我有以下一段代码，它加载一个数据集，将图像调整为1200 * 800，加载它们的注释，然后报告准确性和预测：
# resize images
resized_images = []
file_names = glob(os.path.join(IMAGE_DIR, "*.jpg"))
for i in range(len(file_names)):
print("Resizing: " + str(i))
image = skimage.io.imread(file_names[i])
image_resized = resize(image, (1200, 800),anti_aliasing=True)
resized_images.append(image_resized)
masks_prediction = np.zeros((1200, 800, len(file_names)))
for i in range(len(resized_images)):
print(i)
image = resized_images[i]
predictions = model.detect([image], verbose=1)
p = predictions[0]
masks = p['masks']
merged_mask = np.zeros((masks.shape[0], masks.shape[1]))
for j in range(masks.shape[2]):
merged_mask[masks[:,:,j]==True] = True
masks_prediction[:,:,i] = merged_mask
print(masks_prediction.shape)
#load annotations
dataset = components.ComponentsDataset()
dataset.load_components(ANNOTATION_DIR, "predict")
resized_images = []
file_names = glob(os.path.join(IMAGE_DIR, "*.jpg"))
for i in range(len(file_names)):
print("Resizing: " + str(i))
image = skimage.io.imread(file_names[i])
image_resized = resize(image, (1200, 800),anti_aliasing=True)
resized_images.append(image_resized)
# report the accuracy and prediction
accuracy = 0
precision = 0
for image_id in range(len(dataset.image_info)):
name = dataset.image_info[image_id]['id']
file_name = os.path.join(IMAGE_DIR, name)
image_id_pred = file_names.index(file_name)
merged_mask = masks_prediction[:, :, image_id_pred]
annotated_mask = dataset.load_mask(image_id)[0]
merged_annotated_mask = np.zeros((1200, 800))
for i in range(annotated_mask.shape[2]):
merged_annotated_mask[annotated_mask[:,:,i]==True] = True
accuracy += np.sum(merged_mask==merged_annotated_mask) / (1200 * 800)
all_correct = np.sum(merged_annotated_mask[merged_mask == 1])
precision += all_correct / (np.sum(merged_mask))
print('accuracy:{}'.format(accuracy / len(file_names)))
print('precision:{}'.format(precision / len(file_names)))
但是我收到以下错误，这使我认为尺寸完全不对：
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-38-a652e79112fb> in <module>()
10 merged_annotated_mask = np.zeros((1200, 800))
11 for i in range(annotated_mask.shape[2]):
---> 12 merged_annotated_mask[annotated_mask[:,:,i]==True] = True
13 accuracy += np.sum(merged_mask==merged_annotated_mask) / (1200 * 800)
14 all_correct = np.sum(merged_annotated_mask[merged_mask == 1])
IndexError: boolean index did not match indexed array along dimension 0; dimension is 1200 but corresponding boolean dimension is 1572
在将尺寸调整为1200 * 800之前，我没有收到此错误，但是随后出现另一个错误，告诉我尺寸不匹配。在这一点上，我将非常感谢能够以某种方式一次解决此大小问题的解决方案。我时不时在Python中遇到这个问题，而且越来越令人沮丧。
编辑：包括数据集类。
############################################################
# Dataset
############################################################
class ComponentsDataset(utils.Dataset):
def load_components(self, dataset_dir, subset):
"""Load a subset of the Components dataset.
dataset_dir: Root directory of the dataset.
subset: Subset to load: train or val
"""
# Add classes.
self.add_class("components", 1, "screw")
self.add_class("components", 2, "lid")
# which dataset?
assert subset in ["train", "val", "predict"]
dataset_dir = os.path.join(dataset_dir, subset)
# We mostly care about the x and y coordinates of each region
annotations = json.load(open(os.path.join(dataset_dir, "via_region_data.json")))
annotations = list(annotations.values()) # don't need the dict keys
# The VIA tool saves images in the JSON even if they don't have any
# annotations. Skip unannotated images.
annotations = [a for a in annotations if a['regions']]
# Add images
for a in annotations:
# Get the x, y coordinaets of points of the polygons that make up
# the outline of each object instance. There are stored in the
# shape_attributes (see json format above)
polygons = [r['shape_attributes'] for r in a['regions']]
names = [r['region_attributes'] for r in a['regions']]
# load_mask() needs the image size to convert polygons to masks.
# Unfortunately, VIA doesn't include it in JSON, so we must read
# the image. This is only managable since the dataset is tiny.
image_path = os.path.join(dataset_dir, a['filename'])
image = skimage.io.imread(image_path)
height, width = image.shape[:2]
self.add_image(
"components",
image_id=a['filename'], # use file name as a unique image id
path=image_path,
width=width, height=height,
polygons=polygons,
names=names)
def load_mask(self, image_id):
"""Generate instance masks for an image.
Returns:
masks: A bool array of shape [height, width, instance count] with
one mask per instance.
class_ids: a 1D array of class IDs of the instance masks.
"""
# If not a balloon dataset image, delegate to parent class.
image_info = self.image_info[image_id]
if image_info["source"] != "components":
return super(self.__class__, self).load_mask(image_id)
# Convert polygons to a bitmap mask of shape
# [height, width, instance_count]
info = self.image_info[image_id]
class_names = info["names"]
mask = np.zeros([info["height"], info["width"], len(info["polygons"])],
dtype=np.uint8)
for i, p in enumerate(info["polygons"]):
# Get indexes of pixels inside the polygon and set them to 1
rr, cc = skimage.draw.polygon(p['all_points_y'], p['all_points_x'])
mask[rr, cc, i] = 1
# Assign class_ids by reading class_names
class_ids = np.zeros([len(info["polygons"])])
# In the components dataset, pictures are labeled with name 'screw' and 'lid' representing arm and ring.
for i, p in enumerate(class_names):
# "name" is the attributes name decided when labeling, etc. 'region_attributes': {name:'a'}
if p['name'] == 'screw':
class_ids[i] = 1
elif p['name'] == 'lid':
class_ids[i] = 2
# assert code here to extend to other labels
class_ids = class_ids.astype(int)
# Return mask, and array of class IDs of each instance. Since we have
# one class ID only, we return an array of 1s
return mask.astype(np.bool), class_ids
def image_reference(self, image_id):
"""Return the path of the image."""
info = self.image_info[image_id]
if info["source"] == "components":
return info["path"]
else:
super(self.__class__, self).image_reference(image_id)
def load_mask_hc(self, image_id):
"""Generate instance masks for an image.
Returns:
masks: A bool array of shape [height, width, instance count] with
one mask per instance.
class_ids: a 1D array of class IDs of the instance masks.
"""
# If not a components dataset image, delegate to parent class.
image_info = self.image_info[image_id]
if image_info["source"] != "components":
return super(self.__class__, self).load_mask(image_id)
# Convert polygons to a bitmap mask of shape
# [height, width, instance_count]
info = self.image_info[image_id]
# "name" is the attributes name decided when labeling, etc. 'region_attributes': {name:'a'}
class_names = info["names"]
mask = np.zeros([info["height"], info["width"], len(info["polygons"])],
dtype=np.uint8)
for i, p in enumerate(info["polygons"]):
# Get indexes of pixels inside the polygon and set them to 1
rr, cc = skimage.draw.polygon(p['all_points_y'], p['all_points_x'])
mask[rr, cc, i] = 1
# Assign class_ids by reading class_names
class_ids = np.zeros([len(info["polygons"])])
# In the components dataset, pictures are labeled with name 'screw' and 'lid' representing arm and ring.
for i, p in enumerate(class_names):
if p['name'] == 'lid':
class_ids[i] = 14
elif p['name'] == 'error':
pass
else:
class_ids[i] = int(p['name'])
# assert code here to extend to other labels
class_ids = class_ids.astype(int)
# Return mask, and array of class IDs of each instance. Since we have
# one class ID only, we return an array of 1s
return mask.astype(np.bool), class_ids
答案 0 :(得分：1)
列表resized_images中的图像均已正确调整为（1200，800）。但是带注释的蒙版是从数据集中加载的，不会即时调整大小：
annotated_mask = dataset.load_mask(image_id)[0]
方法load_mask生成图像的原始height和width的遮罩图像，而不是调整大小的图像。遮罩的大小和图像的大小需要匹配。
您可以在加载遮罩图像后调整其大小（类似于调整输入图像的大小），以使此方法有效。
另一种选择是进行批处理-将所有图像调整为相同的大小，再次将其保存为.jpg并将其用作新输入，而在此程序中根本不进行任何调整。但是随后，您还必须仔细调整其他数据（例如多边形）以匹配新坐标。