JC6123/aloha
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

first commit

Browse Source
This commit is contained in:
Tony Zhao
2023-02-23 16:56:49 -08:00
commit c09015ddef
46 changed files with 5149 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
detr/util/__init__.py Normal file
View File

@@ -0,0 +1 @@
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved

88
detr/util/box_ops.py Normal file
View File

@@ -0,0 +1,88 @@
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
"""
Utilities for bounding box manipulation and GIoU.
"""
import torch
from torchvision.ops.boxes import box_area
def box_cxcywh_to_xyxy(x):
x_c, y_c, w, h = x.unbind(-1)
b = [(x_c - 0.5 * w), (y_c - 0.5 * h),
(x_c + 0.5 * w), (y_c + 0.5 * h)]
return torch.stack(b, dim=-1)
def box_xyxy_to_cxcywh(x):
x0, y0, x1, y1 = x.unbind(-1)
b = [(x0 + x1) / 2, (y0 + y1) / 2,
(x1 - x0), (y1 - y0)]
return torch.stack(b, dim=-1)
# modified from torchvision to also return the union
def box_iou(boxes1, boxes2):
area1 = box_area(boxes1)
area2 = box_area(boxes2)
lt = torch.max(boxes1[:, None, :2], boxes2[:, :2]) # [N,M,2]
rb = torch.min(boxes1[:, None, 2:], boxes2[:, 2:]) # [N,M,2]
wh = (rb - lt).clamp(min=0) # [N,M,2]
inter = wh[:, :, 0] * wh[:, :, 1] # [N,M]
union = area1[:, None] + area2 - inter
iou = inter / union
return iou, union
def generalized_box_iou(boxes1, boxes2):
"""
Generalized IoU from https://giou.stanford.edu/
The boxes should be in [x0, y0, x1, y1] format
Returns a [N, M] pairwise matrix, where N = len(boxes1)
and M = len(boxes2)
"""
# degenerate boxes gives inf / nan results
# so do an early check
assert (boxes1[:, 2:] >= boxes1[:, :2]).all()
assert (boxes2[:, 2:] >= boxes2[:, :2]).all()
iou, union = box_iou(boxes1, boxes2)
lt = torch.min(boxes1[:, None, :2], boxes2[:, :2])
rb = torch.max(boxes1[:, None, 2:], boxes2[:, 2:])
wh = (rb - lt).clamp(min=0) # [N,M,2]
area = wh[:, :, 0] * wh[:, :, 1]
return iou - (area - union) / area
def masks_to_boxes(masks):
"""Compute the bounding boxes around the provided masks
The masks should be in format [N, H, W] where N is the number of masks, (H, W) are the spatial dimensions.
Returns a [N, 4] tensors, with the boxes in xyxy format
"""
if masks.numel() == 0:
return torch.zeros((0, 4), device=masks.device)
h, w = masks.shape[-2:]
y = torch.arange(0, h, dtype=torch.float)
x = torch.arange(0, w, dtype=torch.float)
y, x = torch.meshgrid(y, x)
x_mask = (masks * x.unsqueeze(0))
x_max = x_mask.flatten(1).max(-1)[0]
x_min = x_mask.masked_fill(~(masks.bool()), 1e8).flatten(1).min(-1)[0]
y_mask = (masks * y.unsqueeze(0))
y_max = y_mask.flatten(1).max(-1)[0]
y_min = y_mask.masked_fill(~(masks.bool()), 1e8).flatten(1).min(-1)[0]
return torch.stack([x_min, y_min, x_max, y_max], 1)

468
detr/util/misc.py Normal file
View File

@@ -0,0 +1,468 @@
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
"""
Misc functions, including distributed helpers.
Mostly copy-paste from torchvision references.
"""
import os
import subprocess
import time
from collections import defaultdict, deque
import datetime
import pickle
from packaging import version
from typing import Optional, List
import torch
import torch.distributed as dist
from torch import Tensor
# needed due to empty tensor bug in pytorch and torchvision 0.5
import torchvision
if version.parse(torchvision.__version__) < version.parse('0.7'):
from torchvision.ops import _new_empty_tensor
from torchvision.ops.misc import _output_size
class SmoothedValue(object):
"""Track a series of values and provide access to smoothed values over a
window or the global series average.
"""
def __init__(self, window_size=20, fmt=None):
if fmt is None:
fmt = "{median:.4f} ({global_avg:.4f})"
self.deque = deque(maxlen=window_size)
self.total = 0.0
self.count = 0
self.fmt = fmt
def update(self, value, n=1):
self.deque.append(value)
self.count += n
self.total += value * n
def synchronize_between_processes(self):
"""
Warning: does not synchronize the deque!
"""
if not is_dist_avail_and_initialized():
return
t = torch.tensor([self.count, self.total], dtype=torch.float64, device='cuda')
dist.barrier()
dist.all_reduce(t)
t = t.tolist()
self.count = int(t[0])
self.total = t[1]
@property
def median(self):
d = torch.tensor(list(self.deque))
return d.median().item()
@property
def avg(self):
d = torch.tensor(list(self.deque), dtype=torch.float32)
return d.mean().item()
@property
def global_avg(self):
return self.total / self.count
@property
def max(self):
return max(self.deque)
@property
def value(self):
return self.deque[-1]
def __str__(self):
return self.fmt.format(
median=self.median,
avg=self.avg,
global_avg=self.global_avg,
max=self.max,
value=self.value)
def all_gather(data):
"""
Run all_gather on arbitrary picklable data (not necessarily tensors)
Args:
data: any picklable object
Returns:
list[data]: list of data gathered from each rank
"""
world_size = get_world_size()
if world_size == 1:
return [data]
# serialized to a Tensor
buffer = pickle.dumps(data)
storage = torch.ByteStorage.from_buffer(buffer)
tensor = torch.ByteTensor(storage).to("cuda")
# obtain Tensor size of each rank
local_size = torch.tensor([tensor.numel()], device="cuda")
size_list = [torch.tensor([0], device="cuda") for _ in range(world_size)]
dist.all_gather(size_list, local_size)
size_list = [int(size.item()) for size in size_list]
max_size = max(size_list)
# receiving Tensor from all ranks
# we pad the tensor because torch all_gather does not support
# gathering tensors of different shapes
tensor_list = []
for _ in size_list:
tensor_list.append(torch.empty((max_size,), dtype=torch.uint8, device="cuda"))
if local_size != max_size:
padding = torch.empty(size=(max_size - local_size,), dtype=torch.uint8, device="cuda")
tensor = torch.cat((tensor, padding), dim=0)
dist.all_gather(tensor_list, tensor)
data_list = []
for size, tensor in zip(size_list, tensor_list):
buffer = tensor.cpu().numpy().tobytes()[:size]
data_list.append(pickle.loads(buffer))
return data_list
def reduce_dict(input_dict, average=True):
"""
Args:
input_dict (dict): all the values will be reduced
average (bool): whether to do average or sum
Reduce the values in the dictionary from all processes so that all processes
have the averaged results. Returns a dict with the same fields as
input_dict, after reduction.
"""
world_size = get_world_size()
if world_size < 2:
return input_dict
with torch.no_grad():
names = []
values = []
# sort the keys so that they are consistent across processes
for k in sorted(input_dict.keys()):
names.append(k)
values.append(input_dict[k])
values = torch.stack(values, dim=0)
dist.all_reduce(values)
if average:
values /= world_size
reduced_dict = {k: v for k, v in zip(names, values)}
return reduced_dict
class MetricLogger(object):
def __init__(self, delimiter="\t"):
self.meters = defaultdict(SmoothedValue)
self.delimiter = delimiter
def update(self, **kwargs):
for k, v in kwargs.items():
if isinstance(v, torch.Tensor):
v = v.item()
assert isinstance(v, (float, int))
self.meters[k].update(v)
def __getattr__(self, attr):
if attr in self.meters:
return self.meters[attr]
if attr in self.__dict__:
return self.__dict__[attr]
raise AttributeError("'{}' object has no attribute '{}'".format(
type(self).__name__, attr))
def __str__(self):
loss_str = []
for name, meter in self.meters.items():
loss_str.append(
"{}: {}".format(name, str(meter))
)
return self.delimiter.join(loss_str)
def synchronize_between_processes(self):
for meter in self.meters.values():
meter.synchronize_between_processes()
def add_meter(self, name, meter):
self.meters[name] = meter
def log_every(self, iterable, print_freq, header=None):
i = 0
if not header:
header = ''
start_time = time.time()
end = time.time()
iter_time = SmoothedValue(fmt='{avg:.4f}')
data_time = SmoothedValue(fmt='{avg:.4f}')
space_fmt = ':' + str(len(str(len(iterable)))) + 'd'
if torch.cuda.is_available():
log_msg = self.delimiter.join([
header,
'[{0' + space_fmt + '}/{1}]',
'eta: {eta}',
'{meters}',
'time: {time}',
'data: {data}',
'max mem: {memory:.0f}'
])
else:
log_msg = self.delimiter.join([
header,
'[{0' + space_fmt + '}/{1}]',
'eta: {eta}',
'{meters}',
'time: {time}',
'data: {data}'
])
MB = 1024.0 * 1024.0
for obj in iterable:
data_time.update(time.time() - end)
yield obj
iter_time.update(time.time() - end)
if i % print_freq == 0 or i == len(iterable) - 1:
eta_seconds = iter_time.global_avg * (len(iterable) - i)
eta_string = str(datetime.timedelta(seconds=int(eta_seconds)))
if torch.cuda.is_available():
print(log_msg.format(
i, len(iterable), eta=eta_string,
meters=str(self),
time=str(iter_time), data=str(data_time),
memory=torch.cuda.max_memory_allocated() / MB))
else:
print(log_msg.format(
i, len(iterable), eta=eta_string,
meters=str(self),
time=str(iter_time), data=str(data_time)))
i += 1
end = time.time()
total_time = time.time() - start_time
total_time_str = str(datetime.timedelta(seconds=int(total_time)))
print('{} Total time: {} ({:.4f} s / it)'.format(
header, total_time_str, total_time / len(iterable)))
def get_sha():
cwd = os.path.dirname(os.path.abspath(__file__))
def _run(command):
return subprocess.check_output(command, cwd=cwd).decode('ascii').strip()
sha = 'N/A'
diff = "clean"
branch = 'N/A'
try:
sha = _run(['git', 'rev-parse', 'HEAD'])
subprocess.check_output(['git', 'diff'], cwd=cwd)
diff = _run(['git', 'diff-index', 'HEAD'])
diff = "has uncommited changes" if diff else "clean"
branch = _run(['git', 'rev-parse', '--abbrev-ref', 'HEAD'])
except Exception:
pass
message = f"sha: {sha}, status: {diff}, branch: {branch}"
return message
def collate_fn(batch):
batch = list(zip(*batch))
batch[0] = nested_tensor_from_tensor_list(batch[0])
return tuple(batch)
def _max_by_axis(the_list):
# type: (List[List[int]]) -> List[int]
maxes = the_list[0]
for sublist in the_list[1:]:
for index, item in enumerate(sublist):
maxes[index] = max(maxes[index], item)
return maxes
class NestedTensor(object):
def __init__(self, tensors, mask: Optional[Tensor]):
self.tensors = tensors
self.mask = mask
def to(self, device):
# type: (Device) -> NestedTensor # noqa
cast_tensor = self.tensors.to(device)
mask = self.mask
if mask is not None:
assert mask is not None
cast_mask = mask.to(device)
else:
cast_mask = None
return NestedTensor(cast_tensor, cast_mask)
def decompose(self):
return self.tensors, self.mask
def __repr__(self):
return str(self.tensors)
def nested_tensor_from_tensor_list(tensor_list: List[Tensor]):
# TODO make this more general
if tensor_list[0].ndim == 3:
if torchvision._is_tracing():
# nested_tensor_from_tensor_list() does not export well to ONNX
# call _onnx_nested_tensor_from_tensor_list() instead
return _onnx_nested_tensor_from_tensor_list(tensor_list)
# TODO make it support different-sized images
max_size = _max_by_axis([list(img.shape) for img in tensor_list])
# min_size = tuple(min(s) for s in zip(*[img.shape for img in tensor_list]))
batch_shape = [len(tensor_list)] + max_size
b, c, h, w = batch_shape
dtype = tensor_list[0].dtype
device = tensor_list[0].device
tensor = torch.zeros(batch_shape, dtype=dtype, device=device)
mask = torch.ones((b, h, w), dtype=torch.bool, device=device)
for img, pad_img, m in zip(tensor_list, tensor, mask):
pad_img[: img.shape[0], : img.shape[1], : img.shape[2]].copy_(img)
m[: img.shape[1], :img.shape[2]] = False
else:
raise ValueError('not supported')
return NestedTensor(tensor, mask)
# _onnx_nested_tensor_from_tensor_list() is an implementation of
# nested_tensor_from_tensor_list() that is supported by ONNX tracing.
@torch.jit.unused
def _onnx_nested_tensor_from_tensor_list(tensor_list: List[Tensor]) -> NestedTensor:
max_size = []
for i in range(tensor_list[0].dim()):
max_size_i = torch.max(torch.stack([img.shape[i] for img in tensor_list]).to(torch.float32)).to(torch.int64)
max_size.append(max_size_i)
max_size = tuple(max_size)
# work around for
# pad_img[: img.shape[0], : img.shape[1], : img.shape[2]].copy_(img)
# m[: img.shape[1], :img.shape[2]] = False
# which is not yet supported in onnx
padded_imgs = []
padded_masks = []
for img in tensor_list:
padding = [(s1 - s2) for s1, s2 in zip(max_size, tuple(img.shape))]
padded_img = torch.nn.functional.pad(img, (0, padding[2], 0, padding[1], 0, padding[0]))
padded_imgs.append(padded_img)
m = torch.zeros_like(img[0], dtype=torch.int, device=img.device)
padded_mask = torch.nn.functional.pad(m, (0, padding[2], 0, padding[1]), "constant", 1)
padded_masks.append(padded_mask.to(torch.bool))
tensor = torch.stack(padded_imgs)
mask = torch.stack(padded_masks)
return NestedTensor(tensor, mask=mask)
def setup_for_distributed(is_master):
"""
This function disables printing when not in master process
"""
import builtins as __builtin__
builtin_print = __builtin__.print
def print(*args, **kwargs):
force = kwargs.pop('force', False)
if is_master or force:
builtin_print(*args, **kwargs)
__builtin__.print = print
def is_dist_avail_and_initialized():
if not dist.is_available():
return False
if not dist.is_initialized():
return False
return True
def get_world_size():
if not is_dist_avail_and_initialized():
return 1
return dist.get_world_size()
def get_rank():
if not is_dist_avail_and_initialized():
return 0
return dist.get_rank()
def is_main_process():
return get_rank() == 0
def save_on_master(*args, **kwargs):
if is_main_process():
torch.save(*args, **kwargs)
def init_distributed_mode(args):
if 'RANK' in os.environ and 'WORLD_SIZE' in os.environ:
args.rank = int(os.environ["RANK"])
args.world_size = int(os.environ['WORLD_SIZE'])
args.gpu = int(os.environ['LOCAL_RANK'])
elif 'SLURM_PROCID' in os.environ:
args.rank = int(os.environ['SLURM_PROCID'])
args.gpu = args.rank % torch.cuda.device_count()
else:
print('Not using distributed mode')
args.distributed = False
return
args.distributed = True
torch.cuda.set_device(args.gpu)
args.dist_backend = 'nccl'
print('| distributed init (rank {}): {}'.format(
args.rank, args.dist_url), flush=True)
torch.distributed.init_process_group(backend=args.dist_backend, init_method=args.dist_url,
world_size=args.world_size, rank=args.rank)
torch.distributed.barrier()
setup_for_distributed(args.rank == 0)
@torch.no_grad()
def accuracy(output, target, topk=(1,)):
"""Computes the precision@k for the specified values of k"""
if target.numel() == 0:
return [torch.zeros([], device=output.device)]
maxk = max(topk)
batch_size = target.size(0)
_, pred = output.topk(maxk, 1, True, True)
pred = pred.t()
correct = pred.eq(target.view(1, -1).expand_as(pred))
res = []
for k in topk:
correct_k = correct[:k].view(-1).float().sum(0)
res.append(correct_k.mul_(100.0 / batch_size))
return res
def interpolate(input, size=None, scale_factor=None, mode="nearest", align_corners=None):
# type: (Tensor, Optional[List[int]], Optional[float], str, Optional[bool]) -> Tensor
"""
Equivalent to nn.functional.interpolate, but with support for empty batch sizes.
This will eventually be supported natively by PyTorch, and this
class can go away.
"""
if version.parse(torchvision.__version__) < version.parse('0.7'):
if input.numel() > 0:
return torch.nn.functional.interpolate(
input, size, scale_factor, mode, align_corners
)
output_shape = _output_size(2, input, size, scale_factor)
output_shape = list(input.shape[:-2]) + list(output_shape)
return _new_empty_tensor(input, output_shape)
else:
return torchvision.ops.misc.interpolate(input, size, scale_factor, mode, align_corners)

107
detr/util/plot_utils.py Normal file
View File

@@ -0,0 +1,107 @@
"""
Plotting utilities to visualize training logs.
"""
import torch
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from pathlib import Path, PurePath
def plot_logs(logs, fields=('class_error', 'loss_bbox_unscaled', 'mAP'), ewm_col=0, log_name='log.txt'):
'''
Function to plot specific fields from training log(s). Plots both training and test results.
:: Inputs - logs = list containing Path objects, each pointing to individual dir with a log file
- fields = which results to plot from each log file - plots both training and test for each field.
- ewm_col = optional, which column to use as the exponential weighted smoothing of the plots
- log_name = optional, name of log file if different than default 'log.txt'.
:: Outputs - matplotlib plots of results in fields, color coded for each log file.
- solid lines are training results, dashed lines are test results.
'''
func_name = "plot_utils.py::plot_logs"
# verify logs is a list of Paths (list[Paths]) or single Pathlib object Path,
# convert single Path to list to avoid 'not iterable' error
if not isinstance(logs, list):
if isinstance(logs, PurePath):
logs = [logs]
print(f"{func_name} info: logs param expects a list argument, converted to list[Path].")
else:
raise ValueError(f"{func_name} - invalid argument for logs parameter.\n \
Expect list[Path] or single Path obj, received {type(logs)}")
# Quality checks - verify valid dir(s), that every item in list is Path object, and that log_name exists in each dir
for i, dir in enumerate(logs):
if not isinstance(dir, PurePath):
raise ValueError(f"{func_name} - non-Path object in logs argument of {type(dir)}: \n{dir}")
if not dir.exists():
raise ValueError(f"{func_name} - invalid directory in logs argument:\n{dir}")
# verify log_name exists
fn = Path(dir / log_name)
if not fn.exists():
print(f"-> missing {log_name}. Have you gotten to Epoch 1 in training?")
print(f"--> full path of missing log file: {fn}")
return
# load log file(s) and plot
dfs = [pd.read_json(Path(p) / log_name, lines=True) for p in logs]
fig, axs = plt.subplots(ncols=len(fields), figsize=(16, 5))
for df, color in zip(dfs, sns.color_palette(n_colors=len(logs))):
for j, field in enumerate(fields):
if field == 'mAP':
coco_eval = pd.DataFrame(
np.stack(df.test_coco_eval_bbox.dropna().values)[:, 1]
).ewm(com=ewm_col).mean()
axs[j].plot(coco_eval, c=color)
else:
df.interpolate().ewm(com=ewm_col).mean().plot(
y=[f'train_{field}', f'test_{field}'],
ax=axs[j],
color=[color] * 2,
style=['-', '--']
)
for ax, field in zip(axs, fields):
ax.legend([Path(p).name for p in logs])
ax.set_title(field)
def plot_precision_recall(files, naming_scheme='iter'):
if naming_scheme == 'exp_id':
# name becomes exp_id
names = [f.parts[-3] for f in files]
elif naming_scheme == 'iter':
names = [f.stem for f in files]
else:
raise ValueError(f'not supported {naming_scheme}')
fig, axs = plt.subplots(ncols=2, figsize=(16, 5))
for f, color, name in zip(files, sns.color_palette("Blues", n_colors=len(files)), names):
data = torch.load(f)
# precision is n_iou, n_points, n_cat, n_area, max_det
precision = data['precision']
recall = data['params'].recThrs
scores = data['scores']
# take precision for all classes, all areas and 100 detections
precision = precision[0, :, :, 0, -1].mean(1)
scores = scores[0, :, :, 0, -1].mean(1)
prec = precision.mean()
rec = data['recall'][0, :, 0, -1].mean()
print(f'{naming_scheme} {name}: mAP@50={prec * 100: 05.1f}, ' +
f'score={scores.mean():0.3f}, ' +
f'f1={2 * prec * rec / (prec + rec + 1e-8):0.3f}'
)
axs[0].plot(recall, precision, c=color)
axs[1].plot(recall, scores, c=color)
axs[0].set_title('Precision / Recall')
axs[0].legend(names)
axs[1].set_title('Scores / Recall')
axs[1].legend(names)
return fig, axs