m53297601
/
mindspore
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

!13892 removed the useless link of apply form

Browse Source 
From: @oacjiewen
Reviewed-by: @c_34,@liangchenghui
Signed-off-by: @c_34
pull/13892/MERGE
mindspore-ci-bot 4 years ago committed by Gitee
parent bca26cf68e da60f433f1
commit d2b0daeb74
104 changed files with 273 additions and 274 deletions
Show Stats Download Patch File Download Diff File

2
model_zoo/official/cv/FCN8s/README.md
Unescape View File

@ -41,7 +41,7 @@ Dataset used:
# [环境要求](#contents)
- 硬件（Ascend/GPU）
- 需要准备具有Ascend或GPU处理能力的硬件环境. 如需使用Ascend，可以发送 [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) 到ascend@huawei.com。一旦批准，你就可以使用此资源
- 需要准备具有Ascend或GPU处理能力的硬件环境.
- 框架
- [MindSpore](https://www.mindspore.cn/install/en)
- 如需获取更多信息，请查看如下链接：

130
model_zoo/official/cv/centerface/README.md
Unescape View File

@ -82,7 +82,7 @@ other datasets need to use the same format as WiderFace.
# [Environment Requirements](#contents)
- Hardware（Ascend）
- Prepare hardware environment with Ascend processor. If you want to try Ascend, please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend processor.
- Framework
- [MindSpore](https://www.mindspore.cn/install/en)
- For more information, please check the resources below：
@ -229,53 +229,53 @@ sh eval_all.sh
1. train scripts parameters
the command is: python train.py [train parameters]
Major parameters train.py as follows:
```text
--lr: learning rate
--per_batch_size: batch size on each device
--is_distributed: multi-device or not
--t_max: for cosine lr_scheduler
--max_epoch: training epochs
--warmup_epochs: warmup_epochs, not needed for adam, needed for sgd
--lr scheduler: learning rate scheduler, default is multistep
--lr_epochs: decrease lr steps
--lr_gamma: decrease lr by a factor
--weight_decay: weight decay
--loss_scale: mix precision training
--pretrained_backbone: pretrained mobilenet_v2 model path
--data_dir: data dir
--annot_path: annotations path
--img_dir: img dir in data_dir
```
the command is: python train.py [train parameters]
Major parameters train.py as follows:
```text
--lr: learning rate
--per_batch_size: batch size on each device
--is_distributed: multi-device or not
--t_max: for cosine lr_scheduler
--max_epoch: training epochs
--warmup_epochs: warmup_epochs, not needed for adam, needed for sgd
--lr scheduler: learning rate scheduler, default is multistep
--lr_epochs: decrease lr steps
--lr_gamma: decrease lr by a factor
--weight_decay: weight decay
--loss_scale: mix precision training
--pretrained_backbone: pretrained mobilenet_v2 model path
--data_dir: data dir
--annot_path: annotations path
--img_dir: img dir in data_dir
```
2. centerface unique configs: in config.py; not recommend user to change
3. test scripts parameters:
the command is: python test.py [test parameters]
Major parameters test.py as follows:
```python
test_script_path: test.py path;
--is_distributed: multi-device or not
--data_dir: img dir
--test_model: test model dir
--ground_truth_mat: ground_truth file, mat type
--save_dir: save_path for evaluate
--rank: use device id
--ckpt_name: test model name
# blow are used for calculate ckpt/model name
# model/ckpt name is "0-" + str(ckpt_num) + "_" + str(steps_per_epoch*ckpt_num) + ".ckpt";
# ckpt_num is epoch number, can be calculated by device_num
# detail can be found in "test.py"
# if ckpt is specified not need below 4 parameter
--device_num: training device number
--steps_per_epoch: steps for each epoch
--start: start loop number, used to calculate first epoch number
--end: end loop number, used to calculate last epoch number
```
the command is: python test.py [test parameters]
Major parameters test.py as follows:
```python
test_script_path: test.py path;
--is_distributed: multi-device or not
--data_dir: img dir
--test_model: test model dir
--ground_truth_mat: ground_truth file, mat type
--save_dir: save_path for evaluate
--rank: use device id
--ckpt_name: test model name
# blow are used for calculate ckpt/model name
# model/ckpt name is "0-" + str(ckpt_num) + "_" + str(steps_per_epoch*ckpt_num) + ".ckpt";
# ckpt_num is epoch number, can be calculated by device_num
# detail can be found in "test.py"
# if ckpt is specified not need below 4 parameter
--device_num: training device number
--steps_per_epoch: steps for each epoch
--start: start loop number, used to calculate first epoch number
--end: end loop number, used to calculate last epoch number
```
4. eval scripts parameters:
@ -384,18 +384,18 @@ mkdir [SAVE_PATH]
1. test a single ckpt file
```python
# you need to change the parameter in test.sh
# or use symbolic link as quick start
# or use the command as follow:
# MODEL_PATH: ckpt path saved during training
# DATASET: img dir
# GROUND_TRUTH_MAT: ground_truth file, mat type
# SAVE_PATH: save_path for evaluate
# DEVICE_ID: use device id
# CKPT: test model name
sh test.sh [MODEL_PATH] [DATASET] [GROUND_TRUTH_MAT] [SAVE_PATH] [DEVICE_ID] [CKPT]
```
```python
# you need to change the parameter in test.sh
# or use symbolic link as quick start
# or use the command as follow:
# MODEL_PATH: ckpt path saved during training
# DATASET: img dir
# GROUND_TRUTH_MAT: ground_truth file, mat type
# SAVE_PATH: save_path for evaluate
# DEVICE_ID: use device id
# CKPT: test model name
sh test.sh [MODEL_PATH] [DATASET] [GROUND_TRUTH_MAT] [SAVE_PATH] [DEVICE_ID] [CKPT]
```
2. test many out ckpt for user to choose the best one
@ -433,19 +433,19 @@ cd ../../../scripts;
1. eval a single testing output
```python
# you need to change the parameter in eval.sh
# default eval the ckpt saved in ./scripts/output/centerface/999
sh eval.sh
```
```python
# you need to change the parameter in eval.sh
# default eval the ckpt saved in ./scripts/output/centerface/999
sh eval.sh
```
2. eval many testing output for user to choose the best one
```python
# you need to change the parameter in eval_all.sh
# default eval the ckpt saved in ./scripts/output/centerface/[89-140]
sh eval_all.sh
```
```python
# you need to change the parameter in eval_all.sh
# default eval the ckpt saved in ./scripts/output/centerface/[89-140]
sh eval_all.sh
```
3. test+eval

2
model_zoo/official/cv/cnnctc/README.md
Unescape View File

@ -96,7 +96,7 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
- Hardware（Ascend）
- Prepare hardware environment with Ascend processor. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend processor.
- Framework
- [MindSpore](https://www.mindspore.cn/install/en)

2
model_zoo/official/cv/crnn/README.md
Unescape View File

@ -58,7 +58,7 @@ We provide `convert_ic03.py`, `convert_iiit5k.py`, `convert_svt.py` as exmples f
## [Environment Requirements](#contents)
- Hardware（Ascend）
- Prepare hardware environment with Ascend processor. If you want to try Ascend, please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. You will be able to have access to related resources once approved.
- Prepare hardware environment with Ascend processor.
- Framework
- [MindSpore](https://gitee.com/mindspore/mindspore)
- For more information, please check the resources below：

2
model_zoo/official/cv/crnn_seq2seq_ocr/README.md
Unescape View File

@ -38,7 +38,7 @@ For training and evaluation, we use the French Street Name Signs (FSNS) released
## [Environment Requirements](#contents)
- Hardware（Ascend）
- Prepare hardware environment with Ascend processor. If you want to try Ascend, please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. You will be able to have access to related resources once approved.
- Prepare hardware environment with Ascend processor.
- Framework
- [MindSpore](https://gitee.com/mindspore/mindspore)
- For more information, please check the resources below：

8
model_zoo/official/cv/ctpn/README.md
Unescape View File

@ -1,9 +1,9 @@
![](https://www.mindspore.cn/static/img/logo_black.6a5c850d.png)
<!-- TOC -->
![logo](https://www.mindspore.cn/static/img/logo_black.6a5c850d.png)
# CTPN for Ascend
<!-- TOC -->
- [CTPN Description](#CTPN-description)
- [Model Architecture](#model-architecture)
- [Dataset](#dataset)
@ -57,7 +57,7 @@ Here we used 6 datasets for training, and 1 datasets for Evaluation.
# [Environment Requirements](#contents)
- Hardware（Ascend）
- Prepare hardware environment with Ascend processor. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend processor.
- Framework
- [MindSpore](https://www.mindspore.cn/install/en)
- For more information, please check the resources below：

158
model_zoo/official/cv/deeplabv3/README.md
Unescape View File

@ -74,7 +74,7 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
# [Environment Requirements](#contents)
- Hardware（Ascend）
- Prepare hardware environment with Ascend. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend.
- Framework
- [MindSpore](https://www.mindspore.cn/install/en)
- For more information, please check the resources below：
@ -83,7 +83,7 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
- Install python packages in requirements.txt
- Generate config json file for 8pcs training
```
```bash
# From the root of this project
cd src/tools/
python3 get_multicards_json.py 10.111.*.*
@ -108,47 +108,47 @@ For 8 devices training, training steps are as follows:
1. Train s16 with vocaug dataset, finetuning from resnet101 pretrained model, script is:
```shell
run_distribute_train_s16_r1.sh
```
```shell
run_distribute_train_s16_r1.sh
```
2. Train s8 with vocaug dataset, finetuning from model in previous step, training script is:
```shell
run_distribute_train_s8_r1.sh
```
```shell
run_distribute_train_s8_r1.sh
```
3. Train s8 with voctrain dataset, finetuning from model in previous step, training script is:
```shell
run_distribute_train_s8_r2.sh
```
```shell
run_distribute_train_s8_r2.sh
```
For evaluation, evaluating steps are as follows:
1. Eval s16 with voc val dataset, eval script is:
```shell
run_eval_s16.sh
```
```shell
run_eval_s16.sh
```
2. Eval s8 with voc val dataset, eval script is:
```shell
run_eval_s8.sh
```
```shell
run_eval_s8.sh
```
3. Eval s8 multiscale with voc val dataset, eval script is:
```shell
run_eval_s8_multiscale.sh
```
```shell
run_eval_s8_multiscale.sh
```
4. Eval s8 multiscale and flip with voc val dataset, eval script is:
```shell
run_eval_s8_multiscale_flip.sh
```
```shell
run_eval_s8_multiscale_flip.sh
```
# [Script Description](#contents)
@ -245,64 +245,64 @@ For 8 devices training, training steps are as follows:
1. Train s16 with vocaug dataset, finetuning from resnet101 pretrained model, script is as follows:
```shell
# run_distribute_train_s16_r1.sh
for((i=0;i<=$RANK_SIZE-1;i++));
do
export RANK_ID=${i}
export DEVICE_ID=$((i + RANK_START_ID))
echo 'start rank='${i}', device id='${DEVICE_ID}'...'
mkdir ${train_path}/device${DEVICE_ID}
cd ${train_path}/device${DEVICE_ID} || exit
python ${train_code_path}/train.py --train_dir=${train_path}/ckpt \
--data_file=/PATH/TO/MINDRECORD_NAME \
--train_epochs=300 \
--batch_size=32 \
--crop_size=513 \
--base_lr=0.08 \
--lr_type=cos \
--min_scale=0.5 \
--max_scale=2.0 \
--ignore_label=255 \
--num_classes=21 \
--model=deeplab_v3_s16 \
--ckpt_pre_trained=/PATH/TO/PRETRAIN_MODEL \
--is_distributed \
--save_steps=410 \
--keep_checkpoint_max=200 >log 2>&1 &
done
```
```shell
# run_distribute_train_s16_r1.sh
for((i=0;i<=$RANK_SIZE-1;i++));
do
export RANK_ID=${i}
export DEVICE_ID=$((i + RANK_START_ID))
echo 'start rank='${i}', device id='${DEVICE_ID}'...'
mkdir ${train_path}/device${DEVICE_ID}
cd ${train_path}/device${DEVICE_ID} || exit
python ${train_code_path}/train.py --train_dir=${train_path}/ckpt \
--data_file=/PATH/TO/MINDRECORD_NAME \
--train_epochs=300 \
--batch_size=32 \
--crop_size=513 \
--base_lr=0.08 \
--lr_type=cos \
--min_scale=0.5 \
--max_scale=2.0 \
--ignore_label=255 \
--num_classes=21 \
--model=deeplab_v3_s16 \
--ckpt_pre_trained=/PATH/TO/PRETRAIN_MODEL \
--is_distributed \
--save_steps=410 \
--keep_checkpoint_max=200 >log 2>&1 &
done
```
2. Train s8 with vocaug dataset, finetuning from model in previous step, training script is as follows:
```shell
# run_distribute_train_s8_r1.sh
for((i=0;i<=$RANK_SIZE-1;i++));
do
export RANK_ID=${i}
export DEVICE_ID=$((i + RANK_START_ID))
echo 'start rank='${i}', device id='${DEVICE_ID}'...'
mkdir ${train_path}/device${DEVICE_ID}
cd ${train_path}/device${DEVICE_ID} || exit
python ${train_code_path}/train.py --train_dir=${train_path}/ckpt \
--data_file=/PATH/TO/MINDRECORD_NAME \
--train_epochs=800 \
--batch_size=16 \
--crop_size=513 \
--base_lr=0.02 \
--lr_type=cos \
--min_scale=0.5 \
--max_scale=2.0 \
--ignore_label=255 \
--num_classes=21 \
--model=deeplab_v3_s8 \
--loss_scale=2048 \
--ckpt_pre_trained=/PATH/TO/PRETRAIN_MODEL \
--is_distributed \
--save_steps=820 \
--keep_checkpoint_max=200 >log 2>&1 &
done
```
```shell
# run_distribute_train_s8_r1.sh
for((i=0;i<=$RANK_SIZE-1;i++));
do
export RANK_ID=${i}
export DEVICE_ID=$((i + RANK_START_ID))
echo 'start rank='${i}', device id='${DEVICE_ID}'...'
mkdir ${train_path}/device${DEVICE_ID}
cd ${train_path}/device${DEVICE_ID} || exit
python ${train_code_path}/train.py --train_dir=${train_path}/ckpt \
--data_file=/PATH/TO/MINDRECORD_NAME \
--train_epochs=800 \
--batch_size=16 \
--crop_size=513 \
--base_lr=0.02 \
--lr_type=cos \
--min_scale=0.5 \
--max_scale=2.0 \
--ignore_label=255 \
--num_classes=21 \
--model=deeplab_v3_s8 \
--loss_scale=2048 \
--ckpt_pre_trained=/PATH/TO/PRETRAIN_MODEL \
--is_distributed \
--save_steps=820 \
--keep_checkpoint_max=200 >log 2>&1 &
done
```
3. Train s8 with voctrain dataset, finetuning from model in previous step, training script is as follows:
@ -566,4 +566,4 @@ In dataset.py, we set the seed inside "create_dataset" function. We also use ran
# [ModelZoo Homepage](#contents)
Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/master/model_zoo).
Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/master/model_zoo).

48
model_zoo/official/cv/deeplabv3/README_CN.md
Unescape View File

@ -71,7 +71,7 @@ Pascal VOC数据集和语义边界数据集（Semantic Boundaries Dataset，SBD
- 配置并运行build_data.sh，将数据集转换为MindRecords。scripts/build_data.sh中的参数：
```
```bash
--data_root 训练数据的根路径
--data_lst 训练数据列表（如上准备）
--dst_path MindRecord所在路径
@ -89,7 +89,7 @@ Pascal VOC数据集和语义边界数据集（Semantic Boundaries Dataset，SBD
# 环境要求
- 硬件（Ascend）
- 准备Ascend处理器搭建硬件环境。如需试用Ascend处理器，请发送[申请表](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx)至ascend@huawei.com，审核通过即可获得资源。
- 准备Ascend处理器搭建硬件环境。
- 框架
- [MindSpore](https://www.mindspore.cn/install)
- 如需查看详情，请参见如下资源：
@ -98,7 +98,7 @@ Pascal VOC数据集和语义边界数据集（Semantic Boundaries Dataset，SBD
- 安装requirements.txt中的python包。
- 生成config json文件用于8卡训练。
```
```bash
# 从项目根目录进入
cd src/tools/
python3 get_multicards_json.py 10.111.*.*
@ -123,47 +123,47 @@ run_standalone_train.sh
1. 使用VOCaug数据集训练s16，微调ResNet-101预训练模型。脚本如下：
```bash
run_distribute_train_s16_r1.sh
```
```bash
run_distribute_train_s16_r1.sh
```
2. 使用VOCaug数据集训练s8，微调上一步的模型。脚本如下：
```bash
run_distribute_train_s8_r1.sh
```
```bash
run_distribute_train_s8_r1.sh
```
3. 使用VOCtrain数据集训练s8，微调上一步的模型。脚本如下：
```bash
run_distribute_train_s8_r2.sh
```
```bash
run_distribute_train_s8_r2.sh
```
评估步骤如下：
1. 使用voc val数据集评估s16。评估脚本如下：
```bash
run_eval_s16.sh
```
```bash
run_eval_s16.sh
```
2. 使用voc val数据集评估s8。评估脚本如下：
```bash
run_eval_s8.sh
```
```bash
run_eval_s8.sh
```
3. 使用voc val数据集评估多尺度s8。评估脚本如下：
```bash
run_eval_s8_multiscale.sh
```
```bash
run_eval_s8_multiscale.sh
```
4. 使用voc val数据集评估多尺度和翻转s8。评估脚本如下：
```bash
run_eval_s8_multiscale_flip.sh
```
```bash
run_eval_s8_multiscale_flip.sh
```
# 脚本说明

2
model_zoo/official/cv/deeptext/README.md
Unescape View File

@ -49,7 +49,7 @@ Here we used 4 datasets for training, and 1 datasets for Evaluation.
# [Environment Requirements](#contents)
- Hardware（Ascend）
- Prepare hardware environment with Ascend processor. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend processor.
- Framework
- [MindSpore](https://www.mindspore.cn/install/en)
- For more information, please check the resources below：

2
model_zoo/official/cv/densenet/README.md
Unescape View File

@ -78,7 +78,7 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
# [Environment Requirements](#contents)
- Hardware（Ascend/GPU）
- Prepare hardware environment with Ascend or GPU processor. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend or GPU processor.
- Framework
- [MindSpore](https://www.mindspore.cn/install/en)
- For more information, please check the resources below：

2
model_zoo/official/cv/densenet/README_CN.md
Unescape View File

@ -82,7 +82,7 @@ DenseNet-100使用的数据集： Cifar-10
# 环境要求
- 硬件（Ascend/GPU）
- 准备Ascend或GPU处理器搭建硬件环境。如需试用昇腾处理器，请发送[申请表](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx)至ascend@huawei.com，审核通过即可获得资源。
- 准备Ascend或GPU处理器搭建硬件环境。
- 框架
- [MindSpore](https://www.mindspore.cn/install)
- 如需查看详情，请参见如下资源：

2
model_zoo/official/cv/dpn/README.md
Unescape View File

@ -70,7 +70,7 @@ The [mixed precision](https://www.mindspore.cn/tutorial/training/en/master/advan
To run the python scripts in the repository, you need to prepare the environment as follow:
- Hardware
- Prepare hardware environment with Ascend or GPU processor. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to [ascend@huawei.com](mailto:ascend@huawei.com). Once approved, you can get the resources.
- Prepare hardware environment with Ascend or GPU processor.
- Python and dependencies
- Python3.7
- Mindspore 1.1.0

2
model_zoo/official/cv/faster_rcnn/README.md
Unescape View File

@ -48,7 +48,7 @@ Dataset used: [COCO2017](<https://cocodataset.org/>)
# Environment Requirements
- Hardware（Ascend/GPU）
- Prepare hardware environment with Ascend processor. If you want to try Ascend, please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend processor.
- Docker base image
- [Ascend Hub](ascend.huawei.com/ascendhub/#/home)

2
model_zoo/official/cv/faster_rcnn/README_CN.md
Unescape View File

@ -49,7 +49,7 @@ Faster R-CNN是一个两阶段目标检测网络，该网络采用RPN，可以
# 环境要求
- 硬件（Ascend/GPU）
- 使用Ascend处理器来搭建硬件环境。如需试用Ascend处理器，请发送[申请表](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx)至ascend@huawei.com，审核通过即可获得资源。
- 使用Ascend处理器来搭建硬件环境。
- 获取基础镜像
- [Ascend Hub](https://ascend.huawei.com/ascendhub/#/home)

2
model_zoo/official/cv/googlenet/README.md
Unescape View File

@ -68,7 +68,7 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
# [Environment Requirements](#contents)
- Hardware（Ascend/GPU）
- Prepare hardware environment with Ascend or GPU processor. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend or GPU processor.
- Framework
- [MindSpore](https://www.mindspore.cn/install/en)
- For more information, please check the resources below：

2
model_zoo/official/cv/googlenet/README_CN.md
Unescape View File

@ -75,7 +75,7 @@ GoogleNet由多个inception模块串联起来，可以更加深入。 降维的
# 环境要求
- 硬件（Ascend/GPU）
- 使用Ascend或GPU处理器来搭建硬件环境。如需试用Ascend处理器，请发送[申请表](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx)至ascend@huawei.com，审核通过即可获得资源。
- 使用Ascend或GPU处理器来搭建硬件环境。
- 框架
- [MindSpore](https://www.mindspore.cn/install/en)
- 如需查看详情，请参见如下资源：

2
model_zoo/official/cv/inceptionv3/README.md
Unescape View File

@ -59,7 +59,7 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
# [Environment Requirements](#contents)
- Hardware（Ascend）
- Prepare hardware environment with Ascend processor. If you want to try Ascend, please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend processor.
- Framework
- [MindSpore](https://www.mindspore.cn/install/en)
- For more information, please check the resources below：

2
model_zoo/official/cv/inceptionv3/README_CN.md
Unescape View File

@ -70,7 +70,7 @@ InceptionV3的总体网络架构如下：
# 环境要求
- 硬件（Ascend）
- 使用Ascend来搭建硬件环境。如需试用Ascend处理器，请发送[申请表](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx)至ascend@huawei.com，审核通过即可获得资源。
- 使用Ascend来搭建硬件环境。
- 框架
- [MindSpore](https://www.mindspore.cn/install/en)
- 如需查看详情，请参见如下资源：

2
model_zoo/official/cv/inceptionv4/README.md
Unescape View File

@ -51,7 +51,7 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
# [Environment Requirements](#contents)
- Hardware（Ascend/GPU）
- Prepare hardware environment with Ascend processor. If you want to try Ascend, please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend processor.
- or prepare GPU processor.
- Framework
- [MindSpore](https://www.mindspore.cn/install/en)

2
model_zoo/official/cv/maskrcnn/README.md
Unescape View File

@ -53,7 +53,7 @@ Note that you can run the scripts based on the dataset mentioned in original pap
# [Environment Requirements](#contents)
- Hardware（Ascend）
- Prepare hardware environment with Ascend processor. If you want to try Ascend, please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend processor.
- Framework
- [MindSpore](https://gitee.com/mindspore/mindspore)
- Docker base image

2
model_zoo/official/cv/maskrcnn/README_CN.md
Unescape View File

@ -55,7 +55,7 @@ MaskRCNN是一个两级目标检测网络，作为FasterRCNN的扩展模型，
# 环境要求
- 硬件（昇腾处理器）
- 采用昇腾处理器搭建硬件环境。如需试用昇腾处理器，请发送[申请表](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx)至ascend@huawei.com，审核通过即可获得资源。
- 采用昇腾处理器搭建硬件环境。
- 框架
- [MindSpore](https://gitee.com/mindspore/mindspore)
- 获取基础镜像

2
model_zoo/official/cv/maskrcnn_mobilenetv1/README.md
Unescape View File

@ -54,7 +54,7 @@ Note that you can run the scripts based on the dataset mentioned in original pap
# [Environment Requirements](#contents)
- Hardware（Ascend）
- Prepare hardware environment with Ascend processor. If you want to try Ascend , please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend processor.
- Framework
- [MindSpore](https://gitee.com/mindspore/mindspore)
- For more information, please check the resources below:

2
model_zoo/official/cv/mobilenetv1/README.md
Unescape View File

@ -64,7 +64,7 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
## Environment Requirements
- Hardware（Ascend）
- Prepare hardware environment with Ascend. If you want to try Ascend, please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend.
- Framework
- [MindSpore](https://www.mindspore.cn/install/en)
- For more information, please check the resources below：

2
model_zoo/official/cv/mobilenetv2/README.md
Unescape View File

@ -50,7 +50,7 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
# [Environment Requirements](#contents)
- Hardware（Ascend/GPU/CPU）
- Prepare hardware environment with Ascend, GPU or CPU processor. If you want to try Ascend, please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
- Prepare hardware environment with Ascend, GPU or CPU processor.
- Framework
- [MindSpore](https://www.mindspore.cn/install/en)
- For more information, please check the resources below：

2
model_zoo/official/cv/mobilenetv2/README_CN.md
Unescape View File

@ -56,7 +56,7 @@ MobileNetV2总体网络架构如下：
# 环境要求
- 硬件（Ascend/GPU/CPU）
- 使用Ascend、GPU或CPU处理器来搭建硬件环境。如需试用Ascend处理器，请发送[申请表](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx)至ascend@huawei.com，审核通过即可获得资源。
- 使用Ascend、GPU或CPU处理器来搭建硬件环境。
- 框架
- [MindSpore](https://www.mindspore.cn/install)
- 如需查看详情，请参见如下资源：

Some files were not shown because too many files have changed in this diff Show More

Write Preview
Loading…
Cancel
Save