yolov3的實現主要是基於pytorch來實現的，具體參考來源：https://github.com/eriklindernoren/PyTorch-YOLOv3，本文主要解析utils裏面的實現，總體也比較簡單。主要包含了parse_config.py，datasets.py，augmentations.py，logger.py，utils.py這幾個文件。
parse_config.py
#解析model文件（如yolov3-tiny.cfg），便於後續進行網絡模型的構建
def parse_model_config(path):
"""Parses the yolo-v3 layer configuration file and returns module definitions"""
file = open(path, 'r')
lines = file.read().split('\n')
lines = [x for x in lines if x and not x.startswith('#')]
lines = [x.rstrip().lstrip() for x in lines] # get rid of fringe whitespaces
module_defs = []
for line in lines:
if line.startswith('['): # This marks the start of a new block
module_defs.append({})
module_defs[-1]['type'] = line[1:-1].rstrip()
if module_defs[-1]['type'] == 'convolutional':
module_defs[-1]['batch_normalize'] = 0
else:
key, value = line.split("=")
value = value.strip()
module_defs[-1][key.rstrip()] = value.strip()
return module_defs
#解析coco.data文件,便於後續加載圖片,類別以及對應的標籤信息
def parse_data_config(path):
"""Parses the data configuration file"""
options = dict()
options['gpus'] = '0,1,2,3'
options['num_workers'] = '10'
with open(path, 'r') as fp:
lines = fp.readlines()
for line in lines:
line = line.strip()
if line == '' or line.startswith('#'):
continue
key, value = line.split('=')
options[key.strip()] = value.strip()
return options
datasets.py
import glob
import random
import os
import sys
import numpy as np
from PIL import Image
import torch
import torch.nn.functional as F
from utils.augmentations import horisontal_flip
from torch.utils.data import Dataset
import torchvision.transforms as transforms
#將圖片擴展爲正方形
def pad_to_square(img, pad_value):
c, h, w = img.shape
dim_diff = np.abs(h - w)
# (upper / left) padding and (lower / right) padding
pad1, pad2 = dim_diff // 2, dim_diff - dim_diff // 2
# Determine padding
pad = (0, 0, pad1, pad2) if h <= w else (pad1, pad2, 0, 0)
# Add padding
img = F.pad(img, pad, "constant", value=pad_value)
return img, pad
#設置圖像爲固定大小
def resize(image, size):
image = F.interpolate(image.unsqueeze(0), size=size, mode="nearest").squeeze(0)
return image
#隨機設置圖像的尺寸,範圍爲[min_size,max_size]
def random_resize(images, min_size=288, max_size=448):
new_size = random.sample(list(range(min_size, max_size + 1, 32)), 1)[0]
images = F.interpolate(images, size=new_size, mode="nearest")
return images
#讀取文件夾下的圖片,並設置成一定大小
class ImageFolder(Dataset):
def __init__(self, folder_path, img_size=416):
self.files = sorted(glob.glob("%s/*.*" % folder_path))
self.img_size = img_size
def __getitem__(self, index):
img_path = self.files[index % len(self.files)]
# Extract image as PyTorch tensor
img = transforms.ToTensor()(Image.open(img_path))
# Pad to square resolution
img, _ = pad_to_square(img, 0)
# Resize
img = resize(img, self.img_size)
return img_path, img
def __len__(self):
return len(self.files)
#加載數據
class ListDataset(Dataset):
def __init__(self, list_path, img_size=416, augment=True, multiscale=True, normalized_labels=True):
with open(list_path, "r") as file:
self.img_files = file.readlines() #讀取圖像文件路徑
#讀取圖像的類別以及box的信息
self.label_files = [
path.replace("images", "labels").replace(".png", ".txt").replace(".jpg", ".txt")
for path in self.img_files
]
self.img_size = img_size
self.max_objects = 100
self.augment = augment
self.multiscale = multiscale
self.normalized_labels = normalized_labels
self.min_size = self.img_size - 3 * 32
self.max_size = self.img_size + 3 * 32
self.batch_count = 0
def __getitem__(self, index):
# ---------
# Image
# ---------
img_path = self.img_files[index % len(self.img_files)].rstrip() #圖像路徑
# Extract image as PyTorch tensor
img = transforms.ToTensor()(Image.open(img_path).convert('RGB')) #讀取圖像
# Handle images with less than three channels
if len(img.shape) != 3:
img = img.unsqueeze(0)
img = img.expand((3, img.shape[1:]))
_, h, w = img.shape
h_factor, w_factor = (h, w) if self.normalized_labels else (1, 1)
# Pad to square resolution
img, pad = pad_to_square(img, 0)
_, padded_h, padded_w = img.shape
# ---------
# Label
# ---------
label_path = self.label_files[index % len(self.img_files)].rstrip()
targets = None
if os.path.exists(label_path):
boxes = torch.from_numpy(np.loadtxt(label_path).reshape(-1, 5))
# Extract coordinates for unpadded + unscaled image
x1 = w_factor * (boxes[:, 1] - boxes[:, 3] / 2)
y1 = h_factor * (boxes[:, 2] - boxes[:, 4] / 2)
x2 = w_factor * (boxes[:, 1] + boxes[:, 3] / 2)
y2 = h_factor * (boxes[:, 2] + boxes[:, 4] / 2)
# Adjust for added padding
x1 += pad[0]
y1 += pad[2]
x2 += pad[1]
y2 += pad[3]
# Returns (x, y, w, h)
boxes[:, 1] = ((x1 + x2) / 2) / padded_w
boxes[:, 2] = ((y1 + y2) / 2) / padded_h
boxes[:, 3] *= w_factor / padded_w
boxes[:, 4] *= h_factor / padded_h
targets = torch.zeros((len(boxes), 6))
targets[:, 1:] = boxes
# Apply augmentations
if self.augment:
if np.random.random() < 0.5:
img, targets = horisontal_flip(img, targets) #鏡像處理
#返回圖像路徑，圖像，標籤信息
return img_path, img, targets
def collate_fn(self, batch):
paths, imgs, targets = list(zip(*batch))
# Remove empty placeholder targets
targets = [boxes for boxes in targets if boxes is not None]
# Add sample index to targets
for i, boxes in enumerate(targets):
boxes[:, 0] = i
targets = torch.cat(targets, 0)
# Selects new image size every tenth batch
if self.multiscale and self.batch_count % 10 == 0: #如果是多尺度情形下，就每個10個batch進行一次尺度改變
self.img_size = random.choice(range(self.min_size, self.max_size + 1, 32))
# Resize images to input shape
imgs = torch.stack([resize(img, self.img_size) for img in imgs])
self.batch_count += 1
return paths, imgs, targets
#返回數據長度
def __len__(self):
return len(self.img_files)
augmentations.py
import torch
import torch.nn.functional as F
import numpy as np
#圖像鏡像處理，以及標籤做對應處理
def horisontal_flip(images, targets):
images = torch.flip(images, [-1])
targets[:, 2] = 1 - targets[:, 2]
return images, targets
utils.py
from __future__ import division
import math
import time
import tqdm
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.patches as patches
def to_cpu(tensor):
return tensor.detach().cpu()
#加載數據類別
def load_classes(path):
"""
Loads class labels at 'path'
"""
fp = open(path, "r")
names = fp.read().split("\n")[:-1]
return names
#權重初始化
def weights_init_normal(m):
classname = m.__class__.__name__
if classname.find("Conv") != -1:
torch.nn.init.normal_(m.weight.data, 0.0, 0.02)
elif classname.find("BatchNorm2d") != -1:
torch.nn.init.normal_(m.weight.data, 1.0, 0.02)
torch.nn.init.constant_(m.bias.data, 0.0)
#將圖像設定爲原始大小
def rescale_boxes(boxes, current_dim, original_shape):
""" Rescales bounding boxes to the original shape """
orig_h, orig_w = original_shape
# The amount of padding that was added
pad_x = max(orig_h - orig_w, 0) * (current_dim / max(original_shape))
pad_y = max(orig_w - orig_h, 0) * (current_dim / max(original_shape))
# Image height and width after padding is removed
unpad_h = current_dim - pad_y
unpad_w = current_dim - pad_x
# Rescale bounding boxes to dimension of original image
boxes[:, 0] = ((boxes[:, 0] - pad_x // 2) / unpad_w) * orig_w
boxes[:, 1] = ((boxes[:, 1] - pad_y // 2) / unpad_h) * orig_h
boxes[:, 2] = ((boxes[:, 2] - pad_x // 2) / unpad_w) * orig_w
boxes[:, 3] = ((boxes[:, 3] - pad_y // 2) / unpad_h) * orig_h
return boxes
#box的標籤信息轉換
def xywh2xyxy(x):
y = x.new(x.shape)
y[..., 0] = x[..., 0] - x[..., 2] / 2
y[..., 1] = x[..., 1] - x[..., 3] / 2
y[..., 2] = x[..., 0] + x[..., 2] / 2
y[..., 3] = x[..., 1] + x[..., 3] / 2
return y
#求每個類別的tp,conf,pred_cls,target_cls
def ap_per_class(tp, conf, pred_cls, target_cls):
""" Compute the average precision, given the recall and precision curves.
Source: https://github.com/rafaelpadilla/Object-Detection-Metrics.
# Arguments
tp: True positives (list).
conf: Objectness value from 0-1 (list).
pred_cls: Predicted object classes (list).
target_cls: True object classes (list).
# Returns
The average precision as computed in py-faster-rcnn.
"""
# Sort by objectness
i = np.argsort(-conf)
tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]
# Find unique classes
unique_classes = np.unique(target_cls)
# Create Precision-Recall curve and compute AP for each class
ap, p, r = [], [], []
for c in tqdm.tqdm(unique_classes, desc="Computing AP"):
i = pred_cls == c
n_gt = (target_cls == c).sum() # Number of ground truth objects
n_p = i.sum() # Number of predicted objects
if n_p == 0 and n_gt == 0:
continue
elif n_p == 0 or n_gt == 0:
ap.append(0)
r.append(0)
p.append(0)
else:
# Accumulate FPs and TPs
fpc = (1 - tp[i]).cumsum()
tpc = (tp[i]).cumsum()
# Recall
recall_curve = tpc / (n_gt + 1e-16)
r.append(recall_curve[-1])
# Precision
precision_curve = tpc / (tpc + fpc)
p.append(precision_curve[-1])
# AP from recall-precision curve
ap.append(compute_ap(recall_curve, precision_curve))
# Compute F1 score (harmonic mean of precision and recall)
p, r, ap = np.array(p), np.array(r), np.array(ap)
f1 = 2 * p * r / (p + r + 1e-16)
return p, r, ap, f1, unique_classes.astype("int32")
#計算ap
def compute_ap(recall, precision):
""" Compute the average precision, given the recall and precision curves.
Code originally from https://github.com/rbgirshick/py-faster-rcnn.
# Arguments
recall: The recall curve (list).
precision: The precision curve (list).
# Returns
The average precision as computed in py-faster-rcnn.
"""
# correct AP calculation
# first append sentinel values at the end
mrec = np.concatenate(([0.0], recall, [1.0]))
mpre = np.concatenate(([0.0], precision, [0.0]))
# compute the precision envelope
for i in range(mpre.size - 1, 0, -1):
mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i])
# to calculate area under PR curve, look for points
# where X axis (recall) changes value
i = np.where(mrec[1:] != mrec[:-1])[0]
# and sum (\Delta recall) * prec
ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])
return ap
def get_batch_statistics(outputs, targets, iou_threshold):
""" Compute true positives, predicted scores and predicted labels per sample """
batch_metrics = []
for sample_i in range(len(outputs)):
if outputs[sample_i] is None:
continue
output = outputs[sample_i]
pred_boxes = output[:, :4]
pred_scores = output[:, 4]
pred_labels = output[:, -1]
true_positives = np.zeros(pred_boxes.shape[0])
annotations = targets[targets[:, 0] == sample_i][:, 1:]
target_labels = annotations[:, 0] if len(annotations) else []
if len(annotations):
detected_boxes = []
target_boxes = annotations[:, 1:]
for pred_i, (pred_box, pred_label) in enumerate(zip(pred_boxes, pred_labels)):
# If targets are found break
if len(detected_boxes) == len(annotations):
break
# Ignore if label is not one of the target labels
if pred_label not in target_labels:
continue
iou, box_index = bbox_iou(pred_box.unsqueeze(0), target_boxes).max(0)
if iou >= iou_threshold and box_index not in detected_boxes:
true_positives[pred_i] = 1
detected_boxes += [box_index]
batch_metrics.append([true_positives, pred_scores, pred_labels])
return batch_metrics
#box的置信度
def bbox_wh_iou(wh1, wh2):
wh2 = wh2.t()
w1, h1 = wh1[0], wh1[1]
w2, h2 = wh2[0], wh2[1]
inter_area = torch.min(w1, w2) * torch.min(h1, h2)
union_area = (w1 * h1 + 1e-16) + w2 * h2 - inter_area
return inter_area / union_area
#box的置信度
def bbox_iou(box1, box2, x1y1x2y2=True):
"""
Returns the IoU of two bounding boxes
"""
if not x1y1x2y2:
# Transform from center and width to exact coordinates
b1_x1, b1_x2 = box1[:, 0] - box1[:, 2] / 2, box1[:, 0] + box1[:, 2] / 2
b1_y1, b1_y2 = box1[:, 1] - box1[:, 3] / 2, box1[:, 1] + box1[:, 3] / 2
b2_x1, b2_x2 = box2[:, 0] - box2[:, 2] / 2, box2[:, 0] + box2[:, 2] / 2
b2_y1, b2_y2 = box2[:, 1] - box2[:, 3] / 2, box2[:, 1] + box2[:, 3] / 2
else:
# Get the coordinates of bounding boxes
b1_x1, b1_y1, b1_x2, b1_y2 = box1[:, 0], box1[:, 1], box1[:, 2], box1[:, 3]
b2_x1, b2_y1, b2_x2, b2_y2 = box2[:, 0], box2[:, 1], box2[:, 2], box2[:, 3]
# get the corrdinates of the intersection rectangle
inter_rect_x1 = torch.max(b1_x1, b2_x1)
inter_rect_y1 = torch.max(b1_y1, b2_y1)
inter_rect_x2 = torch.min(b1_x2, b2_x2)
inter_rect_y2 = torch.min(b1_y2, b2_y2)
# Intersection area
inter_area = torch.clamp(inter_rect_x2 - inter_rect_x1 + 1, min=0) * torch.clamp(
inter_rect_y2 - inter_rect_y1 + 1, min=0
)
# Union Area
b1_area = (b1_x2 - b1_x1 + 1) * (b1_y2 - b1_y1 + 1)
b2_area = (b2_x2 - b2_x1 + 1) * (b2_y2 - b2_y1 + 1)
iou = inter_area / (b1_area + b2_area - inter_area + 1e-16)
return iou
#box的非極大值抑制
def non_max_suppression(prediction, conf_thres=0.5, nms_thres=0.4):
"""
Removes detections with lower object confidence score than 'conf_thres' and performs
Non-Maximum Suppression to further filter detections.
Returns detections with shape:
(x1, y1, x2, y2, object_conf, class_score, class_pred)
"""
# From (center x, center y, width, height) to (x1, y1, x2, y2)
prediction[..., :4] = xywh2xyxy(prediction[..., :4])
output = [None for _ in range(len(prediction))]
for image_i, image_pred in enumerate(prediction):
# Filter out confidence scores below threshold
image_pred = image_pred[image_pred[:, 4] >= conf_thres]
# If none are remaining => process next image
if not image_pred.size(0):
continue
# Object confidence times class confidence
score = image_pred[:, 4] * image_pred[:, 5:].max(1)[0]
# Sort by it
image_pred = image_pred[(-score).argsort()]
class_confs, class_preds = image_pred[:, 5:].max(1, keepdim=True)
detections = torch.cat((image_pred[:, :5], class_confs.float(), class_preds.float()), 1)
# Perform non-maximum suppression
keep_boxes = []
while detections.size(0):
large_overlap = bbox_iou(detections[0, :4].unsqueeze(0), detections[:, :4]) > nms_thres
label_match = detections[0, -1] == detections[:, -1]
# Indices of boxes with lower confidence scores, large IOUs and matching labels
invalid = large_overlap & label_match
weights = detections[invalid, 4:5]
# Merge overlapping bboxes by order of confidence
detections[0, :4] = (weights * detections[invalid, :4]).sum(0) / weights.sum()
keep_boxes += [detections[0]]
detections = detections[~invalid]
if keep_boxes:
output[image_i] = torch.stack(keep_boxes)
return output
#求obj,noobj,class的mask，便於後續進一步求解損失代價
def build_targets(pred_boxes, pred_cls, target, anchors, ignore_thres):
ByteTensor = torch.cuda.ByteTensor if pred_boxes.is_cuda else torch.ByteTensor
FloatTensor = torch.cuda.FloatTensor if pred_boxes.is_cuda else torch.FloatTensor
nB = pred_boxes.size(0) #num_samples
nA = pred_boxes.size(1) #num_anchors
nC = pred_cls.size(-1) #feature map c
nG = pred_boxes.size(2) #grid size
# Output tensors [樣本數，anchors數，grid寬，grid高] 這裏寬高相等
obj_mask = ByteTensor(nB, nA, nG, nG).fill_(0) #[num_samples,num_anchors,grid_size,grid_size]
noobj_mask = ByteTensor(nB, nA, nG, nG).fill_(1) #[num_samples,num_anchors,grid_size,grid_size]
class_mask = FloatTensor(nB, nA, nG, nG).fill_(0)
iou_scores = FloatTensor(nB, nA, nG, nG).fill_(0)
tx = FloatTensor(nB, nA, nG, nG).fill_(0)
ty = FloatTensor(nB, nA, nG, nG).fill_(0)
tw = FloatTensor(nB, nA, nG, nG).fill_(0)
th = FloatTensor(nB, nA, nG, nG).fill_(0)
tcls = FloatTensor(nB, nA, nG, nG, nC).fill_(0)
# Convert to position relative to box
target_boxes = target[:, 2:6] * nG
gxy = target_boxes[:, :2]
gwh = target_boxes[:, 2:]
# Get anchors with best iou
ious = torch.stack([bbox_wh_iou(anchor, gwh) for anchor in anchors])
best_ious, best_n = ious.max(0)
# Separate target values
b, target_labels = target[:, :2].long().t()
gx, gy = gxy.t()
gw, gh = gwh.t()
gi, gj = gxy.long().t()
# Set masks
obj_mask[b, best_n, gj, gi] = 1
noobj_mask[b, best_n, gj, gi] = 0
# Set noobj mask to zero where iou exceeds ignore threshold
for i, anchor_ious in enumerate(ious.t()):
noobj_mask[b[i], anchor_ious > ignore_thres, gj[i], gi[i]] = 0
# Coordinates
tx[b, best_n, gj, gi] = gx - gx.floor()
ty[b, best_n, gj, gi] = gy - gy.floor()
# Width and height
tw[b, best_n, gj, gi] = torch.log(gw / anchors[best_n][:, 0] + 1e-16)
th[b, best_n, gj, gi] = torch.log(gh / anchors[best_n][:, 1] + 1e-16)
# One-hot encoding of label
tcls[b, best_n, gj, gi, target_labels] = 1
# Compute label correctness and iou at best anchor
class_mask[b, best_n, gj, gi] = (pred_cls[b, best_n, gj, gi].argmax(-1) == target_labels).float()
iou_scores[b, best_n, gj, gi] = bbox_iou(pred_boxes[b, best_n, gj, gi], target_boxes, x1y1x2y2=False)
tconf = obj_mask.float()
return iou_scores, class_mask, obj_mask, noobj_mask, tx, ty, tw, th, tcls, tconf
logger.py：用於存儲模型訓練的中間信息，便於後續繪圖顯示
import tensorflow as tf
class Logger(object):
def __init__(self, log_dir):
"""Create a summary writer logging to log_dir."""
self.writer = tf.summary.FileWriter(log_dir)
def scalar_summary(self, tag, value, step):
"""Log a scalar variable."""
summary = tf.Summary(value=[tf.Summary.Value(tag=tag, simple_value=value)])
self.writer.add_summary(summary, step)
def list_of_scalars_summary(self, tag_value_pairs, step):
"""Log scalar variables."""
summary = tf.Summary(value=[tf.Summary.Value(tag=tag, simple_value=value) for tag, value in tag_value_pairs])
self.writer.add_summary(summary, step)
水平有限，如有不當之處，請指教，謝謝！