
cells_to_bboxes,
iou_width_height as iou,
non_max_suppression as nms,
plot_image
)
ImageFile.LOAD_TRUNCATED_IMAGES = True
class YOLODataset(Dataset):
def __init__(
self,
csv_file,
img_dir,
label_dir,
anchors,
image_size=416,
S=[13, 26, 52],
C=20,
transform=None,
):
self.annotations = pd.read_csv(csv_file)
self.img_dir = img_dir
self.label_dir = label_dir
self.image_size = image_size
self.transform = transform
self.S = S
self.anchors = torch.tensor(anchors[0] + anchors[1] + anchors[2]) # for all 3 scales
self.num_anchors = self.anchors.shape[0]
self.num_anchors_per_scale = self.num_anchors // 3
self.C = C
self.ignore_iou_thresh = 0.5
def __len__(self):
return len(self.annotations)
def __getitem__(self, index):
label_path = os.path.join(self.label_dir, self.annotations.iloc[index, 1])
bboxes = np.roll(np.loadtxt(fname=label_path, delimiter=" ", ndmin=2), 4, axis=1).tolist()
img_path = os.path.join(self.img_dir, self.annotations.iloc[index, 0])
image = np.array(Image.open(img_path).convert("RGB"))
if self.transform:
augmentations = self.transform(image=image, bboxes=bboxes)
image = augmentations["image"]
bboxes = augmentations["bboxes"]
# Below assumes 3 scale predictions (as paper) and same num of anchors per scale
targets = [torch.zeros((self.num_anchors // 3, S, S, 6)) for S in self.S]
for box in bboxes:
iou_anchors = iou(torch.tensor(box[2:4]), self.anchors)
anchor_indices = iou_anchors.argsort(descending=True, dim=0)
x, y, width, height, class_label = box
has_anchor = [False] * 3 # each scale should have one anchor
for anchor_idx in anchor_indices:
scale_idx = anchor_idx // self.num_anchors_per_scale
anchor_on_scale = anchor_idx % self.num_anchors_per_scale
S = self.S[scale_idx]
i, j = int(S * y), int(S * x) # which cell
anchor_taken = targets[scale_idx][anchor_on_scale, i, j, 0]
if not anchor_taken and not has_anchor[scale_idx]:
targets[scale_idx][anchor_on_scale, i, j, 0] = 1
x_cell, y_cell = S * x - j, S * y - i # both between [0,1]
width_cell, height_cell = (
width * S,
height * S,
) # can be greater than 1 since it's relative to cell
box_coordinates = torch.tensor(
[x_cell, y_cell, width_cell, height_cell]
)
targets[scale_idx][anchor_on_scale, i, j, 1:5] = box_coordinates
targets[scale_idx][anchor_on_scale, i, j, 5] = int(class_label)
has_anchor[scale_idx] = True
elif not anchor_taken and iou_anchors[anchor_idx] > self.ignore_iou_thresh:
targets[scale_idx][anchor_on_scale, i, j, 0] = -1 # ignore prediction
return image, tuple(targets)
def test():
anchors = config.ANCHORS
transform = config.test_transforms
dataset = YOLODataset(
"COCO/train.csv",
"COCO/images/images/",
"COCO/labels/labels_new/",
S=[13, 26, 52],
anchors=anchors,
transform=transform,
)
S = [13, 26, 52]
scaled_anchors = torch.tensor(anchors) / (
1 / torch.tensor(S).unsqueeze(1).unsqueeze(1).repeat(1, 3, 2)
)
loader = DataLoader(dataset=dataset, batch_size=1, shuffle=True)
for x, y in loader:
boxes = []
for i in range(y[0].shape[1]):
anchor = scaled_anchors[i]
print(anchor.shape)
print(y[i].shape)
boxes += cells_to_bboxes(
y[i], is_preds=False, S=y[i].shape[2], anchors=anchor
)[0]
boxes = nms(boxes, iou_threshold=1, threshold=0.7, box_format="midpoint")
print(boxes)
plot_image(x[0].permute(1, 2, 0).to("cpu"), boxes)
if __name__ == "__main__":
test() |