def test_compute_IoU(download_release):
m = main.deepforest()
m.use_release(check_release=False)
csv_file = get_data("OSBS_029.csv")
predictions = m.predict_file(csv_file=csv_file,
root_dir=os.path.dirname(csv_file))
ground_truth = pd.read_csv(csv_file)
predictions['geometry'] = predictions.apply(
lambda x: shapely.geometry.box(x.xmin, x.ymin, x.xmax, x.ymax), axis=1)
predictions = gpd.GeoDataFrame(predictions, geometry='geometry')
ground_truth['geometry'] = ground_truth.apply(
lambda x: shapely.geometry.box(x.xmin, x.ymin, x.xmax, x.ymax), axis=1)
ground_truth = gpd.GeoDataFrame(ground_truth, geometry='geometry')
ground_truth.label = 0
predictions.label = 0
visualize.plot_prediction_dataframe(df=predictions,
ground_truth=ground_truth,
root_dir=os.path.dirname(csv_file))
result = IoU.compute_IoU(ground_truth, predictions)
assert result.shape[0] == ground_truth.shape[0]
assert sum(result.IoU) > 10
def test_plot_prediction_dataframe(m, tmpdir):
ds = m.val_dataloader()
batch = next(iter(ds))
paths, images, targets = batch
for path, image, target in zip(paths, images, targets):
target_df = visualize.format_boxes(target, scores=False)
target_df["image_path"] = path
visualize.plot_prediction_dataframe(
df=target_df,
savedir=tmpdir,
root_dir=m.config["validation"]["root_dir"])
def evaluate_image(predictions, ground_df, show_plot, root_dir, savedir):
"""
Compute intersection-over-union matching among prediction and ground truth boxes for one image
Args:
df: a pandas dataframe with columns name, xmin, xmax, ymin, ymax, label. The 'name' column should be the path relative to the location of the file.
show: Whether to show boxes as they are plotted
summarize: Whether to group statistics by plot and overall score
image_coordinates: Whether the current boxes are in coordinate system of the image, e.g. origin (0,0) upper left.
root_dir: Where to search for image names in df
Returns:
result: pandas dataframe with crown ids of prediciton and ground truth and the IoU score.
"""
plot_names = predictions["image_path"].unique()
if len(plot_names) > 1:
raise ValueError(
"More than one plot passed to image crown: {}".format(plot_name))
else:
plot_name = plot_names[0]
predictions['geometry'] = predictions.apply(
lambda x: shapely.geometry.box(x.xmin, x.ymin, x.xmax, x.ymax), axis=1)
predictions = gpd.GeoDataFrame(predictions, geometry='geometry')
ground_df['geometry'] = ground_df.apply(
lambda x: shapely.geometry.box(x.xmin, x.ymin, x.xmax, x.ymax), axis=1)
ground_df = gpd.GeoDataFrame(ground_df, geometry='geometry')
if savedir:
visualize.plot_prediction_dataframe(df=predictions,
ground_truth=ground_df,
root_dir=root_dir,
savedir=savedir)
else:
if show_plot:
visualize.plot_prediction_dataframe(df=predictions,
ground_truth=ground_df,
root_dir=root_dir,
savedir=savedir,
show=True)
# match
result = IoU.compute_IoU(ground_df, predictions)
#add the label classes
result["predicted_label"] = result.prediction_id.apply(
lambda x: predictions.label.loc[x] if pd.notnull(x) else x)
result["true_label"] = result.truth_id.apply(
lambda x: ground_df.label.loc[x])
return result
def test_confirm_backend(m, tmpdir, show):
"""When a use call a visualize function we are using matplotlib to save figures, this should not interfere with plotting in global scope"""
ds = m.val_dataloader()
batch = next(iter(ds))
paths, images, targets = batch
original_backend = matplotlib.get_backend()
for path, image, target in zip(paths, images, targets):
target_df = visualize.format_boxes(target, scores=False)
target_df["image_path"] = path
visualize.plot_prediction_dataframe(
df=target_df,
savedir=tmpdir,
root_dir=m.config["validation"]["root_dir"],
show=show)
post_backend = matplotlib.get_backend()
assert original_backend == post_backend