Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Revert "Regression updates" #41

Merged
merged 1 commit into from
Sep 17, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 6 additions & 8 deletions configs/augmentations/regression_default.yaml
Original file line number Diff line number Diff line change
@@ -1,13 +1,11 @@
train:
RegPreprocessor: ~
NormalizeMinMax: ~
# NormalizeMeanStd: ~
NormalizeMeanStd: ~
RandomCropToEncoder: ~
# RandomFlip:
# ud_probability: 0.3
# lr_probability: 0.3
RandomFlip:
ud_probability: 0.3
lr_probability: 0.3
test:
RegPreprocessor: ~
NormalizeMinMax: ~
# NormalizeMeanStd: ~
Tile: ~
NormalizeMeanStd: ~
Tile: ~
50 changes: 20 additions & 30 deletions configs/datasets/biomassters.yaml
Original file line number Diff line number Diff line change
@@ -1,14 +1,14 @@
dataset_name: BioMassters
root_path: /geoinfo_vol1/home/r/i/ru/
# download_url: #https://huggingface.co/datasets/ibm-nasa-geospatial/hls_burn_scars/resolve/main/hls_burn_scars.tar.gz?download=true
root_path: /geomatics/gpuserver-0/vmarsocci/biomassters
download_url: #https://huggingface.co/datasets/ibm-nasa-geospatial/hls_burn_scars/resolve/main/hls_burn_scars.tar.gz?download=true
auto_download: False
img_size: 256
temporal: 12 #6 (summer month if multi_temp false), 12
multi_temporal: True
multi_temporal: 12
multi_modal: True


# classes
ignore_index: -1
# ignore_index: -1
num_classes: 1
classes:
- regression
Expand All @@ -25,39 +25,29 @@ bands:
- B2
- B3
- B4
- B5
- B6
- B7
- B8
- B8A
- B11
- B12
- CLP
# - B5
# - B6
# - B7
# - B8
# - B8a
# - B11
# - B12
sar:
- ASC_VV
- ASC_VH
- DSC_VV
- DSC_VH

# TODO: fix the normalization
data_mean:
optical:
# - 66.7703
# - 88.4452
# - 85.1047
sar:
- 66.7703
- 88.4452
- 85.1047
# sar:

data_std:
optical:
# - 48.3066
# - 51.9129
# - 62.7612
sar:

data_min:
optical: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ]
sar: [-25, -62, -25, -60]

data_max:
optical: [19616., 18400., 17536., 17097., 16928., 16768., 16593., 16492., 15401., 15226., 255.]
sar: [29, 28, 30, 22]
- 48.3066
- 51.9129
- 62.7612
# sar:
24 changes: 0 additions & 24 deletions configs/segmentors/reg_upernet.yaml

This file was deleted.

5 changes: 3 additions & 2 deletions configs/segmentors/reg_upernet_mt.yaml
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
segmentor_name: MTUPerNet_regress
segmentor_name: MTUPerNet
task_name: regression
binary: False
multi_temporal_strategy: linear
time_frames: 12
# time_frames: 2
#task_model_args:
#num_frames: 1
#mt_strategy: "ltae" #activated only when if num_frames > 1
Expand Down
92 changes: 37 additions & 55 deletions datasets/biomassters.py
Original file line number Diff line number Diff line change
Expand Up @@ -2,51 +2,38 @@
import torch
import pandas as pd
import pathlib
import rasterio
from skimage import io
from os.path import join as opj
from .utils import read_tif
from utils.registry import DATASET_REGISTRY

s1_min = np.array([-25 , -62 , -25, -60], dtype="float32")
s1_max = np.array([ 29 , 28, 30, 22 ], dtype="float32")
s1_mm = s1_max - s1_min

s2_max = np.array(
[19616., 18400., 17536., 17097., 16928., 16768., 16593., 16492., 15401., 15226., 255.],
dtype="float32",
)

IMG_SIZE = (256, 256)

def read_imgs(multi_temporal, temp , fname, data_dir):
imgs_s1, imgs_s2, mask = [], [], []
if multi_temporal:
month_list = list(range(12))
else:
month_list = [temp]

for month in month_list:

s1_fname = '%s_%s_%02d.tif' % (str.split(fname, '_')[0], 'S1', month)
s2_fname = '%s_%s_%02d.tif' % (str.split(fname, '_')[0], 'S2', month)

s1_filepath = data_dir.joinpath(s1_fname)
if s1_filepath.exists():
img_s1 = io.imread(s1_filepath)
m = img_s1 == -9999
img_s1 = img_s1.astype("float32")
img_s1 = (img_s1 - s1_min) / s1_mm
img_s1 = np.where(m, 0, img_s1)
else:
img_s1 = np.zeros(IMG_SIZE + (4,), dtype="float32")

s2_filepath = data_dir.joinpath(s2_fname)
if s2_filepath.exists():
img_s2 = io.imread(s2_filepath)

def read_imgs(chip_id: str, data_dir: pathlib.Path):
imgs, imgs_s1, imgs_s2, mask = [], [], [], []
for month in range(12):
img_s1 = read_tif(data_dir.joinpath(f"{chip_id}_S1_{month:0>2}.tif"))
m = img_s1 == -9999
img_s1 = img_s1.astype("float32")
img_s1 = (img_s1 - s1_min) / s1_mm
img_s1 = np.where(m, 0, img_s1)
filepath = data_dir.joinpath(f"{chip_id}_S2_{month:0>2}.tif")
if filepath.exists():
img_s2 = read_tif(filepath)
img_s2 = img_s2.astype("float32")
img_s2 = img_s2 / s2_max
else:
else:
img_s2 = np.zeros(IMG_SIZE + (11,), dtype="float32")


# img = np.concatenate([img_s1, img_s2], axis=2)
img_s1 = np.transpose(img_s1, (2, 0, 1))
img_s2 = np.transpose(img_s2, (2, 0, 1))
imgs_s1.append(img_s1)
Expand All @@ -55,43 +42,39 @@ def read_imgs(multi_temporal, temp , fname, data_dir):

mask = np.array(mask)

imgs_s1 = np.stack(imgs_s1, axis=1) # [c, t, h, w] prithvi
imgs_s1 = np.stack(imgs_s1, axis=1) # [c, t, h, w]
imgs_s2 = np.stack(imgs_s2, axis=1) # [c, t, h, w]

return imgs_s1, imgs_s2, mask

@DATASET_REGISTRY.register()
class BioMassters(torch.utils.data.Dataset):
def __init__(self, cfg, split): #, augs=False):

self.root_path = cfg['root_path']
self.data_min = cfg['data_min']
self.data_max = cfg['data_max']
self.multi_temporal = cfg['multi_temporal']
self.temp = cfg['temporal']
df_path = pathlib.Path(cfg["root_path"]).joinpath("The_BioMassters_-_features_metadata.csv.csv")
df: pd.DataFrame = pd.read_csv(str(df_path))
self.df = df[df.split == split].copy()
self.dir_features = pathlib.Path(cfg["root_path"]).joinpath(f"{split}_features")
self.dir_labels = pathlib.Path(cfg["root_path"]).joinpath( f"{split}_agbm")
self.split = split
# self.augs = augs

self.data_path = pathlib.Path(self.root_path).joinpath(f"{split}_Data_list.csv")
self.id_list = pd.read_csv(self.data_path)['chip_id']
self.dir_features = pathlib.Path(self.root_path).joinpath("TRAIN/train_features")
self.dir_labels = pathlib.Path(self.root_path).joinpath( "TRAIN/train_agbm")

def __len__(self):
return len(self.id_list)
return len(self.df)

def __getitem__(self, index):
item = self.df.iloc[index]

# print(item.chip_id)
# print(self.dir_features)

chip_id = self.id_list.iloc[index]
fname = str(chip_id)+'_agbm.tif'
imgs_s1, imgs_s2, mask = read_imgs(item.chip_id, self.dir_features)
if self.dir_labels is not None:
target = read_tif(self.dir_labels.joinpath(f'{item.chip_id}_agbm.tif'))
else:
target = item.chip_id

imgs_s1, imgs_s2, mask = read_imgs(self.multi_temporal, self.temp, fname, self.dir_features)
with rasterio.open(self.dir_labels.joinpath(fname)) as lbl:
target = lbl.read(1)
target = np.nan_to_num(target)
# print(imgs_s1.shape, imgs_s2.shape, len(mask), target.shape)#(4, 1, 256, 256) (11, 1, 256, 256) 1 (256, 256)

# format (B/C, T, H, W)
# Reshaping tensors from (T, H, W, C) to (C, T, H, W)
imgs_s1 = torch.from_numpy(imgs_s1).float()
imgs_s2 = torch.from_numpy(imgs_s2).float()
target = torch.from_numpy(target).float()
Expand All @@ -107,12 +90,11 @@ def __getitem__(self, index):

@staticmethod
def get_splits(dataset_config):
dataset_train = BioMassters(cfg=dataset_config, split="train")
dataset_val = BioMassters(cfg=dataset_config, split="val")
dataset_train = BioMassters(cfg=dataset_config, split="test")
dataset_val = BioMassters(cfg=dataset_config, split="test")
dataset_test = BioMassters(cfg=dataset_config, split="test")
# print('loaded sample points',len(dataset_train), len(dataset_val), len(dataset_test))
return dataset_train, dataset_val, dataset_test

@staticmethod
def download(dataset_config:dict, silent=False):
pass
pass
24 changes: 21 additions & 3 deletions engine/evaluator.py
Original file line number Diff line number Diff line change
Expand Up @@ -170,11 +170,14 @@ def __init__(self, args, val_loader, exp_dir, device):

@torch.no_grad()
def evaluate(self, model, model_name='model'):
# TODO: Rework this to allow evaluation only runs
# Move common parts to parent class, and get loss function from the registry.
t = time.time()

model.eval()

tag = f'Evaluating {model_name} on {self.split} set'
# confusion_matrix = torch.zeros((self.num_classes, self.num_classes), device=self.device)

for batch_idx, data in enumerate(tqdm(self.val_loader, desc=tag)):
image, target = data['image'], data['target']
Expand All @@ -183,8 +186,14 @@ def evaluate(self, model, model_name='model'):

logits = model(image, output_shape=target.shape[-2:]).squeeze(dim=1)
mse = F.mse_loss(logits, target)

metrics = {"MSE" : mse.item(), "RMSE" : torch.sqrt(mse).item()}
# pred = torch.argmax(logits, dim=1)
# valid_mask = target != -1
# pred, target = pred[valid_mask], target[valid_mask]
# count = torch.bincount((pred * self.num_classes + target), minlength=self.num_classes ** 2)
# confusion_matrix += count.view(self.num_classes, self.num_classes)

# torch.distributed.all_reduce(confusion_matrix, op=torch.distributed.ReduceOp.SUM)
metrics = {"MSE" : mse.item, "RMSE" : torch.sqrt(mse).item}
self.log_metrics(metrics)

used_time = time.time() - t
Expand All @@ -195,11 +204,20 @@ def evaluate(self, model, model_name='model'):
def __call__(self, model, model_name='model'):
return self.evaluate(model, model_name)


# def compute_metrics(self, confusion_matrix):
# iou = torch.diag(confusion_matrix) / (confusion_matrix.sum(dim=1) + confusion_matrix.sum(dim=0) - torch.diag(confusion_matrix)) * 100
# iou = iou.cpu()
# metrics = {'IoU': [iou[i].item() for i in range(self.num_classes)], 'mIoU': iou.mean().item()}

# return metrics

def log_metrics(self, metrics):
header = "------- MSE and RMSE --------\n"
# iou = '\n'.join(c.ljust(self.max_name_len, ' ') + '\t{:>7}'.format('%.3f' % num) for c, num in zip(self.classes, metrics['MSE'])) + '\n'
mse = "-------------------\n" + 'MSE \t{:>7}'.format('%.3f' % metrics['MSE'])+'\n'
rmse = "-------------------\n" + 'RMSE \t{:>7}'.format('%.3f' % metrics['RMSE'])
self.logger.info(header+mse+rmse)

if self.args.use_wandb and self.args.rank == 0:
self.wandb.log({"val_MSE": metrics["MSE"], "val_RMSE": metrics["RMSE"]})
self.wandb.log({"val_MSE": metrics["MSE"], "val_RMSE": metrics["RMSE"]})
3 changes: 1 addition & 2 deletions environment.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,6 @@ dependencies:
- pillow
- pytorch>=2.1
- rasterio
- scikit-image
- scikit-learn
- tensorboard
- torchaudio
Expand All @@ -29,4 +28,4 @@ dependencies:
- google-cloud-storage
- omegaconf
- pydataverse
- pytest
- pytest
Loading