File size: 5,580 Bytes
e5765b1 |
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 |
import argparse
import os
from pathlib import Path
from typing import Dict
import pytorch_lightning as pl
import torch
import yaml
from albumentations.core.serialization import from_dict
from iglovikov_helper_functions.config_parsing.utils import object_from_dict
from iglovikov_helper_functions.dl.pytorch.lightning import find_average
from iglovikov_helper_functions.dl.pytorch.utils import state_dict_from_disk
from pytorch_lightning.loggers import WandbLogger
from pytorch_toolbelt.losses import JaccardLoss, BinaryFocalLoss
from torch.utils.data import DataLoader
from cloths_segmentation.dataloaders import SegmentationDataset
from cloths_segmentation.metrics import binary_mean_iou
from cloths_segmentation.utils import get_samples
image_path = Path(os.environ["IMAGE_PATH"])
mask_path = Path(os.environ["MASK_PATH"])
def get_args():
parser = argparse.ArgumentParser()
arg = parser.add_argument
arg("-c", "--config_path", type=Path, help="Path to the config.", required=True)
return parser.parse_args()
class SegmentPeople(pl.LightningModule):
def __init__(self, hparams):
super().__init__()
self.hparams = hparams
self.model = object_from_dict(self.hparams["model"])
if "resume_from_checkpoint" in self.hparams:
corrections: Dict[str, str] = {"model.": ""}
state_dict = state_dict_from_disk(
file_path=self.hparams["resume_from_checkpoint"],
rename_in_layers=corrections,
)
self.model.load_state_dict(state_dict)
self.losses = [
("jaccard", 0.1, JaccardLoss(mode="binary", from_logits=True)),
("focal", 0.9, BinaryFocalLoss()),
]
def forward(self, batch: torch.Tensor) -> torch.Tensor: # type: ignore
return self.model(batch)
def setup(self, stage=0):
samples = get_samples(image_path, mask_path)
num_train = int((1 - self.hparams["val_split"]) * len(samples))
self.train_samples = samples[:num_train]
self.val_samples = samples[num_train:]
print("Len train samples = ", len(self.train_samples))
print("Len val samples = ", len(self.val_samples))
def train_dataloader(self):
train_aug = from_dict(self.hparams["train_aug"])
if "epoch_length" not in self.hparams["train_parameters"]:
epoch_length = None
else:
epoch_length = self.hparams["train_parameters"]["epoch_length"]
result = DataLoader(
SegmentationDataset(self.train_samples, train_aug, epoch_length),
batch_size=self.hparams["train_parameters"]["batch_size"],
num_workers=self.hparams["num_workers"],
shuffle=True,
pin_memory=True,
drop_last=True,
)
print("Train dataloader = ", len(result))
return result
def val_dataloader(self):
val_aug = from_dict(self.hparams["val_aug"])
result = DataLoader(
SegmentationDataset(self.val_samples, val_aug, length=None),
batch_size=self.hparams["val_parameters"]["batch_size"],
num_workers=self.hparams["num_workers"],
shuffle=False,
pin_memory=True,
drop_last=False,
)
print("Val dataloader = ", len(result))
return result
def configure_optimizers(self):
optimizer = object_from_dict(
self.hparams["optimizer"],
params=[x for x in self.model.parameters() if x.requires_grad],
)
scheduler = object_from_dict(self.hparams["scheduler"], optimizer=optimizer)
self.optimizers = [optimizer]
return self.optimizers, [scheduler]
def training_step(self, batch, batch_idx):
features = batch["features"]
masks = batch["masks"]
logits = self.forward(features)
total_loss = 0
logs = {}
for loss_name, weight, loss in self.losses:
ls_mask = loss(logits, masks)
total_loss += weight * ls_mask
logs[f"train_mask_{loss_name}"] = ls_mask
logs["train_loss"] = total_loss
logs["lr"] = self._get_current_lr()
return {"loss": total_loss, "log": logs}
def _get_current_lr(self) -> torch.Tensor:
lr = [x["lr"] for x in self.optimizers[0].param_groups][0] # type: ignore
return torch.Tensor([lr])[0].cuda()
def validation_step(self, batch, batch_id):
features = batch["features"]
masks = batch["masks"]
logits = self.forward(features)
result = {}
for loss_name, _, loss in self.losses:
result[f"val_mask_{loss_name}"] = loss(logits, masks)
result["val_iou"] = binary_mean_iou(logits, masks)
return result
def validation_epoch_end(self, outputs):
logs = {"epoch": self.trainer.current_epoch}
avg_val_iou = find_average(outputs, "val_iou")
logs["val_iou"] = avg_val_iou
return {"val_iou": avg_val_iou, "log": logs}
def main():
args = get_args()
with open(args.config_path) as f:
hparams = yaml.load(f, Loader=yaml.SafeLoader)
pipeline = SegmentPeople(hparams)
Path(hparams["checkpoint_callback"]["filepath"]).mkdir(exist_ok=True, parents=True)
trainer = object_from_dict(
hparams["trainer"],
logger=WandbLogger(hparams["experiment_name"]),
checkpoint_callback=object_from_dict(hparams["checkpoint_callback"]),
)
trainer.fit(pipeline)
if __name__ == "__main__":
main()
|