Merge pull request #1 from ultralytics/master
update from original master
This commit is contained in:
perry0418
GitHub
commit
648ed20717
19
README.md
19
README.md
|
|
@ -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
|
||||
|
||||
|
|
|
|||
|
|
@ -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
21
test.py
|
|
@ -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
77
train.py
|
|
@ -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
|
||||
)
|
||||
|
|
|
|||
|
|
@ -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
|
||||
|
||||
|
||||
|
|
@ -89,147 +89,105 @@ 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
|
||||
img_path = self.img_files[index]
|
||||
label_path = self.label_files[index]
|
||||
|
||||
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
|
||||
img = cv2.imread(img_path) # BGR
|
||||
assert img is not None, 'File Not Found ' + img_path
|
||||
|
||||
def __next__(self):
|
||||
self.count += 1 # batches
|
||||
if self.count >= self.nB:
|
||||
raise StopIteration
|
||||
augment_hsv = True
|
||||
if self.augment and augment_hsv:
|
||||
# SV augmentation by 50%
|
||||
fraction = 0.50
|
||||
img_hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
|
||||
S = img_hsv[:, :, 1].astype(np.float32)
|
||||
V = img_hsv[:, :, 2].astype(np.float32)
|
||||
|
||||
ia = self.count * self.batch_size # start index
|
||||
ib = min(ia + self.batch_size, self.nF) # end index
|
||||
a = (random.random() * 2 - 1) * fraction + 1
|
||||
S *= a
|
||||
if a > 1:
|
||||
np.clip(S, a_min=0, a_max=255, out=S)
|
||||
|
||||
return self.load_images(ia, ib)
|
||||
a = (random.random() * 2 - 1) * fraction + 1
|
||||
V *= a
|
||||
if a > 1:
|
||||
np.clip(V, a_min=0, a_max=255, out=V)
|
||||
|
||||
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_hsv[:, :, 1] = S.astype(np.uint8)
|
||||
img_hsv[:, :, 2] = V.astype(np.uint8)
|
||||
cv2.cvtColor(img_hsv, cv2.COLOR_HSV2BGR, dst=img)
|
||||
|
||||
img = cv2.imread(img_path) # BGR
|
||||
assert img is not None, 'File Not Found ' + img_path
|
||||
h, w, _ = img.shape
|
||||
img, ratio, padw, padh = letterbox(img, height=self.img_size)
|
||||
|
||||
augment_hsv = True
|
||||
if self.augment and augment_hsv:
|
||||
# SV augmentation by 50%
|
||||
fraction = 0.50
|
||||
img_hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
|
||||
S = img_hsv[:, :, 1].astype(np.float32)
|
||||
V = img_hsv[:, :, 2].astype(np.float32)
|
||||
# Load labels
|
||||
if os.path.isfile(label_path):
|
||||
with open(label_path, 'r') as file:
|
||||
lines = file.read().splitlines()
|
||||
|
||||
a = (random.random() * 2 - 1) * fraction + 1
|
||||
S *= a
|
||||
if a > 1:
|
||||
np.clip(S, a_min=0, a_max=255, out=S)
|
||||
|
||||
a = (random.random() * 2 - 1) * fraction + 1
|
||||
V *= a
|
||||
if a > 1:
|
||||
np.clip(V, a_min=0, a_max=255, out=V)
|
||||
|
||||
img_hsv[:, :, 1] = S.astype(np.uint8)
|
||||
img_hsv[:, :, 2] = V.astype(np.uint8)
|
||||
cv2.cvtColor(img_hsv, cv2.COLOR_HSV2BGR, dst=img)
|
||||
|
||||
h, w, _ = img.shape
|
||||
img, ratio, padw, padh = letterbox(img, height=self.img_size)
|
||||
|
||||
# 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)
|
||||
|
||||
# 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
|
||||
else:
|
||||
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 = 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([])
|
||||
|
||||
# Augment image and labels
|
||||
if self.augment:
|
||||
img, labels, M = random_affine(img, labels, degrees=(-5, 5), translate=(0.10, 0.10), scale=(0.90, 1.10))
|
||||
# Augment image and labels
|
||||
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]) / self.img_size
|
||||
|
||||
nL = len(labels)
|
||||
if nL > 0:
|
||||
# convert xyxy to xywh
|
||||
labels[:, 1:5] = xyxy2xywh(labels[:, 1:5].copy()) / self.img_size
|
||||
if self.augment:
|
||||
# random left-right flip
|
||||
lr_flip = True
|
||||
if lr_flip & (random.random() > 0.5):
|
||||
img = np.fliplr(img)
|
||||
if nL > 0:
|
||||
labels[:, 1] = 1 - labels[:, 1]
|
||||
|
||||
if self.augment:
|
||||
# random left-right flip
|
||||
lr_flip = True
|
||||
if lr_flip & (random.random() > 0.5):
|
||||
img = np.fliplr(img)
|
||||
if nL > 0:
|
||||
labels[:, 1] = 1 - labels[:, 1]
|
||||
# random up-down flip
|
||||
ud_flip = False
|
||||
if ud_flip & (random.random() > 0.5):
|
||||
img = np.flipud(img)
|
||||
if nL > 0:
|
||||
labels[:, 2] = 1 - labels[:, 2]
|
||||
|
||||
# random up-down flip
|
||||
ud_flip = False
|
||||
if ud_flip & (random.random() > 0.5):
|
||||
img = np.flipud(img)
|
||||
if nL > 0:
|
||||
labels[:, 2] = 1 - labels[:, 2]
|
||||
|
||||
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 = np.zeros((100, 6), dtype=np.float32)
|
||||
if nL > 0:
|
||||
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
28
utils/gcp.sh
|
|
@ -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
|
||||
|
||||
|
|
|
|||
|
|
@ -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))
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue