Skip to content

P
PaddleClas

PaddlePaddle / PaddleClas
1 年多 前同步成功

通知 115
Star 4999
Fork 1114
P
PaddleClas
提交 a1fa19cd 编写于 作者: G gaotingquan 提交者： cuicheng01
浏览文件
操作

rename: v3 -> V3

上级 2091a59f
隐藏空白更改
内联 并排
Showing with 208 addition and 208 deletion
docs/zh_CN/models/ImageNet1k/MobileViTv3.md → docs/zh_CN/models/ImageNet1k/MobileViTV3.md
浏览文件 @ a1fa19cd
# MobileviTv3
# MobileviTV3
-----
## 目录
......@@ -24,8 +24,8 @@
### 1.1 模型简介
MobileViTv3 是一个结合 CNN 和 ViT 的轻量级模型，用于移动视觉任务。通过 MobileViTv3-block 解决了 MobileViTv1 的扩展问题并简化了学习任务，从而得倒了 MobileViTv3-XXS、XS 和 S 模型，在 ImageNet-1k、ADE20K、COCO 和 PascalVOC2012 数据集上表现优于 MobileViTv1。
通过将提出的融合块添加到 MobileViTv2 中，创建 MobileViTv3-0.5、0.75 和 1.0 模型，在ImageNet-1k、ADE20K、COCO和PascalVOC2012数据集上给出了比 MobileViTv2 更好的准确性数据。[论文地址](https://arxiv.org/abs/2209.15159)。
MobileViTV3 是一个结合 CNN 和 ViT 的轻量级模型，用于移动视觉任务。通过 MobileViTV3-block 解决了 MobileViTV1 的扩展问题并简化了学习任务，从而得倒了 MobileViTV3-XXS、XS 和 S 模型，在 ImageNet-1k、ADE20K、COCO 和 PascalVOC2012 数据集上表现优于 MobileViTV1。
通过将提出的融合块添加到 MobileViTV2 中，创建 MobileViTV3_x0_5、MobileViTV3_x0_75 和 MobileViTV3_x1_0 模型，在ImageNet-1k、ADE20K、COCO和PascalVOC2012数据集上给出了比 MobileViTV2 更好的准确性数据。[论文地址](https://arxiv.org/abs/2209.15159)。
<a name='1.2'></a>
......@@ -33,15 +33,15 @@ MobileViTv3 是一个结合 CNN 和 ViT 的轻量级模型，用于移动视觉
| Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPs<br>(G) | Params<br>(M) |
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
| MobileViTv3_XXS | 0.7087 | 0.8976 | 0.7098 | - | 289.02 | 1.25 |
| MobileViTv3_XS | 0.7663 | 0.9332 | 0.7671 | - | 926.98 | 2.49 |
| MobileViTv3_S | 0.7928 | 0.9454 | 0.7930 | - | 1841.39 | 5.76 |
| MobileViTv3_XXS_L2 | 0.7028 | 0.8942 | 0.7023 | - | 256.97 | 1.15 |
| MobileViTv3_XS_L2 | 0.7607 | 0.9300 | 0.7610 | - | 852.82 | 2.26 |
| MobileViTv3_S_L2 | 0.7907 | 0.9440 | 0.7906 | - | 1651.96 | 5.17 |
| MobileViTv3_x0_5 | 0.7200 | 0.9083 | 0.7233 | - | 481.33 | 1.43 |
| MobileViTv3_x0_75 | 0.7626 | 0.9308 | 0.7655 | - | 1064.48 | 3.00 |
| MobileViTv3_x1_0 | 0.7838 | 0.9421 | 0.7864 | - | 1875.96 | 5.14 |
| MobileViTV3_XXS | 0.7087 | 0.8976 | 0.7098 | - | 289.02 | 1.25 |
| MobileViTV3_XS | 0.7663 | 0.9332 | 0.7671 | - | 926.98 | 2.49 |
| MobileViTV3_S | 0.7928 | 0.9454 | 0.7930 | - | 1841.39 | 5.76 |
| MobileViTV3_XXS_L2 | 0.7028 | 0.8942 | 0.7023 | - | 256.97 | 1.15 |
| MobileViTV3_XS_L2 | 0.7607 | 0.9300 | 0.7610 | - | 852.82 | 2.26 |
| MobileViTV3_S_L2 | 0.7907 | 0.9440 | 0.7906 | - | 1651.96 | 5.17 |
| MobileViTV3_x0_5 | 0.7200 | 0.9083 | 0.7233 | - | 481.33 | 1.43 |
| MobileViTV3_x0_75 | 0.7626 | 0.9308 | 0.7655 | - | 1064.48 | 3.00 |
| MobileViTV3_x1_0 | 0.7838 | 0.9421 | 0.7864 | - | 1875.96 | 5.14 |
**备注：** PaddleClas 所提供的该系列模型的预训练模型权重，均是基于其官方提供的权重转得。
......@@ -55,7 +55,7 @@ MobileViTv3 是一个结合 CNN 和 ViT 的轻量级模型，用于移动视觉
## 3. 模型训练、评估和预测
此部分内容包括训练环境配置、ImageNet数据的准备、该模型在 ImageNet 上的训练、评估、预测等内容。在 `ppcls/configs/ImageNet/MobileViTv3/` 中提供了该模型的训练配置，启动训练方法可以参考：[ResNet50 模型训练、评估和预测](./ResNet.md#3-模型训练评估和预测)。
此部分内容包括训练环境配置、ImageNet数据的准备、该模型在 ImageNet 上的训练、评估、预测等内容。在 `ppcls/configs/ImageNet/MobileViTV3/` 中提供了该模型的训练配置，启动训练方法可以参考：[ResNet50 模型训练、评估和预测](./ResNet.md#3-模型训练评估和预测)。
**备注：** 由于 MobileViT 系列模型默认使用的 GPU 数量为 8 个，所以在训练时，需要指定8个GPU，如`python3 -m paddle.distributed.launch --gpus="0,1,2,3,4,5,6,7" tools/train.py -c xxx.yaml`, 如果使用 4 个 GPU 训练，默认学习率需要减小一半，精度可能有损。
......
ppcls/arch/backbone/__init__.py
浏览文件 @ a1fa19cd
......@@ -79,8 +79,8 @@ from .model_zoo.cvt import CvT_13_224, CvT_13_384, CvT_21_224, CvT_21_384, CvT_W
from .model_zoo.micronet import MicroNet_M0, MicroNet_M1, MicroNet_M2, MicroNet_M3
from .model_zoo.mobilenext import MobileNeXt_x0_35, MobileNeXt_x0_5, MobileNeXt_x0_75, MobileNeXt_x1_0, MobileNeXt_x1_4
from .model_zoo.mobilevit_v2 import MobileViTV2_x0_5, MobileViTV2_x0_75, MobileViTV2_x1_0, MobileViTV2_x1_25, MobileViTV2_x1_5, MobileViTV2_x1_75, MobileViTV2_x2_0
from .model_zoo.mobilevit_v3 import MobileViTv3_XXS, MobileViTv3_XS, MobileViTv3_S, MobileViTv3_XXS_L2, MobileViTv3_XS_L2, MobileViTv3_S_L2, MobileViTv3_x0_5, MobileViTv3_x0_75, MobileViTv3_x1_0
from .model_zoo.tinynet import TinyNet_A, TinyNet_B, TinyNet_C, TinyNet_D, TinyNet_E
from .model_zoo.mobilevit_v3 import MobileViTV3_XXS, MobileViTV3_XS, MobileViTV3_S, MobileViTV3_XXS_L2, MobileViTV3_XS_L2, MobileViTV3_S_L2, MobileViTV3_x0_5, MobileViTV3_x0_75, MobileViTV3_x1_0
from .variant_models.resnet_variant import ResNet50_last_stage_stride1
from .variant_models.resnet_variant import ResNet50_adaptive_max_pool2d
......
ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_S.yaml → ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_S.yaml
浏览文件 @ a1fa19cd
......@@ -28,7 +28,7 @@ EMA:
# model architecture
Arch:
name: MobileViTv3_S
name: MobileViTV3_S
class_num: 1000
dropout: 0.1
......
ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_S_L2.yaml → ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_S_L2.yaml
浏览文件 @ a1fa19cd
......@@ -28,7 +28,7 @@ EMA:
# model architecture
Arch:
name: MobileViTv3_S_L2
name: MobileViTV3_S_L2
class_num: 1000
dropout: 0.1
......
ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XS.yaml → ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XS.yaml
浏览文件 @ a1fa19cd
......@@ -28,7 +28,7 @@ EMA:
# model architecture
Arch:
name: MobileViTv3_XS
name: MobileViTV3_XS
class_num: 1000
dropout: 0.1
......
ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XS_L2.yaml → ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XS_L2.yaml
浏览文件 @ a1fa19cd
......@@ -28,7 +28,7 @@ EMA:
# model architecture
Arch:
name: MobileViTv3_XS_L2
name: MobileViTV3_XS_L2
class_num: 1000
dropout: 0.1
......
ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XXS.yaml → ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XXS.yaml
浏览文件 @ a1fa19cd
......@@ -28,7 +28,7 @@ EMA:
# model architecture
Arch:
name: MobileViTv3_XXS
name: MobileViTV3_XXS
class_num: 1000
dropout: 0.05
......
ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XXS_L2.yaml 0 → 100644
浏览文件 @ a1fa19cd
# global configs
Global:
checkpoints: null
pretrained_model: null
output_dir: ./output/
device: gpu
save_interval: 1
eval_during_train: True
eval_interval: 1
epochs: 300
print_batch_step: 10
use_visualdl: False
# used for static mode and model export
image_shape: [3, 256, 256]
save_inference_dir: ./inference
use_dali: False
# mixed precision training
AMP:
scale_loss: 65536
use_dynamic_loss_scaling: True
# O1: mixed fp16
level: O1
# model ema
EMA:
decay: 0.9995
# model architecture
Arch:
name: MobileViTV3_XXS_L2
class_num: 1000
dropout: 0.1
# loss function config for traing/eval process
Loss:
Train:
- CELoss:
weight: 1.0
epsilon: 0.1
Eval:
- CELoss:
weight: 1.0
Optimizer:
name: AdamW
beta1: 0.9
beta2: 0.999
epsilon: 1e-8
weight_decay: 0.01
lr:
name: Cosine
learning_rate: 0.002 # for total batch size 384
eta_min: 0.0002
warmup_epoch: 1 # 3000 iterations
warmup_start_lr: 0.0002
# data loader for train and eval
DataLoader:
Train:
dataset:
name: MultiScaleDataset
image_root: ./dataset/ILSVRC2012/
cls_label_path: ./dataset/ILSVRC2012/train_list.txt
transform_ops:
- DecodeImage:
to_rgb: True
channel_first: False
- RandCropImage:
size: 256
interpolation: bilinear
use_log_aspect: True
- RandFlipImage:
flip_code: 1
- NormalizeImage:
scale: 1.0/255.0
mean: [0.0, 0.0, 0.0]
std: [1.0, 1.0, 1.0]
order: ''
# support to specify width and height respectively:
# scales: [(256,256) (160,160), (192,192), (224,224) (288,288) (320,320)]
sampler:
name: MultiScaleSampler
scales: [256, 160, 192, 224, 288, 320]
# first_bs: batch size for the first image resolution in the scales list
# divide_factor: to ensure the width and height dimensions can be devided by downsampling multiple
first_bs: 48
divided_factor: 32
is_training: True
loader:
num_workers: 4
use_shared_memory: True
Eval:
dataset:
name: ImageNetDataset
image_root: ./dataset/ILSVRC2012/
cls_label_path: ./dataset/ILSVRC2012/val_list.txt
transform_ops:
- DecodeImage:
to_rgb: True
channel_first: False
- ResizeImage:
resize_short: 288
interpolation: bilinear
- CropImage:
size: 256
- NormalizeImage:
scale: 1.0/255.0
mean: [0.0, 0.0, 0.0]
std: [1.0, 1.0, 1.0]
order: ''
sampler:
name: DistributedBatchSampler
batch_size: 48
drop_last: False
shuffle: False
loader:
num_workers: 4
use_shared_memory: True
Infer:
infer_imgs: docs/images/inference_deployment/whl_demo.jpg
batch_size: 10
transforms:
- DecodeImage:
to_rgb: True
channel_first: False
- ResizeImage:
resize_short: 288
interpolation: bilinear
- CropImage:
size: 256
- NormalizeImage:
scale: 1.0/255.0
mean: [0.0, 0.0, 0.0]
std: [1.0, 1.0, 1.0]
order: ''
- ToCHWImage:
PostProcess:
name: Topk
topk: 5
class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
Metric:
Train:
- TopkAcc:
topk: [1, 5]
Eval:
- TopkAcc:
topk: [1, 5]
ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_x0_5.yaml → ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_x0_5.yaml
浏览文件 @ a1fa19cd
......@@ -28,7 +28,7 @@ EMA:
# model architecture
Arch:
name: MobileViTv3_x0_5
name: MobileViTV3_x0_5
class_num: 1000
classifier_dropout: 0.
......
ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_x0_75.yaml → ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_x0_75.yaml
浏览文件 @ a1fa19cd
......@@ -28,7 +28,7 @@ EMA:
# model architecture
Arch:
name: MobileViTv3_x0_75
name: MobileViTV3_x0_75
class_num: 1000
classifier_dropout: 0.
......
ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_x1_0.yaml → ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_x1_0.yaml
浏览文件 @ a1fa19cd
......@@ -28,7 +28,7 @@ EMA:
# model architecture
Arch:
name: MobileViTv3_x1_0
name: MobileViTV3_x1_0
class_num: 1000
classifier_dropout: 0.
......
ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XXS_L2.yaml 已删除 100644 → 0
浏览文件 @ 2091a59f
# global configs
Global:
checkpoints: null
pretrained_model: null
output_dir: ./output/
device: gpu
save_interval: 1
eval_during_train: True
eval_interval: 1
epochs: 300
print_batch_step: 10
use_visualdl: False
# used for static mode and model export
image_shape: [3, 256, 256]
save_inference_dir: ./inference
use_dali: False
# mixed precision training
AMP:
scale_loss: 65536
use_dynamic_loss_scaling: True
# O1: mixed fp16
level: O1
# model ema
EMA:
decay: 0.9995
# model architecture
Arch:
name: MobileViTv3_XXS_L2
class_num: 1000
dropout: 0.1
# loss function config for traing/eval process
Loss:
Train:
- CELoss:
weight: 1.0
epsilon: 0.1
Eval:
- CELoss:
weight: 1.0
Optimizer:
name: AdamW
beta1: 0.9
beta2: 0.999
epsilon: 1e-8
weight_decay: 0.01
lr:
name: Cosine
learning_rate: 0.002 # for total batch size 384
eta_min: 0.0002
warmup_epoch: 1 # 3000 iterations
warmup_start_lr: 0.0002
# data loader for train and eval
DataLoader:
Train:
dataset:
name: MultiScaleDataset
image_root: ./dataset/ILSVRC2012/
cls_label_path: ./dataset/ILSVRC2012/train_list.txt
transform_ops:
- DecodeImage:
to_rgb: True
channel_first: False
- RandCropImage:
size: 256
interpolation: bilinear
use_log_aspect: True
- RandFlipImage:
flip_code: 1
- NormalizeImage:
scale: 1.0/255.0
mean: [0.0, 0.0, 0.0]
std: [1.0, 1.0, 1.0]
order: ''
# support to specify width and height respectively:
# scales: [(256,256) (160,160), (192,192), (224,224) (288,288) (320,320)]
sampler:
name: MultiScaleSampler
scales: [256, 160, 192, 224, 288, 320]
# first_bs: batch size for the first image resolution in the scales list
# divide_factor: to ensure the width and height dimensions can be devided by downsampling multiple
first_bs: 48
divided_factor: 32
is_training: True
loader:
num_workers: 4
use_shared_memory: True
Eval:
dataset:
name: ImageNetDataset
image_root: ./dataset/ILSVRC2012/
cls_label_path: ./dataset/ILSVRC2012/val_list.txt
transform_ops:
- DecodeImage:
to_rgb: True
channel_first: False
- ResizeImage:
resize_short: 288
interpolation: bilinear
- CropImage:
size: 256
- NormalizeImage:
scale: 1.0/255.0
mean: [0.0, 0.0, 0.0]
std: [1.0, 1.0, 1.0]
order: ''
sampler:
name: DistributedBatchSampler
batch_size: 48
drop_last: False
shuffle: False
loader:
num_workers: 4
use_shared_memory: True
Infer:
infer_imgs: docs/images/inference_deployment/whl_demo.jpg
batch_size: 10
transforms:
- DecodeImage:
to_rgb: True
channel_first: False
- ResizeImage:
resize_short: 288
interpolation: bilinear
- CropImage:
size: 256
- NormalizeImage:
scale: 1.0/255.0
mean: [0.0, 0.0, 0.0]
std: [1.0, 1.0, 1.0]
order: ''
- ToCHWImage:
PostProcess:
name: Topk
topk: 5
class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
Metric:
Train:
- TopkAcc:
topk: [1, 5]
Eval:
- TopkAcc:
topk: [1, 5]
test_tipc/configs/MobileViTv3/MobileViTv3_S_L2_train_infer_python.txt → test_tipc/configs/MobileViTv3/MobileViTV3_S_L2_train_infer_python.txt
浏览文件 @ a1fa19cd
===========================train_params===========================
model_name:MobileViTv3_S_L2
model_name:MobileViTV3_S_L2
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
......@@ -13,7 +13,7 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_S_L2.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_S_L2.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
pact_train:null
fpgm_train:null
distill_train:null
......@@ -21,13 +21,13 @@ null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_S_L2.yaml
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_S_L2.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_S_L2.yaml
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_S_L2.yaml
quant_export:null
fpgm_export:null
distill_export:null
......
test_tipc/configs/MobileViTv3/MobileViTv3_S_train_infer_python.txt → test_tipc/configs/MobileViTv3/MobileViTV3_S_train_infer_python.txt
浏览文件 @ a1fa19cd
===========================train_params===========================
model_name:MobileViTv3_S
model_name:MobileViTV3_S
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
......@@ -13,7 +13,7 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_S.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_S.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
pact_train:null
fpgm_train:null
distill_train:null
......@@ -21,13 +21,13 @@ null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_S.yaml
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_S.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_S.yaml
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_S.yaml
quant_export:null
fpgm_export:null
distill_export:null
......
test_tipc/configs/MobileViTv3/MobileViTv3_XS_L2_train_infer_python.txt → test_tipc/configs/MobileViTv3/MobileViTV3_XS_L2_train_infer_python.txt
浏览文件 @ a1fa19cd
===========================train_params===========================
model_name:MobileViTv3_XS_L2
model_name:MobileViTV3_XS_L2
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
......@@ -13,7 +13,7 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XS_L2.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XS_L2.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
pact_train:null
fpgm_train:null
distill_train:null
......@@ -21,13 +21,13 @@ null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XS_L2.yaml
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XS_L2.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XS_L2.yaml
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XS_L2.yaml
quant_export:null
fpgm_export:null
distill_export:null
......
test_tipc/configs/MobileViTv3/MobileViTv3_XS_train_infer_python.txt → test_tipc/configs/MobileViTv3/MobileViTV3_XS_train_infer_python.txt
浏览文件 @ a1fa19cd
===========================train_params===========================
model_name:MobileViTv3_XS
model_name:MobileViTV3_XS
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
......@@ -13,7 +13,7 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XS.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XS.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
pact_train:null
fpgm_train:null
distill_train:null
......@@ -21,13 +21,13 @@ null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XS.yaml
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XS.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XS.yaml
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XS.yaml
quant_export:null
fpgm_export:null
distill_export:null
......
test_tipc/configs/MobileViTv3/MobileViTv3_XXS_L2_train_infer_python.txt → test_tipc/configs/MobileViTv3/MobileViTV3_XXS_L2_train_infer_python.txt
浏览文件 @ a1fa19cd
===========================train_params===========================
model_name:MobileViTv3_XXS_L2
model_name:MobileViTV3_XXS_L2
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
......@@ -13,7 +13,7 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XXS_L2.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XXS_L2.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
pact_train:null
fpgm_train:null
distill_train:null
......@@ -21,13 +21,13 @@ null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XXS_L2.yaml
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XXS_L2.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XXS_L2.yaml
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XXS_L2.yaml
quant_export:null
fpgm_export:null
distill_export:null
......
test_tipc/configs/MobileViTv3/MobileViTv3_XXS_train_infer_python.txt → test_tipc/configs/MobileViTv3/MobileViTV3_XXS_train_infer_python.txt
浏览文件 @ a1fa19cd
===========================train_params===========================
model_name:MobileViTv3_XXS
model_name:MobileViTV3_XXS
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
......@@ -13,7 +13,7 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XXS.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XXS.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
pact_train:null
fpgm_train:null
distill_train:null
......@@ -21,13 +21,13 @@ null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XXS.yaml
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XXS.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_XXS.yaml
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_XXS.yaml
quant_export:null
fpgm_export:null
distill_export:null
......
test_tipc/configs/MobileViTv3/MobileViTv3_x0_5_train_infer_python.txt → test_tipc/configs/MobileViTv3/MobileViTV3_x0_5_train_infer_python.txt
浏览文件 @ a1fa19cd
===========================train_params===========================
model_name:MobileViTv3_x0_5
model_name:MobileViTV3_x0_5
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
......@@ -13,7 +13,7 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_x0_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_x0_5.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
pact_train:null
fpgm_train:null
distill_train:null
......@@ -21,13 +21,13 @@ null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_x0_5.yaml
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_x0_5.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_x0_5.yaml
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_x0_5.yaml
quant_export:null
fpgm_export:null
distill_export:null
......
test_tipc/configs/MobileViTv3/MobileViTv3_x0_75_train_infer_python.txt → test_tipc/configs/MobileViTv3/MobileViTV3_x0_75_train_infer_python.txt
浏览文件 @ a1fa19cd
===========================train_params===========================
model_name:MobileViTv3_x0_75
model_name:MobileViTV3_x0_75
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
......@@ -13,7 +13,7 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_x0_75.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_x0_75.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
pact_train:null
fpgm_train:null
distill_train:null
......@@ -21,13 +21,13 @@ null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_x0_75.yaml
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_x0_75.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_x0_75.yaml
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_x0_75.yaml
quant_export:null
fpgm_export:null
distill_export:null
......
test_tipc/configs/MobileViTv3/MobileViTv3_x1_0_train_infer_python.txt → test_tipc/configs/MobileViTv3/MobileViTV3_x1_0_train_infer_python.txt
浏览文件 @ a1fa19cd
===========================train_params===========================
model_name:MobileViTv3_x1_0
model_name:MobileViTV3_x1_0
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
......@@ -13,7 +13,7 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_x1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
norm_train:tools/train.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_x1_0.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.print_batch_step=1 -o Global.eval_during_train=False -o Global.save_interval=2
pact_train:null
fpgm_train:null
distill_train:null
......@@ -21,13 +21,13 @@ null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_x1_0.yaml
eval:tools/eval.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_x1_0.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTv3/MobileViTv3_x1_0.yaml
norm_export:tools/export_model.py -c ppcls/configs/ImageNet/MobileViTV3/MobileViTV3_x1_0.yaml
quant_export:null
fpgm_export:null
distill_export:null
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或