HuQiong
/
PaddleRS
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

_preprocess and _postprocess as public methods

Browse Source
own
Bobholamovic 2 years ago
parent c3acca5a9a
commit cdc9d93884
6 changed files with 38 additions and 40 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 12
      paddlers/deploy/predictor.py
  2. 12
      paddlers/tasks/change_detector.py
  3. 18
      paddlers/tasks/classifier.py
  4. 8
      paddlers/tasks/object_detector.py
  5. 12
      paddlers/tasks/segmenter.py
  6. 12
      test_tipc/infer.py

12
paddlers/deploy/predictor.py
Unescape View File

@ -146,7 +146,7 @@ class Predictor(object):
return predictor
def preprocess(self, images, transforms):
preprocessed_samples = self._model._preprocess(
preprocessed_samples = self._model.preprocess(
images, transforms, to_tensor=False)
if self._model.model_type == 'classifier':
preprocessed_samples = {'image': preprocessed_samples[0]}
@ -172,12 +172,12 @@ class Predictor(object):
def postprocess(self, net_outputs, topk=1, ori_shape=None, transforms=None):
if self._model.model_type == 'classifier':
true_topk = min(self._model.num_classes, topk)
if self._model._postprocess is None:
if self._model.postprocess is None:
self._model.build_postprocess_from_labels(topk)
# XXX: Convert ndarray to tensor as self._model._postprocess requires
# XXX: Convert ndarray to tensor as self._model.postprocess requires
assert len(net_outputs) == 1
net_outputs = paddle.to_tensor(net_outputs[0])
outputs = self._model._postprocess(net_outputs)
outputs = self._model.postprocess(net_outputs)
class_ids = map(itemgetter('class_ids'), outputs)
scores = map(itemgetter('scores'), outputs)
label_names = map(itemgetter('label_names'), outputs)
@ -187,7 +187,7 @@ class Predictor(object):
'label_names_map': n,
} for l, s, n in zip(class_ids, scores, label_names)]
elif self._model.model_type in ('segmenter', 'change_detector'):
label_map, score_map = self._model._postprocess(
label_map, score_map = self._model.postprocess(
net_outputs,
batch_origin_shape=ori_shape,
transforms=transforms.transforms)
@ -200,7 +200,7 @@ class Predictor(object):
k: v
for k, v in zip(['bbox', 'bbox_num', 'mask'], net_outputs)
}
preds = self._model._postprocess(net_outputs)
preds = self._model.postprocess(net_outputs)
else:
logging.error(
"Invalid model type {}.".format(self._model.model_type),

12
paddlers/tasks/change_detector.py
Unescape View File

@ -111,10 +111,10 @@ class BaseChangeDetector(BaseModel):
if mode == 'test':
origin_shape = inputs[2]
if self.status == 'Infer':
label_map_list, score_map_list = self._postprocess(
label_map_list, score_map_list = self.postprocess(
net_out, origin_shape, transforms=inputs[3])
else:
logit_list = self._postprocess(
logit_list = self.postprocess(
logit, origin_shape, transforms=inputs[3])
label_map_list = []
score_map_list = []
@ -142,7 +142,7 @@ class BaseChangeDetector(BaseModel):
raise ValueError("Expected label.ndim == 4 but got {}".format(
label.ndim))
origin_shape = [label.shape[-2:]]
pred = self._postprocess(
pred = self.postprocess(
pred, origin_shape, transforms=inputs[3])[0] # NCHW
intersect_area, pred_area, label_area = paddleseg.utils.metrics.calculate_area(
pred, label, self.num_classes)
@ -553,7 +553,7 @@ class BaseChangeDetector(BaseModel):
images = [img_file]
else:
images = img_file
batch_im1, batch_im2, batch_origin_shape = self._preprocess(
batch_im1, batch_im2, batch_origin_shape = self.preprocess(
images, transforms, self.model_type)
self.net.eval()
data = (batch_im1, batch_im2, batch_origin_shape, transforms.transforms)
@ -664,7 +664,7 @@ class BaseChangeDetector(BaseModel):
dst_data = None
print("GeoTiff saved in {}.".format(save_file))
def _preprocess(self, images, transforms, to_tensor=True):
def preprocess(self, images, transforms, to_tensor=True):
self._check_transforms(transforms, 'test')
batch_im1, batch_im2 = list(), list()
batch_ori_shape = list()
@ -736,7 +736,7 @@ class BaseChangeDetector(BaseModel):
batch_restore_list.append(restore_list)
return batch_restore_list
def _postprocess(self, batch_pred, batch_origin_shape, transforms):
def postprocess(self, batch_pred, batch_origin_shape, transforms):
batch_restore_list = BaseChangeDetector.get_transforms_shape_info(
batch_origin_shape, transforms)
if isinstance(batch_pred, (tuple, list)) and self.status == 'Infer':

18
paddlers/tasks/classifier.py
Unescape View File

@ -61,7 +61,7 @@ class BaseClassifier(BaseModel):
self.metrics = None
self.losses = None
self.labels = None
self._postprocess = None
self.postprocess = None
if params.get('with_net', True):
params.pop('with_net', None)
self.net = self.build_net(**params)
@ -121,13 +121,12 @@ class BaseClassifier(BaseModel):
net_out = net(inputs[0])
if mode == 'test':
return self._postprocess(net_out)
return self.postprocess(net_out)
outputs = OrderedDict()
label = paddle.to_tensor(inputs[1], dtype="int64")
if mode == 'eval':
# print(self._postprocess(net_out)[0]) # for test
label = paddle.unsqueeze(label, axis=-1)
metric_dict = self.metrics(net_out, label)
outputs['top1'] = metric_dict["top1"]
@ -176,13 +175,13 @@ class BaseClassifier(BaseModel):
label_dict = dict()
for i, label in enumerate(self.labels):
label_dict[i] = label
self._postprocess = build_postprocess({
self.postprocess = build_postprocess({
"name": "Topk",
"topk": topk,
"class_id_map_file": None
})
# Add class_id_map from model.yml
self._postprocess.class_id_map = label_dict
self.postprocess.class_id_map = label_dict
def train(self,
num_epochs,
@ -247,8 +246,7 @@ class BaseClassifier(BaseModel):
if self.losses is None:
self.losses = self.default_loss()
self.metrics = self.default_metric()
self._postprocess = self.default_postprocess(train_dataset.label_list)
# print(self._postprocess.class_id_map)
self.postprocess = self.default_postprocess(train_dataset.label_list)
if optimizer is None:
num_steps_each_epoch = train_dataset.num_samples // train_batch_size
@ -454,12 +452,12 @@ class BaseClassifier(BaseModel):
images = [img_file]
else:
images = img_file
batch_im, batch_origin_shape = self._preprocess(images, transforms,
batch_im, batch_origin_shape = self.preprocess(images, transforms,
self.model_type)
self.net.eval()
data = (batch_im, batch_origin_shape, transforms.transforms)
if self._postprocess is None:
if self.postprocess is None:
self.build_postprocess_from_labels()
outputs = self.run(self.net, data, 'test')
@ -480,7 +478,7 @@ class BaseClassifier(BaseModel):
}
return prediction
def _preprocess(self, images, transforms, to_tensor=True):
def preprocess(self, images, transforms, to_tensor=True):
self._check_transforms(transforms, 'test')
batch_im = list()
batch_ori_shape = list()

8
paddlers/tasks/object_detector.py
Unescape View File

@ -580,16 +580,16 @@ class BaseDetector(BaseModel):
else:
images = img_file
batch_samples = self._preprocess(images, transforms)
batch_samples = self.preprocess(images, transforms)
self.net.eval()
outputs = self.run(self.net, batch_samples, 'test')
prediction = self._postprocess(outputs)
prediction = self.postprocess(outputs)
if isinstance(img_file, (str, np.ndarray)):
prediction = prediction[0]
return prediction
def _preprocess(self, images, transforms, to_tensor=True):
def preprocess(self, images, transforms, to_tensor=True):
self._check_transforms(transforms, 'test')
batch_samples = list()
for im in images:
@ -606,7 +606,7 @@ class BaseDetector(BaseModel):
return batch_samples
def _postprocess(self, batch_pred):
def postprocess(self, batch_pred):
infer_result = {}
if 'bbox' in batch_pred:
bboxes = batch_pred['bbox']

12
paddlers/tasks/segmenter.py
Unescape View File

@ -110,10 +110,10 @@ class BaseSegmenter(BaseModel):
if mode == 'test':
origin_shape = inputs[1]
if self.status == 'Infer':
label_map_list, score_map_list = self._postprocess(
label_map_list, score_map_list = self.postprocess(
net_out, origin_shape, transforms=inputs[2])
else:
logit_list = self._postprocess(
logit_list = self.postprocess(
logit, origin_shape, transforms=inputs[2])
label_map_list = []
score_map_list = []
@ -141,7 +141,7 @@ class BaseSegmenter(BaseModel):
raise ValueError("Expected label.ndim == 4 but got {}".format(
label.ndim))
origin_shape = [label.shape[-2:]]
pred = self._postprocess(
pred = self.postprocess(
pred, origin_shape, transforms=inputs[2])[0] # NCHW
intersect_area, pred_area, label_area = paddleseg.utils.metrics.calculate_area(
pred, label, self.num_classes)
@ -526,7 +526,7 @@ class BaseSegmenter(BaseModel):
images = [img_file]
else:
images = img_file
batch_im, batch_origin_shape = self._preprocess(images, transforms,
batch_im, batch_origin_shape = self.preprocess(images, transforms,
self.model_type)
self.net.eval()
data = (batch_im, batch_origin_shape, transforms.transforms)
@ -631,7 +631,7 @@ class BaseSegmenter(BaseModel):
dst_data = None
print("GeoTiff saved in {}.".format(save_file))
def _preprocess(self, images, transforms, to_tensor=True):
def preprocess(self, images, transforms, to_tensor=True):
self._check_transforms(transforms, 'test')
batch_im = list()
batch_ori_shape = list()
@ -698,7 +698,7 @@ class BaseSegmenter(BaseModel):
batch_restore_list.append(restore_list)
return batch_restore_list
def _postprocess(self, batch_pred, batch_origin_shape, transforms):
def postprocess(self, batch_pred, batch_origin_shape, transforms):
batch_restore_list = BaseSegmenter.get_transforms_shape_info(
batch_origin_shape, transforms)
if isinstance(batch_pred, (tuple, list)) and self.status == 'Infer':

12
test_tipc/infer.py
Unescape View File

@ -141,7 +141,7 @@ class TIPCPredictor(object):
return config
def preprocess(self, images, transforms):
preprocessed_samples = self._model._preprocess(
preprocessed_samples = self._model.preprocess(
images, transforms, to_tensor=False)
if self._model.model_type == 'classifier':
preprocessed_samples = {'image': preprocessed_samples[0]}
@ -167,12 +167,12 @@ class TIPCPredictor(object):
def postprocess(self, net_outputs, topk=1, ori_shape=None, transforms=None):
if self._model.model_type == 'classifier':
true_topk = min(self._model.num_classes, topk)
if self._model._postprocess is None:
if self._model.postprocess is None:
self._model.build_postprocess_from_labels(topk)
# XXX: Convert ndarray to tensor as self._model._postprocess requires
# XXX: Convert ndarray to tensor as self._model.postprocess requires
assert len(net_outputs) == 1
net_outputs = paddle.to_tensor(net_outputs[0])
outputs = self._model._postprocess(net_outputs)
outputs = self._model.postprocess(net_outputs)
class_ids = map(itemgetter('class_ids'), outputs)
scores = map(itemgetter('scores'), outputs)
label_names = map(itemgetter('label_names'), outputs)
@ -182,7 +182,7 @@ class TIPCPredictor(object):
'label_names_map': n,
} for l, s, n in zip(class_ids, scores, label_names)]
elif self._model.model_type in ('segmenter', 'change_detector'):
label_map, score_map = self._model._postprocess(
label_map, score_map = self._model.postprocess(
net_outputs,
batch_origin_shape=ori_shape,
transforms=transforms.transforms)
@ -195,7 +195,7 @@ class TIPCPredictor(object):
k: v
for k, v in zip(['bbox', 'bbox_num', 'mask'], net_outputs)
}
preds = self._model._postprocess(net_outputs)
preds = self._model.postprocess(net_outputs)
else:
logging.error(
"Invalid model type {}.".format(self._model.model_type),

Write Preview
Loading…
Cancel
Save