Spaces:
Runtime error
Runtime error
File size: 5,008 Bytes
3672502 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 |
from enum import Enum
from PIL import Image
import numpy as np
import torch
import torch.distributed as dist
IGNORE_INDEX = -100
IMAGE_TOKEN_INDEX = -200
DEFAULT_IMAGE_TOKEN = "<image>"
DEFAULT_IMAGE_PATCH_TOKEN = "<im_patch>"
DEFAULT_IM_START_TOKEN = "<im_start>"
DEFAULT_IM_END_TOKEN = "<im_end>"
SHORT_QUESTION_LIST = [DEFAULT_IMAGE_TOKEN + "\n" + "Please locate the {class_name} in this image."]
ANSWER_LIST = [
"Sure, [LOC].",
]
class Summary(Enum):
NONE = 0
AVERAGE = 1
SUM = 2
COUNT = 3
def expand2square(pil_img, background_color):
width, height = pil_img.size
if width == height:
return pil_img
elif width > height:
result = Image.new(pil_img.mode, (width, width), background_color)
result.paste(pil_img, (0, 0))
return result
else:
result = Image.new(pil_img.mode, (height, height), background_color)
result.paste(pil_img, (0, 0))
return result
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)
class AverageMeter(object):
"""Computes and stores the average and current value"""
def __init__(self, name, fmt=":f", summary_type=Summary.AVERAGE):
self.name = name
self.fmt = fmt
self.summary_type = summary_type
self.reset()
def reset(self):
self.val = 0
self.avg = 0
self.sum = 0
self.count = 0
def update(self, val, n=1):
self.val = val
self.sum += val * n
self.count += n
self.avg = self.sum / self.count
def all_reduce(self):
device = "cuda" if torch.cuda.is_available() else "cpu"
if isinstance(self.sum, np.ndarray):
total = torch.tensor(
self.sum.tolist()
+ [
self.count,
],
dtype=torch.float32,
device=device,
)
else:
total = torch.tensor(
[self.sum, self.count], dtype=torch.float32, device=device
)
dist.all_reduce(total, dist.ReduceOp.SUM, async_op=False)
if total.shape[0] > 2:
self.sum, self.count = total[:-1].cpu().numpy(), total[-1].cpu().item()
else:
self.sum, self.count = total.tolist()
self.avg = self.sum / (self.count + 1e-5)
def __str__(self):
fmtstr = "{name} {val" + self.fmt + "} ({avg" + self.fmt + "})"
return fmtstr.format(**self.__dict__)
def summary(self):
fmtstr = ""
if self.summary_type is Summary.NONE:
fmtstr = ""
elif self.summary_type is Summary.AVERAGE:
fmtstr = "{name} {avg:.3f}"
elif self.summary_type is Summary.SUM:
fmtstr = "{name} {sum:.3f}"
elif self.summary_type is Summary.COUNT:
fmtstr = "{name} {count:.3f}"
else:
raise ValueError("invalid summary type %r" % self.summary_type)
return fmtstr.format(**self.__dict__)
def intersectionAndUnionGPU(output, target, K, ignore_index=255):
# 'K' classes, output and target sizes are N or N * L or N * H * W, each value in range 0 to K - 1.
assert output.dim() in [1, 2, 3]
assert output.shape == target.shape
output = output.view(-1)
target = target.view(-1)
output[target == ignore_index] = ignore_index
intersection = output[output == target]
area_intersection = torch.histc(intersection, bins=K, min=0, max=K - 1)
area_output = torch.histc(output, bins=K, min=0, max=K - 1)
area_target = torch.histc(target, bins=K, min=0, max=K - 1)
area_union = area_output + area_target - area_intersection
return area_intersection, area_union, area_target
class ProgressMeter(object):
def __init__(self, num_batches, meters, prefix=""):
self.batch_fmtstr = self._get_batch_fmtstr(num_batches)
self.meters = meters
self.prefix = prefix
def display(self, batch):
entries = [self.prefix + self.batch_fmtstr.format(batch)]
entries += [str(meter) for meter in self.meters]
print("\t".join(entries))
def display_summary(self):
entries = [" *"]
entries += [meter.summary() for meter in self.meters]
print(" ".join(entries))
def _get_batch_fmtstr(self, num_batches):
num_digits = len(str(num_batches // 1))
fmt = "{:" + str(num_digits) + "d}"
return "[" + fmt + "/" + fmt.format(num_batches) + "]"
def dict_to_cuda(input_dict):
for k, v in input_dict.items():
if isinstance(input_dict[k], torch.Tensor):
input_dict[k] = v.cuda(non_blocking=True)
elif (
isinstance(input_dict[k], list)
and len(input_dict[k]) > 0
and isinstance(input_dict[k][0], torch.Tensor)
):
input_dict[k] = [ele.cuda(non_blocking=True) for ele in v]
return input_dict
|