Here's using the data before we started cleaning. This is only for bounding boxes, not ring counts
Installing IceVision and IceData
If on Colab run the following cell, else check the installation instructions
!if -e /content:
try:
!wget https://raw.githubusercontent.com/airctic/icevision/master/install_colab.sh
!chmod +x install_colab.sh && ./install_colab.sh
except:
print("Ignore the error messages and just keep going")
!if !-e /content:
# For Icevision Install of MMD. cf. https://airctic.com/0.8.1/install/
import torch, re
tv, cv = torch.__version__, torch.version.cuda
tv = re.sub('\+cu.*','',tv)
TORCH_VERSION = 'torch'+tv[0:-1]+'0'
CUDA_VERSION = 'cu'+cv.replace('.','')
print(f"TORCH_VERSION={TORCH_VERSION}; CUDA_VERSION={CUDA_VERSION}")
!pip install -qq mmcv-full=="1.3.8" -f https://download.openmmlab.com/mmcv/dist/{CUDA_VERSION}/{TORCH_VERSION}/index.html --upgrade
!pip install mmdet -qq
from icevision.all import *
import pandas as pd
We're going to be using a small sample of the chess dataset, the full dataset is offered by roboflow here
#data_dir = icedata.load_data(data_url, 'chess_sample') / 'chess_sample-master'
# SPNET Real Dataset link (currently proprietary, thus link may not work)
#data_url = "https://anonymized.machine.com/~drscotthawley/spnet_sample-master.zip"
#data_dir = icedata.load_data(data_url, 'spnet_sample') / 'spnet_sample-master'
# espiownage cyclegan dataset:
#data_url = 'https://anonymized.machine.com/~drscotthawley/espiownage-cyclegan.tgz'
#data_dir = icedata.load_data(data_url, 'espiownage-cyclegan') / 'espiownage-cyclegan'
from pathlib import Path
# pre-cleaned "annotations_15ormore"
data_dir = Path('/home/drscotthawley/datasets/espiownage-preclean')
In this task we were given a .csv file with annotations, let's take a look at that.
df = pd.read_csv(data_dir / "bboxes/annotations.csv")
df.head()
At first glance, we can make the following assumptions:
- Multiple rows with the same filename, width, height
- A label for each row
- A bbox [xmin, ymin, xmax, ymax] for each row
Once we know what our data provides we can create our custom Parser.
set(np.array(df['label']).flatten())
Label all as "AN" for antinodes:
df['label'] = "AN"
df.head()
The first step is to create a template record for our specific type of dataset, in this case we're doing standard object detection:
template_record = ObjectDetectionRecord()
Now use the method generate_template that will print out all the necessary steps we have to implement.
Parser.generate_template(template_record)
# but currently not a priority!
class ChessParser(Parser):
def __init__(self, template_record, data_dir):
super().__init__(template_record=template_record)
self.data_dir = data_dir
self.df = pd.read_csv(data_dir / "bboxes/annotations.csv")
self.df['label'] = 'AN' # make them all the same object
self.class_map = ClassMap(list(self.df['label'].unique()))
def __iter__(self) -> Any:
for o in self.df.itertuples():
yield o
def __len__(self) -> int:
return len(self.df)
def record_id(self, o) -> Hashable:
return o.filename
def parse_fields(self, o, record, is_new):
if is_new:
record.set_filepath(self.data_dir / 'images' / o.filename)
record.set_img_size(ImgSize(width=o.width, height=o.height))
record.detection.set_class_map(self.class_map)
record.detection.add_bboxes([BBox.from_xyxy(o.xmin, o.ymin, o.xmax, o.ymax)])
record.detection.add_labels([o.label])
Let's randomly split the data and parser with Parser.parse:
parser = ChessParser(template_record, data_dir)
train_records, valid_records = parser.parse()
Let's take a look at one record:
show_record(train_records[5], display_label=False, figsize=(14, 10))
train_records[0]
# size is set to 384 because EfficientDet requires its inputs to be divisible by 128
image_size = 384
train_tfms = tfms.A.Adapter([*tfms.A.aug_tfms(size=image_size, presize=512), tfms.A.Normalize()])
valid_tfms = tfms.A.Adapter([*tfms.A.resize_and_pad(image_size), tfms.A.Normalize()])
# Datasets
train_ds = Dataset(train_records, train_tfms)
valid_ds = Dataset(valid_records, valid_tfms)
samples = [train_ds[0] for _ in range(3)]
show_samples(samples, ncols=3)
model_type = models.mmdet.retinanet
backbone = model_type.backbones.resnet50_fpn_1x(pretrained=True)
selection = 0
extra_args = {}
if selection == 0:
model_type = models.mmdet.retinanet
backbone = model_type.backbones.resnet50_fpn_1x
elif selection == 1:
# The Retinanet model is also implemented in the torchvision library
model_type = models.torchvision.retinanet
backbone = model_type.backbones.resnet50_fpn
elif selection == 2:
model_type = models.ross.efficientdet
backbone = model_type.backbones.tf_lite0
# The efficientdet model requires an img_size parameter
extra_args['img_size'] = image_size
elif selection == 3:
model_type = models.ultralytics.yolov5
backbone = model_type.backbones.small
# The yolov5 model requires an img_size parameter
extra_args['img_size'] = image_size
model_type, backbone, extra_args
model = model_type.model(backbone=backbone(pretrained=True), num_classes=len(parser.class_map), **extra_args)
train_dl = model_type.train_dl(train_ds, batch_size=8, num_workers=4, shuffle=True)
valid_dl = model_type.valid_dl(valid_ds, batch_size=8, num_workers=4, shuffle=False)
model_type.show_batch(first(valid_dl), ncols=4)
metrics = [COCOMetric(metric_type=COCOMetricType.bbox)]
learn = model_type.fastai.learner(dls=[train_dl, valid_dl], model=model, metrics=metrics)
learn.lr_find()
# For Sparse-RCNN, use lower `end_lr`
# learn.lr_find(end_lr=0.005)
learn.fine_tune(60, 1e-4, freeze_epochs=2)
learn.save('iv_bbox_preclean')
learn.load('iv_bbox_preclean');
model_type.show_results(model, valid_ds, detection_threshold=.5)
Note: Notice that a lot of rings get missed, even for this "exact" CycleGAN data. This does not bode well for the real data.
Note: We could try varying the
detection_threshold=0.5 and plot an ROC curve.