add *.jpeg support

This commit is contained in:
Glenn Jocher 2019-05-10 14:15:09 +02:00
parent 9a13bb53c8
commit 31592c276f
4 changed files with 34 additions and 12 deletions

View File

@ -176,14 +176,17 @@ def test(
map = cocoEval.stats[1] # update mAP to pycocotools mAP map = cocoEval.stats[1] # update mAP to pycocotools mAP
# Return results # Return results
return mp, mr, map, mf1, loss / len(dataloader) maps = np.zeros(nc)
for i, c in enumerate(ap_class):
maps[c] = ap[i]
return (mp, mr, map, mf1, loss / len(dataloader)), maps
if __name__ == '__main__': if __name__ == '__main__':
parser = argparse.ArgumentParser(prog='test.py') parser = argparse.ArgumentParser(prog='test.py')
parser.add_argument('--batch-size', type=int, default=16, help='size of each image batch') parser.add_argument('--batch-size', type=int, default=16, help='size of each image batch')
parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='cfg file path') parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='cfg file path')
parser.add_argument('--data-cfg', type=str, default='data/coco.data', help='coco.data file path') parser.add_argument('--data-cfg', type=str, default='data/coco_64img.data', help='coco.data file path')
parser.add_argument('--weights', type=str, default='weights/yolov3-spp.weights', help='path to weights file') parser.add_argument('--weights', type=str, default='weights/yolov3-spp.weights', help='path to weights file')
parser.add_argument('--iou-thres', type=float, default=0.5, help='iou threshold required to qualify as detected') parser.add_argument('--iou-thres', type=float, default=0.5, help='iou threshold required to qualify as detected')
parser.add_argument('--conf-thres', type=float, default=0.001, help='object confidence threshold') parser.add_argument('--conf-thres', type=float, default=0.001, help='object confidence threshold')

View File

@ -23,6 +23,7 @@ hyp = {'xy': 0.5, # xy loss gain
'weight_decay': 0.0005, # optimizer weight decay 'weight_decay': 0.0005, # optimizer weight decay
} }
# Original # Original
# hyp = {'xy': 0.5, # xy loss gain # hyp = {'xy': 0.5, # xy loss gain
# 'wh': 0.0625, # wh loss gain # 'wh': 0.0625, # wh loss gain
@ -36,7 +37,6 @@ hyp = {'xy': 0.5, # xy loss gain
# } # }
def train( def train(
cfg, cfg,
data_cfg, data_cfg,
@ -119,7 +119,7 @@ def train(
# plt.savefig('LR.png', dpi=300) # plt.savefig('LR.png', dpi=300)
# Dataset # Dataset
dataset = LoadImagesAndLabels(train_path, img_size, batch_size, augment=True) dataset = LoadImagesAndLabels(train_path, img_size, batch_size, augment=True, image_weighting=False)
# Initialize distributed training # Initialize distributed training
if torch.cuda.device_count() > 1: if torch.cuda.device_count() > 1:
@ -147,6 +147,7 @@ def train(
model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) # attach class weights model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) # attach class weights
model_info(model) model_info(model)
nb = len(dataloader) nb = len(dataloader)
maps = np.zeros(nc) # mAP per class
results = (0, 0, 0, 0, 0) # P, R, mAP, F1, test_loss results = (0, 0, 0, 0, 0) # P, R, mAP, F1, test_loss
n_burnin = min(round(nb / 5 + 1), 1000) # burn-in batches n_burnin = min(round(nb / 5 + 1), 1000) # burn-in batches
for f in glob.glob('train_batch*.jpg') + glob.glob('test_batch*.jpg'): for f in glob.glob('train_batch*.jpg') + glob.glob('test_batch*.jpg'):
@ -165,6 +166,9 @@ def train(
if int(name.split('.')[1]) < cutoff: # if layer < 75 if int(name.split('.')[1]) < cutoff: # if layer < 75
p.requires_grad = False if epoch == 0 else True p.requires_grad = False if epoch == 0 else True
# Update image weights (optional)
dataset.image_weights = labels_to_image_weights(dataset.labels, nc=nc, class_weights=1 - maps)
mloss = torch.zeros(5).to(device) # mean losses mloss = torch.zeros(5).to(device) # mean losses
for i, (imgs, targets, _, _) in enumerate(dataloader): for i, (imgs, targets, _, _) in enumerate(dataloader):
imgs = imgs.to(device) imgs = imgs.to(device)
@ -218,9 +222,9 @@ def train(
print('multi_scale img_size = %g' % dataset.img_size) print('multi_scale img_size = %g' % dataset.img_size)
# Calculate mAP (always test final epoch, skip first 5 if opt.nosave) # Calculate mAP (always test final epoch, skip first 5 if opt.nosave)
if not (opt.notest or (opt.nosave and epoch < 5)) or epoch == epochs - 1: if not (opt.notest or (opt.nosave and epoch < 10)) or epoch == epochs - 1:
with torch.no_grad(): with torch.no_grad():
results = test.test(cfg, data_cfg, batch_size=batch_size, img_size=img_size, model=model, results, maps = test.test(cfg, data_cfg, batch_size=batch_size, img_size=img_size, model=model,
conf_thres=0.1) conf_thres=0.1)
# Write epoch results # Write epoch results

View File

@ -130,12 +130,13 @@ class LoadWebcam: # for inference
class LoadImagesAndLabels(Dataset): # for training/testing class LoadImagesAndLabels(Dataset): # for training/testing
def __init__(self, path, img_size=416, batch_size=16, augment=False, rect=True): def __init__(self, path, img_size=416, batch_size=16, augment=False, rect=True, image_weighting=False):
with open(path, 'r') as f: with open(path, 'r') as f:
img_files = f.read().splitlines() img_files = f.read().splitlines()
self.img_files = list(filter(lambda x: len(x) > 0, img_files)) self.img_files = list(filter(lambda x: len(x) > 0, img_files))
n = len(self.img_files) n = len(self.img_files)
self.n = n
assert n > 0, 'No images found in %s' % path assert n > 0, 'No images found in %s' % path
self.img_size = img_size self.img_size = img_size
self.augment = augment self.augment = augment
@ -145,9 +146,11 @@ class LoadImagesAndLabels(Dataset): # for training/testing
replace('.bmp', '.txt'). replace('.bmp', '.txt').
replace('.png', '.txt') for x in self.img_files] replace('.png', '.txt') for x in self.img_files]
self.image_weighting = image_weighting
self.rect = False if image_weighting else rect
# Rectangular Training https://github.com/ultralytics/yolov3/issues/232 # Rectangular Training https://github.com/ultralytics/yolov3/issues/232
self.pad_rectangular = rect if self.rect:
if self.pad_rectangular:
from PIL import Image from PIL import Image
bi = np.floor(np.arange(n) / batch_size).astype(np.int) # batch index bi = np.floor(np.arange(n) / batch_size).astype(np.int) # batch index
nb = bi[-1] + 1 # number of batches nb = bi[-1] + 1 # number of batches
@ -200,6 +203,9 @@ class LoadImagesAndLabels(Dataset): # for training/testing
return len(self.img_files) return len(self.img_files)
def __getitem__(self, index): def __getitem__(self, index):
if self.image_weighting:
index = random.choices(range(self.n), weights=self.image_weights, k=1)[0] # random weighted index
img_path = self.img_files[index] img_path = self.img_files[index]
label_path = self.label_files[index] label_path = self.label_files[index]
@ -230,7 +236,7 @@ class LoadImagesAndLabels(Dataset): # for training/testing
# Letterbox # Letterbox
h, w, _ = img.shape h, w, _ = img.shape
if self.pad_rectangular: if self.rect:
new_shape = self.batch_shapes[self.batch[index]] new_shape = self.batch_shapes[self.batch[index]]
img, ratio, padw, padh = letterbox(img, new_shape=new_shape, mode='rect') img, ratio, padw, padh = letterbox(img, new_shape=new_shape, mode='rect')
else: else:
@ -389,7 +395,7 @@ def random_affine(img, targets=(), degrees=(-10, 10), translate=(.1, .1), scale=
h = xy[:, 3] - xy[:, 1] h = xy[:, 3] - xy[:, 1]
area = w * h area = w * h
ar = np.maximum(w / (h + 1e-16), h / (w + 1e-16)) ar = np.maximum(w / (h + 1e-16), h / (w + 1e-16))
i = (w > 2) & (h > 2) & (area / (area0 + 1e-16) > 0.1) & (ar < 10) i = (w > 4) & (h > 4) & (area / (area0 + 1e-16) > 0.1) & (ar < 10)
targets = targets[i] targets = targets[i]
targets[:, 1:5] = xy[i] targets[:, 1:5] = xy[i]

View File

@ -61,6 +61,15 @@ def labels_to_class_weights(labels, nc=80):
return torch.Tensor(weights) return torch.Tensor(weights)
def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)):
# Produces image weights based on class mAPs
n = len(labels)
class_counts = np.array([np.bincount(labels[i][:, 0].astype(np.int), minlength=nc) for i in range(n)])
image_weights = (class_weights.reshape(1, nc) * class_counts).sum(1)
# index = random.choices(range(n), weights=image_weights, k=1) # weight image sample
return image_weights
def coco_class_weights(): # frequency of each class in coco train2014 def coco_class_weights(): # frequency of each class in coco train2014
n = [187437, 4955, 30920, 6033, 3838, 4332, 3160, 7051, 7677, 9167, 1316, 1372, 833, 6757, 7355, 3302, 3776, 4671, n = [187437, 4955, 30920, 6033, 3838, 4332, 3160, 7051, 7677, 9167, 1316, 1372, 833, 6757, 7355, 3302, 3776, 4671,
6769, 5706, 3908, 903, 3686, 3596, 6200, 7920, 8779, 4505, 4272, 1862, 4698, 1962, 4403, 6659, 2402, 2689, 6769, 5706, 3908, 903, 3686, 3596, 6200, 7920, 8779, 4505, 4272, 1862, 4698, 1962, 4403, 6659, 2402, 2689,