Bienqq
/
car-detection-bayes
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #1 from ultralytics/master 

update from original master
This commit is contained in:
perry0418 2019-03-25 14:39:41 +08:00 committed by GitHub
parent 35396adc9c 4114d5e9c9
commit 648ed20717
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 157 additions and 190 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
README.md
View File

@ -64,7 +64,7 @@ HS**V** Intensity | +/- 50%
## Speed
https://cloud.google.com/deep-learning-vm/
**Machine type:** n1-highmem-4 (4 vCPUs, 26 GB memory)
**Machine type:** n1-standard-8 (8 vCPUs, 30 GB memory)
**CPU platform:** Intel Skylake
**GPUs:** 1-4 x NVIDIA Tesla P100
**HDD:** 100 GB SSD
@ -72,19 +72,22 @@ https://cloud.google.com/deep-learning-vm/
GPUs | `batch_size` | speed | COCO epoch
--- |---| --- | ---
(P100) | (images) | (s/batch) | (min/epoch)
1 | 16 | 0.54s | 66min
2 | 32 | 0.99s | 61min
4 | 64 | 1.61s | 49min
1 | 16 | 0.39s | 48min
2 | 32 | 0.48s | 29min
4 | 64 | 0.65s | 20min
# Inference
Run `detect.py` to apply trained weights to an image, such as `zidane.jpg` from the `data/samples` folder:
**YOLOv3:** `detect.py --cfg cfg/yolov3.cfg --weights weights/yolov3.pt`
<img src="https://user-images.githubusercontent.com/26833433/50524393-b0adc200-0ad5-11e9-9335-4774a1e52374.jpg" width="700">
**YOLOv3:** `python3 detect.py --cfg cfg/yolov3.cfg --weights weights/yolov3.weights`
<img src="https://user-images.githubusercontent.com/26833433/50524393-b0adc200-0ad5-11e9-9335-4774a1e52374.jpg" width="600">
**YOLOv3-tiny:** `detect.py --cfg cfg/yolov3-tiny.cfg --weights weights/yolov3-tiny.pt`
<img src="https://user-images.githubusercontent.com/26833433/50374155-21427380-05ea-11e9-8d24-f1a4b2bac1ad.jpg" width="700">
**YOLOv3-tiny:** `python3 detect.py --cfg cfg/yolov3-tiny.cfg --weights weights/yolov3-tiny.weights`
<img src="https://user-images.githubusercontent.com/26833433/50374155-21427380-05ea-11e9-8d24-f1a4b2bac1ad.jpg" width="600">
**YOLOv3-SPP:** `python3 detect.py --cfg cfg/yolov3-spp.cfg --weights weights/yolov3-spp.weights`
<img src="https://user-images.githubusercontent.com/26833433/54747926-e051ff00-4bd8-11e9-8b5d-93a41d871ec7.jpg" width="600">
## Webcam

3
models.py
View File

@ -174,9 +174,6 @@ class Darknet(nn.Module):
self.module_defs[0]['cfg'] = cfg_path
self.module_defs[0]['height'] = img_size
self.hyperparams, self.module_list = create_modules(self.module_defs)
self.img_size = img_size
self.loss_names = ['loss', 'xy', 'wh', 'conf', 'cls', 'nT']
self.losses = []
def forward(self, x, var=None):
img_size = x.shape[-1]

21
test.py
View File

@ -3,6 +3,8 @@ import json
import time
from pathlib import Path
from torch.utils.data import DataLoader
from models import *
from utils.datasets import *
from utils.utils import *
@ -39,16 +41,21 @@ def test(
model.to(device).eval()
# Get dataloader
# dataloader = torch.utils.data.DataLoader(LoadImagesAndLabels(test_path), batch_size=batch_size)
dataloader = LoadImagesAndLabels(test_path, batch_size=batch_size, img_size=img_size)
# Dataloader
dataset = LoadImagesAndLabels(test_path, img_size=img_size)
dataloader = DataLoader(dataset, batch_size=batch_size, num_workers=4)
mean_mAP, mean_R, mean_P, seen = 0.0, 0.0, 0.0, 0
print('%11s' * 5 % ('Image', 'Total', 'P', 'R', 'mAP'))
mP, mR, mAPs, TP, jdict = [], [], [], [], []
AP_accum, AP_accum_count = np.zeros(nC), np.zeros(nC)
coco91class = coco80_to_coco91_class()
for (imgs, targets, paths, shapes) in dataloader:
for imgs, targets, paths, shapes in dataloader:
# Unpad and collate targets
for j, t in enumerate(targets):
t[:, 0] = j
targets = torch.cat([t[t[:, 5].nonzero()] for t in targets], 0).squeeze(1)
targets = targets.to(device)
t = time.time()
output = model(imgs.to(device))
@ -71,7 +78,7 @@ def test(
if save_json:
# [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ...
box = detections[:, :4].clone() # xyxy
scale_coords(img_size, box, shapes[si]) # to original shape
scale_coords(img_size, box, (shapes[0][si], shapes[1][si])) # to original shape
box = xyxy2xywh(box) # xywh
box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner
@ -129,7 +136,7 @@ def test(
# Print image mAP and running mean mAP
print(('%11s%11s' + '%11.3g' * 4 + 's') %
(seen, dataloader.nF, mean_P, mean_R, mean_mAP, time.time() - t))
(seen, len(dataset), mean_P, mean_R, mean_mAP, time.time() - t))
# Print mAP per class
print('\nmAP Per Class:')
@ -139,7 +146,7 @@ def test(
# Save JSON
if save_json:
imgIds = [int(Path(x).stem.split('_')[-1]) for x in dataloader.img_files]
imgIds = [int(Path(x).stem.split('_')[-1]) for x in dataset.img_files]
with open('results.json', 'w') as file:
json.dump(jdict, file)

77
train.py
View File

@ -1,6 +1,8 @@
import argparse
import time
from torch.utils.data import DataLoader
import test # Import test.py to get mAP after each epoch
from models import *
from utils.datasets import *
@ -17,6 +19,7 @@ def train(
accumulate=1,
multi_scale=False,
freeze_backbone=False,
num_workers=0
):
weights = 'weights' + os.sep
latest = weights + 'latest.pt'
@ -34,47 +37,39 @@ def train(
# Initialize model
model = Darknet(cfg, img_size).to(device)
# Get dataloader
dataloader = LoadImagesAndLabels(train_path, batch_size, img_size, augment=True)
# dataloader = torch.utils.data.DataLoader(dataloader, batch_size=batch_size, num_workers=0)
# Optimizer
lr0 = 0.001 # initial learning rate
optimizer = torch.optim.SGD(model.parameters(), lr=lr0, momentum=.9)
# Dataloader
dataset = LoadImagesAndLabels(train_path, img_size=img_size, augment=True)
dataloader = DataLoader(dataset, batch_size=batch_size, num_workers=num_workers)
cutoff = -1 # backbone reaches to cutoff layer
start_epoch = 0
best_loss = float('inf')
if resume:
checkpoint = torch.load(latest, map_location=device)
# Load weights to resume from
if resume: # Load previously saved PyTorch model
checkpoint = torch.load(latest, map_location=device) # load checkpoint
model.load_state_dict(checkpoint['model'])
# Transfer learning (train only YOLO layers)
# for i, (name, p) in enumerate(model.named_parameters()):
# p.requires_grad = True if (p.shape[0] == 255) else False
# Set optimizer
optimizer = torch.optim.SGD(filter(lambda x: x.requires_grad, model.parameters()), lr=lr0, momentum=.9)
start_epoch = checkpoint['epoch'] + 1
if checkpoint['optimizer'] is not None:
optimizer.load_state_dict(checkpoint['optimizer'])
best_loss = checkpoint['best_loss']
del checkpoint # current, saved
else:
# Initialize model with backbone (optional)
else: # Initialize model with backbone (optional)
if cfg.endswith('yolov3.cfg'):
cutoff = load_darknet_weights(model, weights + 'darknet53.conv.74')
elif cfg.endswith('yolov3-tiny.cfg'):
cutoff = load_darknet_weights(model, weights + 'yolov3-tiny.conv.15')
# Set optimizer
optimizer = torch.optim.SGD(model.parameters(), lr=lr0, momentum=.9)
if torch.cuda.device_count() > 1:
print('WARNING: MultiGPU Issue: https://github.com/ultralytics/yolov3/issues/146')
model = nn.DataParallel(model)
model.to(device).train()
# Transfer learning (train only YOLO layers)
# for i, (name, p) in enumerate(model.named_parameters()):
# p.requires_grad = True if (p.shape[0] == 255) else False
# Set scheduler
# scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=[54, 61], gamma=0.1)
@ -94,10 +89,7 @@ def train(
# scheduler.step()
# Update scheduler (manual)
if epoch > 250:
lr = lr0 / 10
else:
lr = lr0
lr = lr0 / 10 if epoch > 250 else lr0
for x in optimizer.param_groups:
x['lr'] = lr
@ -107,14 +99,28 @@ def train(
if int(name.split('.')[1]) < cutoff: # if layer < 75
p.requires_grad = False if (epoch == 0) else True
ui = -1
rloss = defaultdict(float)
for i, (imgs, targets, _, _) in enumerate(dataloader):
targets = targets.to(device)
nT = targets.shape[0]
# Unpad and collate targets
for j, t in enumerate(targets):
t[:, 0] = j
targets = torch.cat([t[t[:, 5].nonzero()] for t in targets], 0).squeeze(1)
nT = len(targets)
if nT == 0: # if no targets continue
continue
# Plot images with bounding boxes
plot_images = False
if plot_images:
import matplotlib.pyplot as plt
plt.figure(figsize=(10, 10))
for ip in range(batch_size):
labels = xywh2xyxy(targets[targets[:, 0] == ip, 2:6]).numpy() * img_size
plt.subplot(4, 4, ip + 1).imshow(imgs[ip].numpy().transpose(1, 2, 0))
plt.plot(labels[:, [0, 2, 2, 0, 0]].T, labels[:, [1, 1, 3, 3, 1]].T, '.-')
plt.axis('off')
# SGD burn-in
if (epoch == 0) and (i <= n_burnin):
lr = lr0 * (i / n_burnin) ** 4
@ -125,7 +131,7 @@ def train(
pred = model(imgs.to(device))
# Build targets
target_list = build_targets(model, targets, pred)
target_list = build_targets(model, targets.to(device), pred)
# Compute loss
loss, loss_dict = compute_loss(pred, target_list)
@ -139,9 +145,8 @@ def train(
optimizer.zero_grad()
# Running epoch-means of tracked metrics
ui += 1
for key, val in loss_dict.items():
rloss[key] = (rloss[key] * ui + val) / (ui + 1)
rloss[key] = (rloss[key] * i + val) / (i + 1)
s = ('%8s%12s' + '%10.3g' * 7) % (
'%g/%g' % (epoch, epochs - 1),
@ -154,8 +159,8 @@ def train(
# Multi-Scale training (320 - 608 pixels) every 10 batches
if multi_scale and (i + 1) % 10 == 0:
dataloader.img_size = random.choice(range(10, 20)) * 32
print('multi_scale img_size = %g' % dataloader.img_size)
dataset.img_size = random.choice(range(10, 20)) * 32
print('multi_scale img_size = %g' % dataset.img_size)
# Update best loss
if rloss['total'] < best_loss:
@ -198,6 +203,7 @@ if __name__ == '__main__':
parser.add_argument('--multi-scale', action='store_true', help='random image sizes per batch 320 - 608')
parser.add_argument('--img-size', type=int, default=32 * 13, help='pixels')
parser.add_argument('--resume', action='store_true', help='resume training flag')
parser.add_argument('--num-workers', type=int, default=4, help='number of Pytorch DataLoader workers')
opt = parser.parse_args()
print(opt, end='\n\n')
@ -212,4 +218,5 @@ if __name__ == '__main__':
batch_size=opt.batch_size,
accumulate=opt.accumulate,
multi_scale=opt.multi_scale,
num_workers=opt.num_workers
)

96
utils/datasets.py
View File

@ -6,8 +6,8 @@ import random
import cv2
import numpy as np
import torch
from torch.utils.data import Dataset
# from torch.utils.data import Dataset
from utils.utils import xyxy2xywh
@ -89,52 +89,23 @@ class LoadWebcam: # for inference
return 0
class LoadImagesAndLabels: # for training
def __init__(self, path, batch_size=1, img_size=608, augment=False):
class LoadImagesAndLabels(Dataset): # for training/testing
def __init__(self, path, img_size=416, augment=False):
with open(path, 'r') as file:
self.img_files = file.read().splitlines()
self.img_files = list(filter(lambda x: len(x) > 0, self.img_files))
self.nF = len(self.img_files) # number of image files
self.nB = math.ceil(self.nF / batch_size) # number of batches
assert self.nF > 0, 'No images found in %s' % path
assert len(self.img_files) > 0, 'No images found in %s' % path
self.img_size = img_size
self.augment = augment
self.label_files = [x.replace('images', 'labels').replace('.png', '.txt').replace('.jpg', '.txt')
for x in self.img_files]
self.batch_size = batch_size
self.img_size = img_size
self.augment = augment
iter(self)
def __iter__(self):
self.count = -1
self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF)
return self
def __len__(self):
return len(self.img_files)
def __getitem__(self, index):
imgs, labels0, img_paths, img_shapes = self.load_images(index, index + 1)
labels0[:,0] = index % self.batch_size
labels = torch.zeros(100, 6)
labels[:min(len(labels0), 100)] = labels0 # max 100 labels per image
return imgs.squeeze(0), labels, img_paths, img_shapes
def __next__(self):
self.count += 1 # batches
if self.count >= self.nB:
raise StopIteration
ia = self.count * self.batch_size # start index
ib = min(ia + self.batch_size, self.nF) # end index
return self.load_images(ia, ib)
def load_images(self, ia, ib):
img_all, labels_all, img_paths, img_shapes = [], [], [], []
for index, files_index in enumerate(range(ia, ib)):
img_path = self.img_files[self.shuffled_vector[files_index]]
label_path = self.label_files[self.shuffled_vector[files_index]]
img_path = self.img_files[index]
label_path = self.label_files[index]
img = cv2.imread(img_path) # BGR
assert img is not None, 'File Not Found ' + img_path
@ -166,17 +137,20 @@ class LoadImagesAndLabels: # for training
# Load labels
if os.path.isfile(label_path):
# labels0 = np.loadtxt(label_path, dtype=np.float32).reshape(-1, 5) # SLOWER
with open(label_path, 'r') as file:
lines = file.read().splitlines()
labels0 = np.array([x.split() for x in lines], dtype=np.float32)
x = np.array([x.split() for x in lines], dtype=np.float32)
if x.size is 0:
# Empty labels file
labels = np.array([])
else:
# Normalized xywh to pixel xyxy format
labels = labels0.copy()
labels[:, 1] = ratio * w * (labels0[:, 1] - labels0[:, 3] / 2) + padw
labels[:, 2] = ratio * h * (labels0[:, 2] - labels0[:, 4] / 2) + padh
labels[:, 3] = ratio * w * (labels0[:, 1] + labels0[:, 3] / 2) + padw
labels[:, 4] = ratio * h * (labels0[:, 2] + labels0[:, 4] / 2) + padh
labels = x.copy()
labels[:, 1] = ratio * w * (x[:, 1] - x[:, 3] / 2) + padw
labels[:, 2] = ratio * h * (x[:, 2] - x[:, 4] / 2) + padh
labels[:, 3] = ratio * w * (x[:, 1] + x[:, 3] / 2) + padw
labels[:, 4] = ratio * h * (x[:, 2] + x[:, 4] / 2) + padh
else:
labels = np.array([])
@ -184,18 +158,10 @@ class LoadImagesAndLabels: # for training
if self.augment:
img, labels, M = random_affine(img, labels, degrees=(-5, 5), translate=(0.10, 0.10), scale=(0.90, 1.10))
plotFlag = False
if plotFlag:
import matplotlib.pyplot as plt
plt.figure(figsize=(10, 10)) if index == 0 else None
plt.subplot(4, 4, index + 1).imshow(img[:, :, ::-1])
plt.plot(labels[:, [1, 3, 3, 1, 1]].T, labels[:, [2, 2, 4, 4, 2]].T, '.-')
plt.axis('off')
nL = len(labels)
if nL > 0:
# convert xyxy to xywh
labels[:, 1:5] = xyxy2xywh(labels[:, 1:5].copy()) / self.img_size
labels[:, 1:5] = xyxy2xywh(labels[:, 1:5]) / self.img_size
if self.augment:
# random left-right flip
@ -212,24 +178,16 @@ class LoadImagesAndLabels: # for training
if nL > 0:
labels[:, 2] = 1 - labels[:, 2]
labels_out = np.zeros((100, 6), dtype=np.float32)
if nL > 0:
labels = np.concatenate((np.zeros((nL, 1), dtype='float32') + index, labels), 1)
labels_all.append(labels)
img_all.append(img)
img_paths.append(img_path)
img_shapes.append((h, w))
labels_out[:nL, 1:] = labels # max 100 labels per image
# Normalize
img_all = np.stack(img_all)[:, :, :, ::-1].transpose(0, 3, 1, 2) # list to np.array and BGR to RGB
img_all = np.ascontiguousarray(img_all, dtype=np.float32) # uint8 to float32
img_all /= 255.0 # 0 - 255 to 0.0 - 1.0
img = img[:, :, ::-1].transpose(2, 0, 1) # list to np.array and BGR to RGB
img = np.ascontiguousarray(img, dtype=np.float32) # uint8 to float32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
labels_all = torch.from_numpy(np.concatenate(labels_all, 0))
return torch.from_numpy(img_all), labels_all, img_paths, img_shapes
def __len__(self):
return self.nB # number of batches
return torch.from_numpy(img), torch.from_numpy(labels_out), img_path, (h, w)
def letterbox(img, height=416, color=(127.5, 127.5, 127.5)): # resize a rectangular image to a padded square

28
utils/gcp.sh
View File

@ -6,39 +6,31 @@ bash yolov3/data/get_coco_dataset.sh
sudo rm -rf cocoapi && git clone https://github.com/cocodataset/cocoapi && cd cocoapi/PythonAPI && make && cd ../.. && cp -r cocoapi/PythonAPI/pycocotools yolov3
sudo shutdown
# Start
# Train
sudo rm -rf yolov3 && git clone https://github.com/ultralytics/yolov3
cp -r weights yolov3
cd yolov3 && python3 train.py --batch-size 26
cd yolov3 && python3 train.py --batch-size 16 --epochs 1
sudo shutdown
# Resume
python3 train.py --resume
# Detect
gsutil cp gs://ultralytics/yolov3.pt yolov3/weights
python3 detect.py
# Clone branch
# Clone a branch
sudo rm -rf yolov3 && git clone -b multi_gpu --depth 1 https://github.com/ultralytics/yolov3
cd yolov3 && python3 train.py --batch-size 26
sudo rm -rf yolov3 && git clone -b multigpu --depth 1 https://github.com/alexpolichroniadis/yolov3
cp coco.data yolov3/cfg
cd yolov3 && python3 train.py --batch-size 26
# Test
sudo rm -rf yolov3 && git clone https://github.com/ultralytics/yolov3
sudo rm -rf cocoapi && git clone https://github.com/cocodataset/cocoapi && cd cocoapi/PythonAPI && make && cd ../.. && cp -r cocoapi/PythonAPI/pycocotools yolov3
cd yolov3 && python3 test.py --save-json --conf-thres 0.005
# Test Darknet
# Test Darknet training
python3 test.py --img_size 416 --weights ../darknet/backup/yolov3.backup
# Download and Resume
sudo rm -rf yolov3 && git clone https://github.com/ultralytics/yolov3 && cd yolov3
# Download with wget
wget https://storage.googleapis.com/ultralytics/yolov3.pt -O weights/latest.pt
python3 train.py --img_size 416 --batch_size 16 --epochs 1 --resume
python3 test.py --img_size 416 --weights weights/latest.pt --conf_thres 0.5
# Copy latest.pt to bucket
gsutil cp yolov3/weights/latest.pt gs://ultralytics
@ -47,8 +39,8 @@ gsutil cp yolov3/weights/latest.pt gs://ultralytics
gsutil cp gs://ultralytics/latest.pt yolov3/weights/latest.pt
wget https://storage.googleapis.com/ultralytics/latest.pt
# Testing
sudo rm -rf yolov3 && git clone https://github.com/ultralytics/yolov3 && cd yolov3
python3 train.py --epochs 3 --var 64
# Trade Studies
sudo rm -rf yolov3 && git clone https://github.com/ultralytics/yolov3
cp -r weights yolov3
cd yolov3 && python3 train.py --batch-size 16 --epochs 1
sudo shutdown

7
utils/utils.py
View File

@ -15,6 +15,9 @@ from utils import torch_utils
torch.set_printoptions(linewidth=1320, precision=5, profile='long')
np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format}) # format short g, %precision=5
# Prevent OpenCV from multithreading (to use PyTorch DataLoader)
cv2.setNumThreads(0)
def float3(x): # format floats to 3 decimals
return float(format(x, '.3f'))
@ -37,10 +40,10 @@ def model_info(model):
# Plots a line-by-line description of a PyTorch model
n_p = sum(x.numel() for x in model.parameters()) # number parameters
n_g = sum(x.numel() for x in model.parameters() if x.requires_grad) # number gradients
print('\n%5s %38s %9s %12s %20s %12s %12s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
print('\n%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
for i, (name, p) in enumerate(model.named_parameters()):
name = name.replace('module_list.', '')
print('%5g %38s %9s %12g %20s %12.3g %12.3g' % (
print('%5g %40s %9s %12g %20s %10.3g %10.3g' % (
i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std()))
print('Model Summary: %g layers, %g parameters, %g gradients' % (i + 1, n_p, n_g))