From 4282a43732c4dba597ed5b980891f2cc2b3b0416 Mon Sep 17 00:00:00 2001 From: gengdongjie Date: Sun, 7 Feb 2021 10:44:54 +0800 Subject: [PATCH] fix typos in maskrcnn and fastercnn --- model_zoo/official/cv/faster_rcnn/README.md | 8 +++++--- model_zoo/official/cv/faster_rcnn/README_CN.md | 2 ++ .../cv/faster_rcnn/ascend310_infer/src/DvppCommon.cpp | 4 ++-- .../official/cv/faster_rcnn/src/FasterRcnn/roi_align.py | 4 ++-- model_zoo/official/cv/maskrcnn/README.md | 6 ++++-- model_zoo/official/cv/maskrcnn/README_CN.md | 2 ++ .../cv/maskrcnn/ascend310_infer/src/DvppCommon.cpp | 4 ++-- .../cv/maskrcnn/src/maskrcnn/bbox_assign_sample.py | 2 +- model_zoo/official/cv/maskrcnn/src/maskrcnn/roi_align.py | 4 ++-- model_zoo/official/cv/maskrcnn_mobilenetv1/README.md | 8 ++++---- .../src/maskrcnn_mobilenetv1/bbox_assign_sample.py | 2 +- .../src/maskrcnn_mobilenetv1/bbox_assign_sample_stage2.py | 2 +- .../src/maskrcnn_mobilenetv1/roi_align.py | 4 ++-- 13 files changed, 30 insertions(+), 22 deletions(-) diff --git a/model_zoo/official/cv/faster_rcnn/README.md b/model_zoo/official/cv/faster_rcnn/README.md index 44f670893f9..c4cfa5d01cb 100644 --- a/model_zoo/official/cv/faster_rcnn/README.md +++ b/model_zoo/official/cv/faster_rcnn/README.md @@ -90,7 +90,7 @@ Dataset used: [COCO2017]() train2017/0000001.jpg 0,259,401,459,7 35,28,324,201,2 0,30,59,80,2 ``` - Each row is an image annotation which split by space, the first column is a relative path of image, the others are box and class infomations of the format [xmin,ymin,xmax,ymax,class]. We read image from an image path joined by the `IMAGE_DIR`(dataset directory) and the relative path in `ANNO_PATH`(the TXT file path), `IMAGE_DIR` and `ANNO_PATH` are setting in `config.py`. + Each row is an image annotation which split by space, the first column is a relative path of image, the others are box and class information of the format [xmin,ymin,xmax,ymax,class]. We read image from an image path joined by the `IMAGE_DIR`(dataset directory) and the relative path in `ANNO_PATH`(the TXT file path), `IMAGE_DIR` and `ANNO_PATH` are setting in `config.py`. # Quick Start @@ -242,7 +242,7 @@ Notes: ### Result -Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". You can find checkpoint file together with result like the followings in loss_rankid.log. +Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". You can find checkpoint file together with result like the following in loss_rankid.log. ```log # distribute training result(8p) @@ -265,10 +265,12 @@ sh run_eval_ascend.sh [VALIDATION_JSON_FILE] [CHECKPOINT_PATH] ``` > checkpoint can be produced in training process. +> +> Images size in dataset should be equal to the annotation size in VALIDATION_JSON_FILE, otherwise the evaluation result cannot be displayed properly. ### Result -Eval result will be stored in the example path, whose folder name is "eval". Under this, you can find result like the followings in log. +Eval result will be stored in the example path, whose folder name is "eval". Under this, you can find result like the following in log. ```log Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.360 diff --git a/model_zoo/official/cv/faster_rcnn/README_CN.md b/model_zoo/official/cv/faster_rcnn/README_CN.md index 79f3a268c73..9e79ed46549 100644 --- a/model_zoo/official/cv/faster_rcnn/README_CN.md +++ b/model_zoo/official/cv/faster_rcnn/README_CN.md @@ -268,6 +268,8 @@ sh run_eval_ascend.sh [VALIDATION_JSON_FILE] [CHECKPOINT_PATH] ``` > 在训练过程中生成检查点。 +> +> 数据集中图片的数量要和VALIDATION_JSON_FILE文件中标记数量一致，否则精度结果展示格式可能出现异常。 ### 结果 diff --git a/model_zoo/official/cv/faster_rcnn/ascend310_infer/src/DvppCommon.cpp b/model_zoo/official/cv/faster_rcnn/ascend310_infer/src/DvppCommon.cpp index 26698bfb8c6..71f443238e4 100755 --- a/model_zoo/official/cv/faster_rcnn/ascend310_infer/src/DvppCommon.cpp +++ b/model_zoo/official/cv/faster_rcnn/ascend310_infer/src/DvppCommon.cpp @@ -59,7 +59,7 @@ int DvppCommon::DeInit(void) { ret = acldvppDestroyChannel(dvppChannelDesc_); if (ret != OK) { - std::cout << "Failed to destory dvpp channel, ret = " << ret << "." << std::endl; + std::cout << "Failed to destroy dvpp channel, ret = " << ret << "." << std::endl; return ret; } @@ -646,7 +646,7 @@ int DvppCommon::CombineJpegdProcess(const RawData& imageInfo, acldvppPixelFormat return ret; } - // In TransferImageH2D function, device buffer will be alloced to store the input image + // In TransferImageH2D function, device buffer will be allocated to store the input image // Need to pay attention to release of the buffer ret = TransferImageH2D(imageInfo, inputImage_); if (ret != OK) { diff --git a/model_zoo/official/cv/faster_rcnn/src/FasterRcnn/roi_align.py b/model_zoo/official/cv/faster_rcnn/src/FasterRcnn/roi_align.py index 8cc727b50cc..f099de0e867 100644 --- a/model_zoo/official/cv/faster_rcnn/src/FasterRcnn/roi_align.py +++ b/model_zoo/official/cv/faster_rcnn/src/FasterRcnn/roi_align.py @@ -24,7 +24,7 @@ from mindspore.common.tensor import Tensor class ROIAlign(nn.Cell): """ - Extract RoI features from mulitple feature map. + Extract RoI features from multiple feature map. Args: out_size_h (int) - RoI height. @@ -59,7 +59,7 @@ class SingleRoIExtractor(nn.Cell): """ Extract RoI features from a single level feature map. - If there are mulitple input feature levels, each RoI is mapped to a level + If there are multiple input feature levels, each RoI is mapped to a level according to its scale. Args: diff --git a/model_zoo/official/cv/maskrcnn/README.md b/model_zoo/official/cv/maskrcnn/README.md index d09a30e82ed..aef4277d6be 100644 --- a/model_zoo/official/cv/maskrcnn/README.md +++ b/model_zoo/official/cv/maskrcnn/README.md @@ -431,7 +431,7 @@ bash run_distribute_train.sh [RANK_TABLE_FILE] [PRETRAINED_MODEL] ### [Training Result](#content) -Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". You can find checkpoint file together with result like the followings in loss_rankid.log. +Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". You can find checkpoint file together with result like the following in loss_rankid.log. ```bash # distribute training result(8p) @@ -457,10 +457,12 @@ bash run_eval.sh [VALIDATION_ANN_FILE_JSON] [CHECKPOINT_PATH] > As for the COCO2017 dataset, VALIDATION_ANN_FILE_JSON is refer to the annotations/instances_val2017.json in the dataset directory. > checkpoint can be produced and saved in training process, whose folder name begins with "train/checkpoint" or "train_parallel*/checkpoint". +> +> Images size in dataset should be equal to the annotation size in VALIDATION_ANN_FILE_JSON, otherwise the evaluation result cannot be displayed properly. ### [Evaluation result](#content) -Inference result will be stored in the example path, whose folder name is "eval". Under this, you can find result like the followings in log. +Inference result will be stored in the example path, whose folder name is "eval". Under this, you can find result like the following in log. ```bash Evaluate annotation type *bbox* diff --git a/model_zoo/official/cv/maskrcnn/README_CN.md b/model_zoo/official/cv/maskrcnn/README_CN.md index 38f6198c17f..0065d2a3a4f 100644 --- a/model_zoo/official/cv/maskrcnn/README_CN.md +++ b/model_zoo/official/cv/maskrcnn/README_CN.md @@ -455,6 +455,8 @@ sh run_eval.sh [VALIDATION_ANN_FILE_JSON] [CHECKPOINT_PATH] > 关于COCO2017数据集，VALIDATION_ANN_FILE_JSON参考数据集目录下的annotations/instances_val2017.json文件。 > 检查点可在训练过程中生成并保存，其文件夹名称以“train/checkpoint”或“train_parallel*/checkpoint”开头。 +> +> 数据集中图片的数量要和VALIDATION_ANN_FILE_JSON文件中标记数量一致，否则精度结果展示格式可能出现异常。 ### 评估结果 diff --git a/model_zoo/official/cv/maskrcnn/ascend310_infer/src/DvppCommon.cpp b/model_zoo/official/cv/maskrcnn/ascend310_infer/src/DvppCommon.cpp index 26698bfb8c6..71f443238e4 100755 --- a/model_zoo/official/cv/maskrcnn/ascend310_infer/src/DvppCommon.cpp +++ b/model_zoo/official/cv/maskrcnn/ascend310_infer/src/DvppCommon.cpp @@ -59,7 +59,7 @@ int DvppCommon::DeInit(void) { ret = acldvppDestroyChannel(dvppChannelDesc_); if (ret != OK) { - std::cout << "Failed to destory dvpp channel, ret = " << ret << "." << std::endl; + std::cout << "Failed to destroy dvpp channel, ret = " << ret << "." << std::endl; return ret; } @@ -646,7 +646,7 @@ int DvppCommon::CombineJpegdProcess(const RawData& imageInfo, acldvppPixelFormat return ret; } - // In TransferImageH2D function, device buffer will be alloced to store the input image + // In TransferImageH2D function, device buffer will be allocated to store the input image // Need to pay attention to release of the buffer ret = TransferImageH2D(imageInfo, inputImage_); if (ret != OK) { diff --git a/model_zoo/official/cv/maskrcnn/src/maskrcnn/bbox_assign_sample.py b/model_zoo/official/cv/maskrcnn/src/maskrcnn/bbox_assign_sample.py index a282b732bbf..537792c79da 100644 --- a/model_zoo/official/cv/maskrcnn/src/maskrcnn/bbox_assign_sample.py +++ b/model_zoo/official/cv/maskrcnn/src/maskrcnn/bbox_assign_sample.py @@ -23,7 +23,7 @@ import mindspore.common.dtype as mstype class BboxAssignSample(nn.Cell): """ - Bbox assigner and sampler defination. + Bbox assigner and sampler definition. Args: config (dict): Config. diff --git a/model_zoo/official/cv/maskrcnn/src/maskrcnn/roi_align.py b/model_zoo/official/cv/maskrcnn/src/maskrcnn/roi_align.py index 1f82e774bf3..b8b27ff3298 100644 --- a/model_zoo/official/cv/maskrcnn/src/maskrcnn/roi_align.py +++ b/model_zoo/official/cv/maskrcnn/src/maskrcnn/roi_align.py @@ -24,7 +24,7 @@ from mindspore.common.tensor import Tensor class ROIAlign(nn.Cell): """ - Extract RoI features from mulitple feature map. + Extract RoI features from mulitiple feature map. Args: out_size_h (int) - RoI height. @@ -61,7 +61,7 @@ class SingleRoIExtractor(nn.Cell): """ Extract RoI features from a single level feature map. - If there are mulitple input feature levels, each RoI is mapped to a level + If there are multiple input feature levels, each RoI is mapped to a level according to its scale. Args: diff --git a/model_zoo/official/cv/maskrcnn_mobilenetv1/README.md b/model_zoo/official/cv/maskrcnn_mobilenetv1/README.md index d6a9db1c2cb..0be61ab07ec 100644 --- a/model_zoo/official/cv/maskrcnn_mobilenetv1/README.md +++ b/model_zoo/official/cv/maskrcnn_mobilenetv1/README.md @@ -208,7 +208,7 @@ Usage: sh run_standalone_train.sh [PRETRAINED_MODEL] "neg_iou_thr": 0.3, # negative sample threshold after IOU "pos_iou_thr": 0.7, # positive sample threshold after IOU "min_pos_iou": 0.3, # minimal positive sample threshold after IOU -"num_bboxes": 245520, # total bbox numner +"num_bboxes": 245520, # total bbox number "num_gts": 128, # total ground truth number "num_expected_neg": 256, # negative sample number "num_expected_pos": 128, # positive sample number @@ -220,7 +220,7 @@ Usage: sh run_standalone_train.sh [PRETRAINED_MODEL] # roi_alignj "roi_layer": dict(type='RoIAlign', out_size=7, mask_out_size=14, sample_num=2), # ROIAlign parameters "roi_align_out_channels": 256, # ROIAlign out channels size -"roi_align_featmap_strides": [4, 8, 16, 32], # stride size for differnt level of ROIAling feature map +"roi_align_featmap_strides": [4, 8, 16, 32], # stride size for different level of ROIAling feature map "roi_align_finest_scale": 56, # finest scale ofr ROIAlign "roi_sample_num": 640, # sample number in ROIAling layer @@ -338,7 +338,7 @@ sh run_distribute_train.sh [RANK_TABLE_FILE] [PRETRAINED_MODEL] ### [Training Result](#content) -Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". You can find checkpoint file together with result like the followings in loss_rankid.log. +Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". You can find checkpoint file together with result like the following in loss_rankid.log. ```bash # distribute training result(8p) @@ -369,7 +369,7 @@ sh run_eval.sh [VALIDATION_ANN_FILE_JSON] [CHECKPOINT_PATH] ### [Evaluation result](#content) -Inference result will be stored in the example path, whose folder name is "eval". Under this, you can find result like the followings in log. +Inference result will be stored in the example path, whose folder name is "eval". Under this, you can find result like the following in log. ```bash Evaluate annotation type *bbox* diff --git a/model_zoo/official/cv/maskrcnn_mobilenetv1/src/maskrcnn_mobilenetv1/bbox_assign_sample.py b/model_zoo/official/cv/maskrcnn_mobilenetv1/src/maskrcnn_mobilenetv1/bbox_assign_sample.py index a282b732bbf..537792c79da 100644 --- a/model_zoo/official/cv/maskrcnn_mobilenetv1/src/maskrcnn_mobilenetv1/bbox_assign_sample.py +++ b/model_zoo/official/cv/maskrcnn_mobilenetv1/src/maskrcnn_mobilenetv1/bbox_assign_sample.py @@ -23,7 +23,7 @@ import mindspore.common.dtype as mstype class BboxAssignSample(nn.Cell): """ - Bbox assigner and sampler defination. + Bbox assigner and sampler definition. Args: config (dict): Config. diff --git a/model_zoo/official/cv/maskrcnn_mobilenetv1/src/maskrcnn_mobilenetv1/bbox_assign_sample_stage2.py b/model_zoo/official/cv/maskrcnn_mobilenetv1/src/maskrcnn_mobilenetv1/bbox_assign_sample_stage2.py index 822759e80c6..8165fffa1d0 100644 --- a/model_zoo/official/cv/maskrcnn_mobilenetv1/src/maskrcnn_mobilenetv1/bbox_assign_sample_stage2.py +++ b/model_zoo/official/cv/maskrcnn_mobilenetv1/src/maskrcnn_mobilenetv1/bbox_assign_sample_stage2.py @@ -22,7 +22,7 @@ from mindspore.common.tensor import Tensor class BboxAssignSampleForRcnn(nn.Cell): """ - Bbox assigner and sampler defination. + Bbox assigner and sampler definition. Args: config (dict): Config. diff --git a/model_zoo/official/cv/maskrcnn_mobilenetv1/src/maskrcnn_mobilenetv1/roi_align.py b/model_zoo/official/cv/maskrcnn_mobilenetv1/src/maskrcnn_mobilenetv1/roi_align.py index 1f82e774bf3..60bdeb658b7 100644 --- a/model_zoo/official/cv/maskrcnn_mobilenetv1/src/maskrcnn_mobilenetv1/roi_align.py +++ b/model_zoo/official/cv/maskrcnn_mobilenetv1/src/maskrcnn_mobilenetv1/roi_align.py @@ -24,7 +24,7 @@ from mindspore.common.tensor import Tensor class ROIAlign(nn.Cell): """ - Extract RoI features from mulitple feature map. + Extract RoI features from multiple feature map. Args: out_size_h (int) - RoI height. @@ -61,7 +61,7 @@ class SingleRoIExtractor(nn.Cell): """ Extract RoI features from a single level feature map. - If there are mulitple input feature levels, each RoI is mapped to a level + If there are multiple input feature levels, each RoI is mapped to a level according to its scale. Args: