p60975123
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

remove quantization_aware option in Mobilenetv2-quant config

This commit is contained in:
yuchaojie 2020-11-24 10:51:09 +08:00
parent 3d6d820612
commit 9051c56436
4 changed files with 8 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
model_zoo/official/cv/mobilenetv2_quant/README_CN.md
View File

@ -102,10 +102,10 @@ MobileNetV2总体网络架构如下：
- 配置MobileNetV2-quant和ImageNet2012数据集。
```python
'class_num':1000 # 数据集类数
'num_classes':1000 # 数据集类数
'batch_size':134 # 训练批次大小
'epoch_size':60 # Mobilenetv2-quant的训练轮次
'start epoch':200 # 非量化网络预训练轮次
'epoch_size':60 # Mobilenetv2-quant的训练轮次
'start_epoch':200 # 非量化网络预训练轮次
'warmup_epochs':0 # 热身轮次
'lr':0.3 # 学习率
'momentum':0.9 # 动量

6
model_zoo/official/cv/mobilenetv2_quant/Readme.md
View File

@ -92,10 +92,10 @@ Parameters for both training and evaluation can be set in config.py
- config for MobileNetV2-quant, ImageNet2012 dataset
```python
'class_num': 1000 # the number of classes in the dataset
'num_classes': 1000 # the number of classes in the dataset
'batch_size': 134 # training batch size
'epoch_size': 60 # training epochs of mobilenetv2-quant
'start epoch':200 # pretraining epochs of unquantative network
'epoch_size': 60 # training epochs of mobilenetv2-quant
'start_epoch':200 # pretraining epochs of unquantative network
'warmup_epochs': 0 # number of warmup epochs
'lr': 0.3 #learning rate
'momentum': 0.9 # momentum

5
model_zoo/official/cv/mobilenetv2_quant/src/config.py
View File

@ -24,7 +24,7 @@ config_ascend_quant = ed({
"data_load_mode": "mindata",
"epoch_size": 60,
"start_epoch": 200,
"warmup_epochs": 1,
"warmup_epochs": 0,
"lr": 0.3,
"momentum": 0.9,
"weight_decay": 4e-5,
@ -34,7 +34,6 @@ config_ascend_quant = ed({
"save_checkpoint_epochs": 1,
"keep_checkpoint_max": 300,
"save_checkpoint_path": "./checkpoint",
"quantization_aware": True,
})
config_gpu_quant = ed({
@ -42,7 +41,7 @@ config_gpu_quant = ed({
"batch_size": 134,
"epoch_size": 60,
"start_epoch": 200,
"warmup_epochs": 1,
"warmup_epochs": 0,
"lr": 0.3,
"momentum": 0.9,
"weight_decay": 4e-5,

1
tests/st/quantization/mobilenetv2_quant/test_mobilenetv2_quant.py
View File

@ -50,7 +50,6 @@ config_ascend_quant = ed({
"save_checkpoint_epochs": 1,
"keep_checkpoint_max": 300,
"save_checkpoint_path": "./checkpoint",
"quantization_aware": True,
})
dataset_path = "/home/workspace/mindspore_dataset/cifar-10-batches-bin/"