pytorch實現yolov3(5) 實現端到端的目標檢測

torch實現yolov3(1)
torch實現yolov3(2)
torch實現yolov3(3)
torch實現yolov3(4)

前面4篇已經實現了network的forward,並且將network的output已經轉換成了易於操作的detection prediction格式.
本篇把前面四篇實現的功能組織起來,實現端到端的推理過程.

整體流程如下

1. 讀取圖片,對圖片前處理,把圖片調整到模型的input size及輸入順序(rgb c x h x w).
2. 載入模型,讀取模型權重檔案.
3. 將第一步讀到的矩陣送給模型.進行forward運算.得到prediction
4. 後處理,我們得到的box座標是相對於調整後的圖片的.要處理成原圖上的座標.

detector.py 實現完整的端到端的圖片檢測. 用法python detect.py --images dog-cycle-car.png --det det

from __future__ import division
import time
import torch 
import torch.nn as nn
from torch.autograd import Variable
import numpy as np
import cv2 
from util import *
import argparse
import os 
import os.path as osp
from darknet import Darknet
import pickle as pkl
import pandas as pd
import random

def arg_parse():
    """
    Parse arguements to the detect module
    
    """
    
    parser = argparse.ArgumentParser(description='YOLO v3 Detection Module')
   
    parser.add_argument("--images", dest = 'images', help = 
                        "Image / Directory containing images to perform detection upon",
                        default = "imgs", type = str)
    parser.add_argument("--det", dest = 'det', help = 
                        "Image / Directory to store detections to",
                        default = "det", type = str)
    parser.add_argument("--bs", dest = "bs", help = "Batch size", default = 1)
    parser.add_argument("--confidence", dest = "confidence", help = "Object Confidence to filter predictions", default = 0.5)
    parser.add_argument("--nms_thresh", dest = "nms_thresh", help = "NMS Threshhold", default = 0.4)
    parser.add_argument("--cfg", dest = 'cfgfile', help = 
                        "Config file",
                        default = "cfg/yolov3.cfg", type = str)
    parser.add_argument("--weights", dest = 'weightsfile', help = 
                        "weightsfile",
                        default = "yolov3.weights", type = str)
    parser.add_argument("--reso", dest = 'reso', help = 
                        "Input resolution of the network. Increase to increase accuracy. Decrease to increase speed",
                        default = "416", type = str)
    
    return parser.parse_args()
    
args = arg_parse()
images = args.images
batch_size = int(args.bs)
confidence = float(args.confidence)
nms_thesh = float(args.nms_thresh)
start = 0
CUDA = torch.cuda.is_available()

num_classes = 80
classes = load_classes("data/coco.names")

#Set up the neural network
print("Loading network.....")
model = Darknet(args.cfgfile)
model.load_weights(args.weightsfile)
print("Network successfully loaded")

model.net_info["height"] = args.reso
inp_dim = int(model.net_info["height"])
assert inp_dim % 32 == 0 
assert inp_dim > 32

#If there's a GPU availible, put the model on GPU
if CUDA:
    model.cuda()


#Set the model in evaluation mode
model.eval()

read_dir = time.time()
#Detection phase
try:
    imlist = [osp.join(osp.realpath('.'), images, img) for img in os.listdir(images)]
except NotADirectoryError:
    imlist = []
    imlist.append(osp.join(osp.realpath('.'), images))
except FileNotFoundError:
    print ("No file or directory with the name {}".format(images))
    exit()
    
if not os.path.exists(args.det):
    os.makedirs(args.det)

load_batch = time.time()
loaded_ims = [cv2.imread(x) for x in imlist]

im_batches = list(map(prep_image, loaded_ims, [inp_dim for x in range(len(imlist))]))
im_dim_list = [(x.shape[1], x.shape[0]) for x in loaded_ims]
im_dim_list = torch.FloatTensor(im_dim_list).repeat(1,2)


leftover = 0
if (len(im_dim_list) % batch_size):
    leftover = 1

if batch_size != 1:
    num_batches = len(imlist) // batch_size + leftover            
    im_batches = [torch.cat((im_batches[i*batch_size : min((i +  1)*batch_size,
                        len(im_batches))]))  for i in range(num_batches)]  

write = 0


if CUDA:
    im_dim_list = im_dim_list.cuda()
    
start_det_loop = time.time()
for i, batch in enumerate(im_batches):
#load the image 
    start = time.time()
    if CUDA:
        batch = batch.cuda()
    with torch.no_grad():
        prediction = model(Variable(batch), CUDA) #類呼叫,相當於呼叫類的__call__()函式

    prediction = write_results(prediction, confidence, num_classes, nms_conf = nms_thesh)

    end = time.time()

    if type(prediction) == int:

        for im_num, image in enumerate(imlist[i*batch_size: min((i +  1)*batch_size, len(imlist))]):
            im_id = i*batch_size + im_num
            print("{0:20s} predicted in {1:6.3f} seconds".format(image.split("/")[-1], (end - start)/batch_size))
            print("{0:20s} {1:s}".format("Objects Detected:", ""))
            print("----------------------------------------------------------")
        continue

    prediction[:,0] += i*batch_size    #transform the atribute from index in batch to index in imlist 

    if not write:                      #If we have't initialised output
        output = prediction  
        write = 1
    else:
        output = torch.cat((output,prediction))

    for im_num, image in enumerate(imlist[i*batch_size: min((i +  1)*batch_size, len(imlist))]):
        im_id = i*batch_size + im_num
        objs = [classes[int(x[-1])] for x in output if int(x[0]) == im_id]
        print("{0:20s} predicted in {1:6.3f} seconds".format(image.split("/")[-1], (end - start)/batch_size))
        print("{0:20s} {1:s}".format("Objects Detected:", " ".join(objs)))
        print("----------------------------------------------------------")

    if CUDA:
        torch.cuda.synchronize()       
try:
    output
except NameError:
    print ("No detections were made")
    exit()

im_dim_list = torch.index_select(im_dim_list, 0, output[:,0].long())

scaling_factor = torch.min(416/im_dim_list,1)[0].view(-1,1)


output[:,[1,3]] -= (inp_dim - scaling_factor*im_dim_list[:,0].view(-1,1))/2
output[:,[2,4]] -= (inp_dim - scaling_factor*im_dim_list[:,1].view(-1,1))/2



output[:,1:5] /= scaling_factor

for i in range(output.shape[0]):
    output[i, [1,3]] = torch.clamp(output[i, [1,3]], 0.0, im_dim_list[i,0])
    output[i, [2,4]] = torch.clamp(output[i, [2,4]], 0.0, im_dim_list[i,1])
    
    
output_recast = time.time()
class_load = time.time()
colors = pkl.load(open("pallete", "rb"))

draw = time.time()


def write(x, results):
    c1 = tuple(x[1:3].int())
    c2 = tuple(x[3:5].int())
    img = results[int(x[0])]
    cls = int(x[-1])
    color = random.choice(colors)
    label = "{0}".format(classes[cls])
    cv2.rectangle(img, c1, c2,color, 1)
    t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 1 , 1)[0]
    c2 = c1[0] + t_size[0] + 3, c1[1] + t_size[1] + 4
    cv2.rectangle(img, c1, c2,color, -1)
    cv2.putText(img, label, (c1[0], c1[1] + t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 1, [225,255,255], 1);
    return img


list(map(lambda x: write(x, loaded_ims), output))

det_names = pd.Series(imlist).apply(lambda x: "{}/det_{}".format(args.det,x.split("/")[-1]))

list(map(cv2.imwrite, det_names, loaded_ims))


end = time.time()

print("SUMMARY")
print("----------------------------------------------------------")
print("{:25s}: {}".format("Task", "Time Taken (in seconds)"))
print()
print("{:25s}: {:2.3f}".format("Reading addresses", load_batch - read_dir))
print("{:25s}: {:2.3f}".format("Loading batch", start_det_loop - load_batch))
print("{:25s}: {:2.3f}".format("Detection (" + str(len(imlist)) +  " images)", output_recast - start_det_loop))
print("{:25s}: {:2.3f}".format("Output Processing", class_load - output_recast))
print("{:25s}: {:2.3f}".format("Drawing Boxes", end - draw))
print("{:25s}: {:2.3f}".format("Average time_per_img", (end - load_batch)/len(imlist)))
print("----------------------------------------------------------")


torch.cuda.empty_cache()
    

第一段沒啥好說的,我們希望可以通過命令列傳參,所以用ArgParse模組來實現引數解析.

第二段 模型載入

#Set up the neural network
print("Loading network.....")
model = Darknet(args.cfgfile)
model.load_weights(args.weightsfile)
print("Network successfully loaded")

第三段 影象預處理

對任意一個圖片,要先做預處理,把尺寸處理到model的input size.

read_dir = time.time()
#Detection phase
try:
    imlist = [osp.join(osp.realpath('.'), images, img) for img in os.listdir(images)]
except NotADirectoryError:
    imlist = []
    imlist.append(osp.join(osp.realpath('.'), images))
except FileNotFoundError:
    print ("No file or directory with the name {}".format(images))
    exit()
    
if not os.path.exists(args.det):
    os.makedirs(args.det)

load_batch = time.time()
loaded_ims = [cv2.imread(x) for x in imlist]

im_batches = list(map(prep_image, loaded_ims, [inp_dim for x in range(len(imlist))]))
im_dim_list = [(x.shape[1], x.shape[0]) for x in loaded_ims]
im_dim_list = torch.FloatTensor(im_dim_list).repeat(1,2)


leftover = 0
if (len(im_dim_list) % batch_size):
    leftover = 1

if batch_size != 1:
    num_batches = len(imlist) // batch_size + leftover            
    im_batches = [torch.cat((im_batches[i*batch_size : min((i +  1)*batch_size,
                        len(im_batches))]))  for i in range(num_batches)]  

從某個目錄讀入n多個圖片.假設模型每個batch處理5個圖片.圖片為320 x 320 x 3. 則每次輸入模型的矩陣為(320*5) x 320 x 3.即

im_batches = [torch.cat((im_batches[i*batch_size : min((i +  1)*batch_size,
                        len(im_batches))]))  for i in range(num_batches)] 

所做的事情.

圖片的前處理所用到的一些工具函式如下.

def letterbox_image(img, inp_dim):
    '''resize image with unchanged aspect ratio using padding'''
    img_w, img_h = img.shape[1], img.shape[0]
    w, h = inp_dim
    new_w = int(img_w * min(w/img_w, h/img_h))
    new_h = int(img_h * min(w/img_w, h/img_h))
    resized_image = cv2.resize(img, (new_w,new_h), interpolation = cv2.INTER_CUBIC)
    
    canvas = np.full((inp_dim[1], inp_dim[0], 3), 128)

    canvas[(h-new_h)//2:(h-new_h)//2 + new_h,(w-new_w)//2:(w-new_w)//2 + new_w,  :] = resized_image
    
    return canvas

保證原有圖片的寬高比,其餘位置灰度值填充.

cv讀進來的bgr格式,我們轉成rgb的.然後transpose 把h x w x c的轉成c x h x w的.

def prep_image(img, inp_dim):
    """
    Prepare image for inputting to the neural network. 
    
    Returns a Variable 
    """

    img = cv2.resize(img, (inp_dim, inp_dim
    img = img[:,:,::-1].transpose((2,0,1)).copy()
    img = torch.from_numpy(img).float().div(255.0).unsqueeze(0)
    return img

參考https://www.cnblogs.com/sdu20112013/p/11216322.html

4.將矩陣餵給模型,進行forward

for i, batch in enumerate(im_batches):
#load the image 
    start = time.time()
    if CUDA:
        batch = batch.cuda()
    with torch.no_grad():
        prediction = model(Variable(batch), CUDA) #類呼叫,相當於呼叫類的__call__()函式

    prediction = write_results(prediction, confidence, num_classes, nms_conf = nms_thesh)

    end = time.time()

    if type(prediction) == int:

        for im_num, image in enumerate(imlist[i*batch_size: min((i +  1)*batch_size, len(imlist))]):
            im_id = i*batch_size + im_num
            print("{0:20s} predicted in {1:6.3f} seconds".format(image.split("/")[-1], (end - start)/batch_size))
            print("{0:20s} {1:s}".format("Objects Detected:", ""))
            print("----------------------------------------------------------")
        continue

    prediction[:,0] += i*batch_size    #transform the atribute from index in batch to index in imlist 

    if not write:                      #If we have't initialised output
        output = prediction  
        write = 1
    else:
        output = torch.cat((output,prediction))

    for im_num, image in enumerate(imlist[i*batch_size: min((i +  1)*batch_size, len(imlist))]):
        im_id = i*batch_size + im_num
        objs = [classes[int(x[-1])] for x in output if int(x[0]) == im_id]
        print("{0:20s} predicted in {1:6.3f} seconds".format(image.split("/")[-1], (end - start)/batch_size))
        print("{0:20s} {1:s}".format("Objects Detected:", " ".join(objs)))
        print("----------------------------------------------------------")

其中重點就是

prediction = model(Variable(batch), CUDA) #類呼叫,相當於呼叫類的__call__()函式,

prediction = write_results(prediction, confidence, num_classes, nms_conf = nms_thesh)

涉及到一個python語法,類例項呼叫.其實就相當於呼叫__call__().基類nn.module的__call__()裡呼叫了forward().所以這一句實際上就相當於呼叫model.forward(batch).

5.後處理

im_dim_list = torch.index_select(im_dim_list, 0, output[:,0].long())

scaling_factor = torch.min(416/im_dim_list,1)[0].view(-1,1)


output[:,[1,3]] -= (inp_dim - scaling_factor*im_dim_list[:,0].view(-1,1))/2
output[:,[2,4]] -= (inp_dim - scaling_factor*im_dim_list[:,1].view(-1,1))/2



output[:,1:5] /= scaling_factor

for i in range(output.shape[0]):
    output[i, [1,3]] = torch.clamp(output[i, [1,3]], 0.0, im_dim_list[i,0])
    output[i, [2,4]] = torch.clamp(output[i, [2,4]], 0.0, im_dim_list[i,1])
    

output中的box座標是相對於模型的輸入圖片的,將其對映到相對於原始圖片的位置.

圖片繪製,涉及python基礎語法參考https://www.cnblogs.com/sdu20112013/p/11216584.html

list(map(lambda x: write(x, loaded_ims), output))

det_names = pd.Series(imlist).apply(lambda x: "{}/det_{}".format(args.det,x.split("/")[-1]))

list(map(cv2.imwrite, det_names, loaded_ims))