I have modified the resolution, classes and convolutional1 settings in cfg.py. My dataset has the resolution of 640x480. However, It gives me error like this.
Epoch 1/300: 0%| | 0/271 [00:02<?, ?img/s]
Traceback (most recent call last):
File "/home/psc/PycharmProjects/FYP/pytorch-YOLOv4/train.py", line 628, in
train(model=model,
File "/home/psc/PycharmProjects/FYP/pytorch-YOLOv4/train.py", line 381, in train
loss, loss_xy, loss_wh, loss_obj, loss_cls, loss_l2 = criterion(bboxes_pred, bboxes)
File "/home/psc/anaconda3/envs/FYP/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/home/psc/PycharmProjects/FYP/pytorch-YOLOv4/train.py", line 243, in forward
output = output.view(batchsize, self.n_anchors, n_ch, fsize, fsize)
RuntimeError: shape '[4, 3, 6, 60, 60]' is invalid for input of size 345600
I have modified the resolution, classes and convolutional1 settings in cfg.py. My dataset has the resolution of 640x480. However, It gives me error like this.
Epoch 1/300: 0%| | 0/271 [00:02<?, ?img/s] Traceback (most recent call last): File "/home/psc/PycharmProjects/FYP/pytorch-YOLOv4/train.py", line 628, in
train(model=model,
File "/home/psc/PycharmProjects/FYP/pytorch-YOLOv4/train.py", line 381, in train
loss, loss_xy, loss_wh, loss_obj, loss_cls, loss_l2 = criterion(bboxes_pred, bboxes)
File "/home/psc/anaconda3/envs/FYP/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/home/psc/PycharmProjects/FYP/pytorch-YOLOv4/train.py", line 243, in forward
output = output.view(batchsize, self.n_anchors, n_ch, fsize, fsize)
RuntimeError: shape '[4, 3, 6, 60, 60]' is invalid for input of size 345600
And here is my cfg.py:
-- coding: utf-8 --
''' @Time : 2020/05/06 21:05 @Author : Tianxiaomo @File : Cfg.py @Noice : @Modificattion : @Author : @Time : @Detail :
''' import os from easydict import EasyDict
_BASE_DIR = os.path.dirname(os.path.abspath(file))
Cfg = EasyDict()
Cfg.use_darknet_cfg = True Cfg.cfgfile = os.path.join(_BASE_DIR, 'cfg', 'yolov4-custom.cfg')
Cfg.batch = 4 Cfg.subdivisions = 1 Cfg.width = 640 Cfg.height = 480 Cfg.channels = 3 Cfg.momentum = 0.949 Cfg.decay = 0.0005 Cfg.angle = 0 Cfg.saturation = 1.5 Cfg.exposure = 1.5 Cfg.hue = .1
Cfg.learning_rate = 0.00261 Cfg.burn_in = 1000 Cfg.max_batches = 500500 Cfg.steps = [400000, 450000] Cfg.policy = Cfg.steps Cfg.scales = .1, .1
Cfg.cutmix = 0 Cfg.mosaic = 1
Cfg.letter_box = 0 Cfg.jitter = 0.2 Cfg.classes = 1 Cfg.track = 0 Cfg.w = Cfg.width Cfg.h = Cfg.height Cfg.flip = 1 Cfg.blur = 0 Cfg.gaussian = 0 Cfg.boxes = 60 # box num Cfg.TRAIN_EPOCHS = 300 Cfg.train_label = os.path.join(_BASE_DIR, 'data', 'train.txt') Cfg.val_label = os.path.join(_BASE_DIR, 'data' ,'val.txt') Cfg.TRAIN_OPTIMIZER = 'adam' ''' image_path1 x1,y1,x2,y2,id x1,y1,x2,y2,id x1,y1,x2,y2,id ... image_path2 x1,y1,x2,y2,id x1,y1,x2,y2,id x1,y1,x2,y2,id ... ... '''
if Cfg.mosaic and Cfg.cutmix: Cfg.mixup = 4 elif Cfg.cutmix: Cfg.mixup = 2 elif Cfg.mosaic: Cfg.mixup = 3
Cfg.checkpoints = os.path.join(_BASE_DIR, 'checkpoints') Cfg.TRAIN_TENSORBOARD_DIR = os.path.join(_BASE_DIR, 'log')
Cfg.iou_type = 'iou' # 'giou', 'diou', 'ciou'
Cfg.keep_checkpoint_max = 10
And my yolov4-custom.cfg
[net]
Testing
batch=1
subdivisions=1
Training
batch=4 subdivisions=1 width=640 height=480 channels=3 momentum=0.949 decay=0.0005 angle=0 saturation = 1.5 exposure = 1.5 hue=.1
learning_rate=0.001 burn_in=1000 max_batches = 500500 policy=steps steps=400000,450000 scales=.1,.1
cutmix=1
mosaic=1
:104x104 54:52x52 85:26x26 104:13x13 for 416
[convolutional] batch_normalize=1 filters=32 size=3 stride=1 pad=1 activation=mish
Downsample
[convolutional] batch_normalize=1 filters=64 size=3 stride=2 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish
[route] layers = -2
[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=32 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish
[route] layers = -1,-7
[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish
Downsample
[convolutional] batch_normalize=1 filters=128 size=3 stride=2 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish
[route] layers = -2
[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=mish
[route] layers = -1,-10
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish
Downsample
[convolutional] batch_normalize=1 filters=256 size=3 stride=2 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish
[route] layers = -2
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=mish
[route] layers = -1,-28
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish
Downsample
[convolutional] batch_normalize=1 filters=512 size=3 stride=2 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish
[route] layers = -2
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=mish
[route] layers = -1,-28
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish
Downsample
[convolutional] batch_normalize=1 filters=1024 size=3 stride=2 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish
[route] layers = -2
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish
[convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=mish
[shortcut] from=-3 activation=linear
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=mish
[route] layers = -1,-16
[convolutional] batch_normalize=1 filters=1024 size=1 stride=1 pad=1 activation=mish
##########################
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky
SPP
[maxpool] stride=1 size=5
[route] layers=-2
[maxpool] stride=1 size=9
[route] layers=-4
[maxpool] stride=1 size=13
[route] layers=-1,-3,-5,-6
End SPP
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky
[upsample] stride=2
[route] layers = 85
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky
[route] layers = -1, -3
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=512 activation=leaky
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=512 activation=leaky
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky
[upsample] stride=2
[route] layers = 54
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky
[route] layers = -1, -3
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=256 activation=leaky
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=256 activation=leaky
[convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky
##########################
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=256 activation=leaky
[convolutional] size=1 stride=1 pad=1 filters=18 activation=linear
[yolo] mask = 0,1,2 anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 classes=1 num=9 jitter=.3 ignore_thresh = .7 truth_thresh = 1 scale_x_y = 1.2 iou_thresh=0.213 cls_normalizer=1.0 iou_normalizer=0.07 iou_loss=ciou nms_kind=greedynms beta_nms=0.6
[route] layers = -4
[convolutional] batch_normalize=1 size=3 stride=2 pad=1 filters=256 activation=leaky
[route] layers = -1, -16
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=512 activation=leaky
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=512 activation=leaky
[convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=512 activation=leaky
[convolutional] size=1 stride=1 pad=1 filters=18 activation=linear
[yolo] mask = 3,4,5 anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 classes=1 num=9 jitter=.3 ignore_thresh = .7 truth_thresh = 1 scale_x_y = 1.1 iou_thresh=0.213 cls_normalizer=1.0 iou_normalizer=0.07 iou_loss=ciou nms_kind=greedynms beta_nms=0.6
[route] layers = -4
[convolutional] batch_normalize=1 size=3 stride=2 pad=1 filters=512 activation=leaky
[route] layers = -1, -37
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky
[convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky
[convolutional] size=1 stride=1 pad=1 filters=18 activation=linear
[yolo] mask = 6,7,8 anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 classes=1 num=9 jitter=.3 ignore_thresh = .7 truth_thresh = 1 random=1 scale_x_y = 1.05 iou_thresh=0.213 cls_normalizer=1.0 iou_normalizer=0.07 iou_loss=ciou nms_kind=greedynms beta_nms=0.6