Spaces:
Running
on
Zero
Running
on
Zero
File size: 8,588 Bytes
689a1f3 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 |
# Copyright (c) Facebook, Inc. and its affiliates.
import datetime
import logging
import time
from collections import OrderedDict, abc
from contextlib import ExitStack, contextmanager
from typing import List, Union
import torch
from torch import nn
from detectron2.utils.comm import get_world_size, is_main_process
from detectron2.utils.logger import log_every_n_seconds
class DatasetEvaluator:
"""
Base class for a dataset evaluator.
The function :func:`inference_on_dataset` runs the model over
all samples in the dataset, and have a DatasetEvaluator to process the inputs/outputs.
This class will accumulate information of the inputs/outputs (by :meth:`process`),
and produce evaluation results in the end (by :meth:`evaluate`).
"""
def reset(self):
"""
Preparation for a new round of evaluation.
Should be called before starting a round of evaluation.
"""
pass
def process(self, inputs, outputs):
"""
Process the pair of inputs and outputs.
If they contain batches, the pairs can be consumed one-by-one using `zip`:
.. code-block:: python
for input_, output in zip(inputs, outputs):
# do evaluation on single input/output pair
...
Args:
inputs (list): the inputs that's used to call the model.
outputs (list): the return value of `model(inputs)`
"""
pass
def evaluate(self):
"""
Evaluate/summarize the performance, after processing all input/output pairs.
Returns:
dict:
A new evaluator class can return a dict of arbitrary format
as long as the user can process the results.
In our train_net.py, we expect the following format:
* key: the name of the task (e.g., bbox)
* value: a dict of {metric name: score}, e.g.: {"AP50": 80}
"""
pass
class DatasetEvaluators(DatasetEvaluator):
"""
Wrapper class to combine multiple :class:`DatasetEvaluator` instances.
This class dispatches every evaluation call to
all of its :class:`DatasetEvaluator`.
"""
def __init__(self, evaluators):
"""
Args:
evaluators (list): the evaluators to combine.
"""
super().__init__()
self._evaluators = evaluators
def reset(self):
for evaluator in self._evaluators:
evaluator.reset()
def process(self, inputs, outputs):
for evaluator in self._evaluators:
evaluator.process(inputs, outputs)
def evaluate(self):
results = OrderedDict()
for evaluator in self._evaluators:
result = evaluator.evaluate()
if is_main_process() and result is not None:
for k, v in result.items():
assert (
k not in results
), "Different evaluators produce results with the same key {}".format(k)
results[k] = v
return results
def inference_on_dataset(
model,
data_loader,
evaluator: Union[DatasetEvaluator, List[DatasetEvaluator], None],
callbacks=None,
):
"""
Run model on the data_loader and evaluate the metrics with evaluator.
Also benchmark the inference speed of `model.__call__` accurately.
The model will be used in eval mode.
Args:
model (callable): a callable which takes an object from
`data_loader` and returns some outputs.
If it's an nn.Module, it will be temporarily set to `eval` mode.
If you wish to evaluate a model in `training` mode instead, you can
wrap the given model and override its behavior of `.eval()` and `.train()`.
data_loader: an iterable object with a length.
The elements it generates will be the inputs to the model.
evaluator: the evaluator(s) to run. Use `None` if you only want to benchmark,
but don't want to do any evaluation.
callbacks (dict of callables): a dictionary of callback functions which can be
called at each stage of inference.
Returns:
The return value of `evaluator.evaluate()`
"""
num_devices = get_world_size()
logger = logging.getLogger(__name__)
logger.info("Start inference on {} batches".format(len(data_loader)))
total = len(data_loader) # inference data loader must have a fixed length
if evaluator is None:
# create a no-op evaluator
evaluator = DatasetEvaluators([])
if isinstance(evaluator, abc.MutableSequence):
evaluator = DatasetEvaluators(evaluator)
evaluator.reset()
num_warmup = min(5, total - 1)
start_time = time.perf_counter()
total_data_time = 0
total_compute_time = 0
total_eval_time = 0
with ExitStack() as stack:
if isinstance(model, nn.Module):
stack.enter_context(inference_context(model))
stack.enter_context(torch.no_grad())
start_data_time = time.perf_counter()
dict.get(callbacks or {}, "on_start", lambda: None)()
for idx, inputs in enumerate(data_loader):
total_data_time += time.perf_counter() - start_data_time
if idx == num_warmup:
start_time = time.perf_counter()
total_data_time = 0
total_compute_time = 0
total_eval_time = 0
start_compute_time = time.perf_counter()
dict.get(callbacks or {}, "before_inference", lambda: None)()
outputs = model(inputs)
dict.get(callbacks or {}, "after_inference", lambda: None)()
if torch.cuda.is_available():
torch.cuda.synchronize()
total_compute_time += time.perf_counter() - start_compute_time
start_eval_time = time.perf_counter()
evaluator.process(inputs, outputs)
total_eval_time += time.perf_counter() - start_eval_time
iters_after_start = idx + 1 - num_warmup * int(idx >= num_warmup)
data_seconds_per_iter = total_data_time / iters_after_start
compute_seconds_per_iter = total_compute_time / iters_after_start
eval_seconds_per_iter = total_eval_time / iters_after_start
total_seconds_per_iter = (time.perf_counter() - start_time) / iters_after_start
if idx >= num_warmup * 2 or compute_seconds_per_iter > 5:
eta = datetime.timedelta(seconds=int(total_seconds_per_iter * (total - idx - 1)))
log_every_n_seconds(
logging.INFO,
(
f"Inference done {idx + 1}/{total}. "
f"Dataloading: {data_seconds_per_iter:.4f} s/iter. "
f"Inference: {compute_seconds_per_iter:.4f} s/iter. "
f"Eval: {eval_seconds_per_iter:.4f} s/iter. "
f"Total: {total_seconds_per_iter:.4f} s/iter. "
f"ETA={eta}"
),
n=5,
)
start_data_time = time.perf_counter()
dict.get(callbacks or {}, "on_end", lambda: None)()
# Measure the time only for this worker (before the synchronization barrier)
total_time = time.perf_counter() - start_time
total_time_str = str(datetime.timedelta(seconds=total_time))
# NOTE this format is parsed by grep
logger.info(
"Total inference time: {} ({:.6f} s / iter per device, on {} devices)".format(
total_time_str, total_time / (total - num_warmup), num_devices
)
)
total_compute_time_str = str(datetime.timedelta(seconds=int(total_compute_time)))
logger.info(
"Total inference pure compute time: {} ({:.6f} s / iter per device, on {} devices)".format(
total_compute_time_str, total_compute_time / (total - num_warmup), num_devices
)
)
results = evaluator.evaluate()
# An evaluator may return None when not in main process.
# Replace it by an empty dict instead to make it easier for downstream code to handle
if results is None:
results = {}
return results
@contextmanager
def inference_context(model):
"""
A context where the model is temporarily changed to eval mode,
and restored to previous mode afterwards.
Args:
model: a torch Module
"""
training_mode = model.training
model.eval()
yield
model.train(training_mode)
|