xdobro23
/
YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

`default.yaml` type comments (#3237)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
single_channel
Glenn Jocher 1 year ago committed by GitHub
parent 21df296425
commit e78fb683f4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 118 additions and 123 deletions
Show Stats Download Patch File Download Diff File

2
ultralytics/models/v6/yolov6.yaml
Unescape View File

@ -2,8 +2,8 @@
# YOLOv6 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/models/yolov6 # YOLOv6 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/models/yolov6
# Parameters # Parameters
act: nn.ReLU()
nc: 80 # number of classes nc: 80 # number of classes
activation: nn.ReLU() # (optional) model default activation function
scales: # model compound scaling constants, i.e. 'model=yolov6n.yaml' will call yolov8.yaml with scale 'n' scales: # model compound scaling constants, i.e. 'model=yolov6n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels] # [depth, width, max_channels]
n: [0.33, 0.25, 1024] n: [0.33, 0.25, 1024]

6
ultralytics/nn/tasks.py
Unescape View File

@ -422,9 +422,7 @@ class RTDETRDetectionModel(DetectionModel):
# NOTE: preprocess gt_bbox and gt_labels to list. # NOTE: preprocess gt_bbox and gt_labels to list.
bs = len(img) bs = len(img)
batch_idx = batch['batch_idx'] batch_idx = batch['batch_idx']
gt_groups = [] gt_groups = [(batch_idx == i).sum().item() for i in range(bs)]
for i in range(bs):
gt_groups.append((batch_idx == i).sum().item())
targets = { targets = {
'cls': batch['cls'].to(img.device, dtype=torch.long).view(-1), 'cls': batch['cls'].to(img.device, dtype=torch.long).view(-1),
'bboxes': batch['bboxes'].to(device=img.device), 'bboxes': batch['bboxes'].to(device=img.device),
@ -606,7 +604,7 @@ def parse_model(d, ch, verbose=True): # model_dict, input_channels(3)
# Args # Args
max_channels = float('inf') max_channels = float('inf')
nc, act, scales = (d.get(x) for x in ('nc', 'act', 'scales')) nc, act, scales = (d.get(x) for x in ('nc', 'activation', 'scales'))
depth, width, kpt_shape = (d.get(x, 1.0) for x in ('depth_multiple', 'width_multiple', 'kpt_shape')) depth, width, kpt_shape = (d.get(x, 1.0) for x in ('depth_multiple', 'width_multiple', 'kpt_shape'))
if scales: if scales:
scale = d.get('scale') scale = d.get('scale')

40
ultralytics/vit/sam/modules/decoders.py
Unescape View File

@ -22,20 +22,15 @@ class MaskDecoder(nn.Module):
iou_head_hidden_dim: int = 256, iou_head_hidden_dim: int = 256,
) -> None: ) -> None:
""" """
Predicts masks given an image and prompt embeddings, using a Predicts masks given an image and prompt embeddings, using a transformer architecture.
transformer architecture.
Arguments: Arguments:
transformer_dim (int): the channel dimension of the transformer transformer_dim (int): the channel dimension of the transformer module
transformer (nn.Module): the transformer used to predict masks transformer (nn.Module): the transformer used to predict masks
num_multimask_outputs (int): the number of masks to predict num_multimask_outputs (int): the number of masks to predict when disambiguating masks
when disambiguating masks activation (nn.Module): the type of activation to use when upscaling masks
activation (nn.Module): the type of activation to use when iou_head_depth (int): the depth of the MLP used to predict mask quality
upscaling masks iou_head_hidden_dim (int): the hidden dimension of the MLP used to predict mask quality
iou_head_depth (int): the depth of the MLP used to predict
mask quality
iou_head_hidden_dim (int): the hidden dimension of the MLP
used to predict mask quality
""" """
super().__init__() super().__init__()
self.transformer_dim = transformer_dim self.transformer_dim = transformer_dim
@ -71,16 +66,15 @@ class MaskDecoder(nn.Module):
Predict masks given image and prompt embeddings. Predict masks given image and prompt embeddings.
Arguments: Arguments:
image_embeddings (torch.Tensor): the embeddings from the image encoder image_embeddings (torch.Tensor): the embeddings from the image encoder
image_pe (torch.Tensor): positional encoding with the shape of image_embeddings image_pe (torch.Tensor): positional encoding with the shape of image_embeddings
sparse_prompt_embeddings (torch.Tensor): the embeddings of the points and boxes sparse_prompt_embeddings (torch.Tensor): the embeddings of the points and boxes
dense_prompt_embeddings (torch.Tensor): the embeddings of the mask inputs dense_prompt_embeddings (torch.Tensor): the embeddings of the mask inputs
multimask_output (bool): Whether to return multiple masks or a single multimask_output (bool): Whether to return multiple masks or a single mask.
mask.
Returns: Returns:
torch.Tensor: batched predicted masks torch.Tensor: batched predicted masks
torch.Tensor: batched predictions of mask quality torch.Tensor: batched predictions of mask quality
""" """
masks, iou_pred = self.predict_masks( masks, iou_pred = self.predict_masks(
image_embeddings=image_embeddings, image_embeddings=image_embeddings,
@ -136,9 +130,11 @@ class MaskDecoder(nn.Module):
return masks, iou_pred return masks, iou_pred
# Lightly adapted from
# https://github.com/facebookresearch/MaskFormer/blob/main/mask_former/modeling/transformer/transformer_predictor.py # noqa
class MLP(nn.Module): class MLP(nn.Module):
"""
Lightly adapted from
https://github.com/facebookresearch/MaskFormer/blob/main/mask_former/modeling/transformer/transformer_predictor.py
"""
def __init__( def __init__(
self, self,

3
ultralytics/vit/utils/ops.py
Unescape View File

@ -249,7 +249,7 @@ def get_cdn_group(batch,
attn_mask[max_nums * 2 * i:max_nums * 2 * (i + 1), max_nums * 2 * (i + 1):num_dn] = True attn_mask[max_nums * 2 * i:max_nums * 2 * (i + 1), max_nums * 2 * (i + 1):num_dn] = True
attn_mask[max_nums * 2 * i:max_nums * 2 * (i + 1), :max_nums * 2 * i] = True attn_mask[max_nums * 2 * i:max_nums * 2 * (i + 1), :max_nums * 2 * i] = True
dn_meta = { dn_meta = {
'dn_pos_idx': [p.reshape(-1) for p in pos_idx.cpu().split([n for n in gt_groups], dim=1)], 'dn_pos_idx': [p.reshape(-1) for p in pos_idx.cpu().split(list(gt_groups), dim=1)],
'dn_num_group': num_group, 'dn_num_group': num_group,
'dn_num_split': [num_dn, num_queries]} 'dn_num_split': [num_dn, num_queries]}
@ -258,5 +258,6 @@ def get_cdn_group(batch,
def inverse_sigmoid(x, eps=1e-6): def inverse_sigmoid(x, eps=1e-6):
"""Inverse sigmoid function."""
x = x.clip(min=0., max=1.) x = x.clip(min=0., max=1.)
return torch.log(x / (1 - x + eps) + eps) return torch.log(x / (1 - x + eps) + eps)

190
ultralytics/yolo/cfg/default.yaml
Unescape View File

@ -1,117 +1,117 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license # Ultralytics YOLO 🚀, AGPL-3.0 license
# Default training settings and hyperparameters for medium-augmentation COCO training # Default training settings and hyperparameters for medium-augmentation COCO training
task: detect # YOLO task, i.e. detect, segment, classify, pose task: detect # (str) YOLO task, i.e. detect, segment, classify, pose
mode: train # YOLO mode, i.e. train, val, predict, export, track, benchmark mode: train # (str) YOLO mode, i.e. train, val, predict, export, track, benchmark
# Train settings ------------------------------------------------------------------------------------------------------- # Train settings -------------------------------------------------------------------------------------------------------
model: # path to model file, i.e. yolov8n.pt, yolov8n.yaml model: # (str, optional) path to model file, i.e. yolov8n.pt, yolov8n.yaml
data: # path to data file, i.e. coco128.yaml data: # (str, optional) path to data file, i.e. coco128.yaml
epochs: 100 # number of epochs to train for epochs: 100 # (int) number of epochs to train for
patience: 50 # epochs to wait for no observable improvement for early stopping of training patience: 50 # (int) epochs to wait for no observable improvement for early stopping of training
batch: 16 # number of images per batch (-1 for AutoBatch) batch: 16 # (int) number of images per batch (-1 for AutoBatch)
imgsz: 640 # size of input images as integer or w,h imgsz: 640 # (int) size of input images as integer or w,h
save: True # save train checkpoints and predict results save: True # (bool) save train checkpoints and predict results
save_period: -1 # Save checkpoint every x epochs (disabled if < 1) save_period: -1 # (int) Save checkpoint every x epochs (disabled if < 1)
cache: False # True/ram, disk or False. Use cache for data loading cache: False # (bool) True/ram, disk or False. Use cache for data loading
device: # device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu device: # (int | str | list, optional) device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu
workers: 8 # number of worker threads for data loading (per RANK if DDP) workers: 8 # (int) number of worker threads for data loading (per RANK if DDP)
project: # project name project: # (str, optional) project name
name: # experiment name, results saved to 'project/name' directory name: # (str, optional) experiment name, results saved to 'project/name' directory
exist_ok: False # whether to overwrite existing experiment exist_ok: False # (bool) whether to overwrite existing experiment
pretrained: False # whether to use a pretrained model pretrained: False # (bool) whether to use a pretrained model
optimizer: auto # optimizer to use, choices=[SGD, Adam, Adamax, AdamW, NAdam, RAdam, RMSProp, auto] optimizer: auto # (str) optimizer to use, choices=[SGD, Adam, Adamax, AdamW, NAdam, RAdam, RMSProp, auto]
verbose: True # whether to print verbose output verbose: True # (bool) whether to print verbose output
seed: 0 # random seed for reproducibility seed: 0 # (int) random seed for reproducibility
deterministic: True # whether to enable deterministic mode deterministic: True # (bool) whether to enable deterministic mode
single_cls: False # train multi-class data as single-class single_cls: False # (bool) train multi-class data as single-class
rect: False # rectangular training if mode='train' or rectangular validation if mode='val' rect: False # (bool) rectangular training if mode='train' or rectangular validation if mode='val'
cos_lr: False # use cosine learning rate scheduler cos_lr: False # (bool) use cosine learning rate scheduler
close_mosaic: 0 # (int) disable mosaic augmentation for final epochs close_mosaic: 0 # (int) disable mosaic augmentation for final epochs
resume: False # resume training from last checkpoint resume: False # (bool) resume training from last checkpoint
amp: True # Automatic Mixed Precision (AMP) training, choices=[True, False], True runs AMP check amp: True # (bool) Automatic Mixed Precision (AMP) training, choices=[True, False], True runs AMP check
fraction: 1.0 # dataset fraction to train on (default is 1.0, all images in train set) fraction: 1.0 # (float) dataset fraction to train on (default is 1.0, all images in train set)
profile: False # profile ONNX and TensorRT speeds during training for loggers profile: False # (bool) profile ONNX and TensorRT speeds during training for loggers
# Segmentation # Segmentation
overlap_mask: True # masks should overlap during training (segment train only) overlap_mask: True # (bool) masks should overlap during training (segment train only)
mask_ratio: 4 # mask downsample ratio (segment train only) mask_ratio: 4 # (int) mask downsample ratio (segment train only)
# Classification # Classification
dropout: 0.0 # use dropout regularization (classify train only) dropout: 0.0 # (float) use dropout regularization (classify train only)
# Val/Test settings ---------------------------------------------------------------------------------------------------- # Val/Test settings ----------------------------------------------------------------------------------------------------
val: True # validate/test during training val: True # (bool) validate/test during training
split: val # dataset split to use for validation, i.e. 'val', 'test' or 'train' split: val # (str) dataset split to use for validation, i.e. 'val', 'test' or 'train'
save_json: False # save results to JSON file save_json: False # (bool) save results to JSON file
save_hybrid: False # save hybrid version of labels (labels + additional predictions) save_hybrid: False # (bool) save hybrid version of labels (labels + additional predictions)
conf: # object confidence threshold for detection (default 0.25 predict, 0.001 val) conf: # (float, optional) object confidence threshold for detection (default 0.25 predict, 0.001 val)
iou: 0.7 # intersection over union (IoU) threshold for NMS iou: 0.7 # (float) intersection over union (IoU) threshold for NMS
max_det: 300 # maximum number of detections per image max_det: 300 # (int) maximum number of detections per image
half: False # use half precision (FP16) half: False # (bool) use half precision (FP16)
dnn: False # use OpenCV DNN for ONNX inference dnn: False # (bool) use OpenCV DNN for ONNX inference
plots: True # save plots during train/val plots: True # (bool) save plots during train/val
# Prediction settings -------------------------------------------------------------------------------------------------- # Prediction settings --------------------------------------------------------------------------------------------------
source: # source directory for images or videos source: # (str, optional) source directory for images or videos
show: False # show results if possible show: False # (bool) show results if possible
save_txt: False # save results as .txt file save_txt: False # (bool) save results as .txt file
save_conf: False # save results with confidence scores save_conf: False # (bool) save results with confidence scores
save_crop: False # save cropped images with results save_crop: False # (bool) save cropped images with results
show_labels: True # show object labels in plots show_labels: True # (bool) show object labels in plots
show_conf: True # show object confidence scores in plots show_conf: True # (bool) show object confidence scores in plots
vid_stride: 1 # video frame-rate stride vid_stride: 1 # (int) video frame-rate stride
line_width: # line width of the bounding boxes line_width: # (int, optional) line width of the bounding boxes, auto if missing
visualize: False # visualize model features visualize: False # (bool) visualize model features
augment: False # apply image augmentation to prediction sources augment: False # (bool) apply image augmentation to prediction sources
agnostic_nms: False # class-agnostic NMS agnostic_nms: False # (bool) class-agnostic NMS
classes: # filter results by class, i.e. class=0, or class=[0,2,3] classes: # (int | list[int], optional) filter results by class, i.e. class=0, or class=[0,2,3]
retina_masks: False # use high-resolution segmentation masks retina_masks: False # (bool) use high-resolution segmentation masks
boxes: True # Show boxes in segmentation predictions boxes: True # (bool) Show boxes in segmentation predictions
# Export settings ------------------------------------------------------------------------------------------------------ # Export settings ------------------------------------------------------------------------------------------------------
format: torchscript # format to export to format: torchscript # (str) format to export to, choices at https://docs.ultralytics.com/modes/export/#export-formats
keras: False # use Keras keras: False # (bool) use Kera=s
optimize: False # TorchScript: optimize for mobile optimize: False # (bool) TorchScript: optimize for mobile
int8: False # CoreML/TF INT8 quantization int8: False # (bool) CoreML/TF INT8 quantization
dynamic: False # ONNX/TF/TensorRT: dynamic axes dynamic: False # (bool) ONNX/TF/TensorRT: dynamic axes
simplify: False # ONNX: simplify model simplify: False # (bool) ONNX: simplify model
opset: # ONNX: opset version (optional) opset: # (int, optional) ONNX: opset version
workspace: 4 # TensorRT: workspace size (GB) workspace: 4 # (int) TensorRT: workspace size (GB)
nms: False # CoreML: add NMS nms: False # (bool) CoreML: add NMS
# Hyperparameters ------------------------------------------------------------------------------------------------------ # Hyperparameters ------------------------------------------------------------------------------------------------------
lr0: 0.01 # initial learning rate (i.e. SGD=1E-2, Adam=1E-3) lr0: 0.01 # (float) initial learning rate (i.e. SGD=1E-2, Adam=1E-3)
lrf: 0.01 # final learning rate (lr0 * lrf) lrf: 0.01 # (float) final learning rate (lr0 * lrf)
momentum: 0.937 # SGD momentum/Adam beta1 momentum: 0.937 # (float) SGD momentum/Adam beta1
weight_decay: 0.0005 # optimizer weight decay 5e-4 weight_decay: 0.0005 # (float) optimizer weight decay 5e-4
warmup_epochs: 3.0 # warmup epochs (fractions ok) warmup_epochs: 3.0 # (float) warmup epochs (fractions ok)
warmup_momentum: 0.8 # warmup initial momentum warmup_momentum: 0.8 # (float) warmup initial momentum
warmup_bias_lr: 0.1 # warmup initial bias lr warmup_bias_lr: 0.1 # (float) warmup initial bias lr
box: 7.5 # box loss gain box: 7.5 # (float) box loss gain
cls: 0.5 # cls loss gain (scale with pixels) cls: 0.5 # (float) cls loss gain (scale with pixels)
dfl: 1.5 # dfl loss gain dfl: 1.5 # (float) dfl loss gain
pose: 12.0 # pose loss gain pose: 12.0 # (float) pose loss gain
kobj: 1.0 # keypoint obj loss gain kobj: 1.0 # (float) keypoint obj loss gain
label_smoothing: 0.0 # label smoothing (fraction) label_smoothing: 0.0 # (float) label smoothing (fraction)
nbs: 64 # nominal batch size nbs: 64 # (int) nominal batch size
hsv_h: 0.015 # image HSV-Hue augmentation (fraction) hsv_h: 0.015 # (float) image HSV-Hue augmentation (fraction)
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) hsv_s: 0.7 # (float) image HSV-Saturation augmentation (fraction)
hsv_v: 0.4 # image HSV-Value augmentation (fraction) hsv_v: 0.4 # (float) image HSV-Value augmentation (fraction)
degrees: 0.0 # image rotation (+/- deg) degrees: 0.0 # (float) image rotation (+/- deg)
translate: 0.1 # image translation (+/- fraction) translate: 0.1 # (float) image translation (+/- fraction)
scale: 0.5 # image scale (+/- gain) scale: 0.5 # (float) image scale (+/- gain)
shear: 0.0 # image shear (+/- deg) shear: 0.0 # (float) image shear (+/- deg)
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 perspective: 0.0 # (float) image perspective (+/- fraction), range 0-0.001
flipud: 0.0 # image flip up-down (probability) flipud: 0.0 # (float) image flip up-down (probability)
fliplr: 0.5 # image flip left-right (probability) fliplr: 0.5 # (float) image flip left-right (probability)
mosaic: 1.0 # image mosaic (probability) mosaic: 1.0 # (float) image mosaic (probability)
mixup: 0.0 # image mixup (probability) mixup: 0.0 # (float) image mixup (probability)
copy_paste: 0.0 # segment copy-paste (probability) copy_paste: 0.0 # (float) segment copy-paste (probability)
# Custom config.yaml --------------------------------------------------------------------------------------------------- # Custom config.yaml ---------------------------------------------------------------------------------------------------
cfg: # for overriding defaults.yaml cfg: # (str, optional) for overriding defaults.yaml
# Debug, do not modify ------------------------------------------------------------------------------------------------- # Debug, do not modify -------------------------------------------------------------------------------------------------
v5loader: False # use legacy YOLOv5 dataloader v5loader: False # (bool) use legacy YOLOv5 dataloader (deprecated)
# Tracker settings ------------------------------------------------------------------------------------------------------ # Tracker settings ------------------------------------------------------------------------------------------------------
tracker: botsort.yaml # tracker type, ['botsort.yaml', 'bytetrack.yaml'] tracker: botsort.yaml # (str) tracker type, choices=[botsort.yaml, bytetrack.yaml]

Write Preview
Loading…
Cancel
Save