mindspore-Ecosystem
/
mindspore
21
0
Fork 27
Code Issues Pull Requests 6 Projects Releases Wiki Activity

fix doc and comment spell mistakes

This commit is contained in:
zhouneng 2021-02-09 15:34:10 +08:00
parent b7b553ae48
commit 278443d6c4
16 changed files with 30 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
model_zoo/official/cv/cnnctc/README_CN.md
View File

@ -261,7 +261,7 @@ bash scripts/run_eval_ascend.sh $TRAINED_CKPT
### 训练性能
| 参数 | Faster R-CNN |
| 参数 | CNNCTC |
| -------------------------- | ----------------------------------------------------------- |
| 模型版本 | V1 |
| 资源 | Ascend 910；CPU 2.60GHz，192核；内存：755G |
@ -278,7 +278,7 @@ bash scripts/run_eval_ascend.sh $TRAINED_CKPT
### 评估性能
| 参数 | Faster R-CNN |
| 参数 | CNNCTC |
| ------------------- | --------------------------- |
| 模型版本 | V1 |
| 资源 | Ascend 910 |

6
model_zoo/official/cv/densenet121/scripts/run_distribute_eval.sh
View File

@ -15,13 +15,13 @@
# ============================================================================
echo "=============================================================================================================="
echo "Please run the scipt as: "
echo "Please run the script as: "
echo "sh scripts/run_distribute_eval.sh DEVICE_NUM RANK_TABLE_FILE DATASET CKPT_PATH"
echo "for example: sh scripts/run_distribute_train.sh 8 /data/hccl.json /path/to/dataset /path/to/ckpt"
echo "It is better to use absolute path."
echo "================================================================================================================="
echo "After running the scipt, the network runs in the background. The log will be generated in eval_x/log.txt"
echo "After running the script, the network runs in the background. The log will be generated in eval_x/log.txt"
export RANK_SIZE=$1
export RANK_TABLE_FILE=$2
@ -37,7 +37,7 @@ do
cp -r ./src ./eval_$i
cd ./eval_$i || exit
export RANK_ID=$i
echo "start infering for rank $i, device $DEVICE_ID"
echo "start inferring for rank $i, device $DEVICE_ID"
env > env.log
python eval.py \
--data_dir=$DATASET \

4
model_zoo/official/cv/densenet121/scripts/run_distribute_train.sh
View File

@ -15,13 +15,13 @@
# ============================================================================
echo "=============================================================================================================="
echo "Please run the scipt as: "
echo "Please run the script as: "
echo "sh scripts/run_distribute_train.sh DEVICE_NUM RANK_TABLE_FILE DATASET CKPT_FILE"
echo "for example: sh scripts/run_distribute_train.sh 8 /data/hccl.json /path/to/dataset ckpt_file"
echo "It is better to use absolute path."
echo "================================================================================================================="
echo "After running the scipt, the network runs in the background. The log will be generated in train_x/log.txt"
echo "After running the script, the network runs in the background. The log will be generated in train_x/log.txt"
export RANK_SIZE=$1
export RANK_TABLE_FILE=$2

4
model_zoo/official/cv/densenet121/src/network/densenet.py
View File

@ -121,7 +121,7 @@ class _DenseBlock(nn.Cell):
class _Transition(nn.Cell):
"""
the transiton layer
the transition layer
"""
def __init__(self, num_input_features, num_output_features):
super(_Transition, self).__init__()
@ -203,7 +203,7 @@ def _densenet201(**kwargs):
class DenseNet121(nn.Cell):
"""
the densenet121 architectur
the densenet121 architecture
"""
def __init__(self, num_classes, include_top=True):
super(DenseNet121, self).__init__()

4
model_zoo/official/cv/inceptionv4/README.md
View File

@ -139,7 +139,7 @@ sh scripts/run_standalone_train_ascend.sh DEVICE_ID DATA_DIR
### Result
Training result will be stored in the example path. Checkpoints will be stored at `ckpt_path` by default, and training log will be redirected to `./log.txt` like followings.
Training result will be stored in the example path. Checkpoints will be stored at `ckpt_path` by default, and training log will be redirected to `./log.txt` like following.
```python
epoch: 1 step: 1251, loss is 5.4833196
@ -175,7 +175,7 @@ You can start training using python or shell scripts. The usage of shell scripts
### Result
Evaluation result will be stored in the example path, you can find result like the followings in `eval.log`.
Evaluation result will be stored in the example path, you can find result like the following in `eval.log`.
```python
metric: {'Loss': 0.9849, 'Top1-Acc':0.7985, 'Top5-Acc':0.9460}

10
model_zoo/official/cv/yolov4/eval.py
View File

@ -115,7 +115,7 @@ class DetectionEngine:
def _nms(self, predicts, threshold):
"""Calculate NMS."""
# conver xywh -> xmin ymin xmax ymax
# convert xywh -> xmin ymin xmax ymax
x1 = predicts[:, 0]
y1 = predicts[:, 1]
x2 = x1 + predicts[:, 2]
@ -139,13 +139,13 @@ class DetectionEngine:
intersect_area = intersect_w * intersect_h
ovr = intersect_area / (areas[i] + areas[order[1:]] - intersect_area)
indexs = np.where(ovr <= threshold)[0]
order = order[indexs + 1]
indexes = np.where(ovr <= threshold)[0]
order = order[indexes + 1]
return reserved_boxes
def _diou_nms(self, dets, thresh=0.5):
"""
conver xywh -> xmin ymin xmax ymax
convert xywh -> xmin ymin xmax ymax
"""
x1 = dets[:, 0]
y1 = dets[:, 1]
@ -248,7 +248,7 @@ class DetectionEngine:
x_top_left = x - w / 2.
y_top_left = y - h / 2.
# creat all False
# create all False
flag = np.random.random(cls_emb.shape) > sys.maxsize
for i in range(flag.shape[0]):
c = cls_argmax[i]

2
model_zoo/official/cv/yolov4/scripts/run_eval.sh
View File

@ -58,7 +58,7 @@ cp ../*.py ./eval
cp -r ../src ./eval
cd ./eval || exit
env > env.log
echo "start infering for device $DEVICE_ID"
echo "start inferring for device $DEVICE_ID"
python eval.py \
--data_dir=$DATASET_PATH \
--pretrained=$CHECKPOINT_PATH \

2
model_zoo/official/cv/yolov4/scripts/run_test.sh
View File

@ -58,7 +58,7 @@ cp ../*.py ./test
cp -r ../src ./test
cd ./test || exit
env > env.log
echo "start infering for device $DEVICE_ID"
echo "start inferring for device $DEVICE_ID"
python test.py \
--data_dir=$DATASET_PATH \
--pretrained=$CHECKPOINT_PATH \

4
model_zoo/official/cv/yolov4/src/yolo.py
View File

@ -59,7 +59,7 @@ class YoloBlock(nn.Cell):
Args:
in_channels: Integer. Input channel.
out_chls: Interger. Middle channel.
out_chls: Integer. Middle channel.
out_channels: Integer. Output channel.
Returns:
@ -111,7 +111,7 @@ class YOLOv4(nn.Cell):
feature_shape: List. Input image shape, [N,C,H,W].
backbone_shape: List. Darknet output channels shape.
backbone: Cell. Backbone Network.
out_channel: Interger. Output channel.
out_channel: Integer. Output channel.
Returns:
Tensor, output tensor.

2
model_zoo/official/cv/yolov4/src/yolo_dataset.py
View File

@ -45,7 +45,7 @@ def has_valid_annotation(anno):
# if all boxes have close to zero area, there is no annotation
if _has_only_empty_bbox(anno):
return False
# keypoints task have a slight different critera for considering
# keypoints task have a slight different criteria for considering
# if an annotation is valid
if "keypoints" not in anno[0]:
return True

6
model_zoo/official/cv/yolov4/test.py
View File

@ -107,7 +107,7 @@ class DetectionEngine():
def _nms(self, dets, thresh):
"""nms function"""
# conver xywh -> xmin ymin xmax ymax
# convert xywh -> xmin ymin xmax ymax
x1 = dets[:, 0]
y1 = dets[:, 1]
x2 = x1 + dets[:, 2]
@ -137,7 +137,7 @@ class DetectionEngine():
def _diou_nms(self, dets, thresh=0.5):
"""conver xywh -> xmin ymin xmax ymax"""
"""convert xywh -> xmin ymin xmax ymax"""
x1 = dets[:, 0]
y1 = dets[:, 1]
x2 = x1 + dets[:, 2]
@ -223,7 +223,7 @@ class DetectionEngine():
x_top_left = x - w / 2.
y_top_left = y - h / 2.
# creat all False
# create all False
flag = np.random.random(cls_emb.shape) > sys.maxsize
for i in range(flag.shape[0]):
c = cls_argmax[i]

4
model_zoo/research/cv/FaceDetection/src/FaceDetection/voc_wrapper.py
View File

@ -70,8 +70,8 @@ def nms(boxes, threshold=0.5):
intersect_area = intersect_w * intersect_h
ovr = intersect_area / (areas[i] + areas[order[1:]] - intersect_area)
indexs = np.where(ovr <= threshold)[0]
order = order[indexs + 1]
indexes = np.where(ovr <= threshold)[0]
order = order[indexes + 1]
return reserved_boxes

2
model_zoo/research/cv/FaceDetection/src/data_to_mindrecord_eval.py
View File

@ -40,7 +40,7 @@ def prepare_file_paths():
image_names = []
for dataset_root in dataset_root_list:
if not os.path.isdir(dataset_root):
raise ValueError("dataset root is unvalid!")
raise ValueError("dataset root is invalid!")
anno_dir = os.path.join(dataset_root, "Annotations")
image_dir = os.path.join(dataset_root, "JPEGImages")
if is_train:

2
model_zoo/research/cv/FaceDetection/src/data_to_mindrecord_train.py
View File

@ -38,7 +38,7 @@ def prepare_file_paths():
anno_files = []
for dataset_root in dataset_root_list:
if not os.path.isdir(dataset_root):
raise ValueError("dataset root is unvalid!")
raise ValueError("dataset root is invalid!")
anno_dir = os.path.join(dataset_root, "Annotations")
image_dir = os.path.join(dataset_root, "JPEGImages")
if is_train:

2
model_zoo/research/cv/FaceDetection/src/data_to_mindrecord_train_append.py
View File

@ -39,7 +39,7 @@ def prepare_file_paths():
anno_files = []
for dataset_root in dataset_root_list:
if not os.path.isdir(dataset_root):
raise ValueError("dataset root is unvalid!")
raise ValueError("dataset root is invalid!")
anno_dir = os.path.join(dataset_root, "Annotations")
image_dir = os.path.join(dataset_root, "JPEGImages")
if is_train:

2
model_zoo/research/cv/FaceRecognition/eval.py
View File

@ -139,7 +139,7 @@ def get_model(args):
load_param_into_net(net, param_dict_new)
args.logger.info('INFO, ------------- load model success--------------')
else:
args.logger.info('ERROR, not supprot file:{}, please check weight in config.py'.format(args.weight))
args.logger.info('ERROR, not support file:{}, please check weight in config.py'.format(args.weight))
return 0
net.set_train(False)
return net