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

fix issues

Browse Source
pull/7587/head
gengdongjie 5 years ago
parent 093653628b
commit 1eca0b0245
4 changed files with 117 additions and 61 deletions
Show Stats Download Patch File Download Diff File

84
model_zoo/official/cv/maskrcnn/README.md
Unescape View File

@ -19,8 +19,8 @@
- [Evaluation Result](#evaluation-result) - [Evaluation Result](#evaluation-result)
- [Model Description](#model-description) - [Model Description](#model-description)
- [Performance](#performance) - [Performance](#performance)
- [Training Performance](#training-performance)
- [Evaluation Performance](#evaluation-performance) - [Evaluation Performance](#evaluation-performance)
- [Inference Performance](#inference-performance)
- [Description of Random Situation](#description-of-random-situation) - [Description of Random Situation](#description-of-random-situation)
- [ModelZoo Homepage](#modelzoo-homepage) - [ModelZoo Homepage](#modelzoo-homepage)
@ -279,7 +279,7 @@ Usage: sh run_standalone_train.sh [PRETRAINED_MODEL]
"save_checkpoint": True, # whether save checkpoint or not "save_checkpoint": True, # whether save checkpoint or not
"save_checkpoint_epochs": 1, # save checkpoint interval "save_checkpoint_epochs": 1, # save checkpoint interval
"keep_checkpoint_max": 12, # max number of saved checkpoint "keep_checkpoint_max": 12, # max number of saved checkpoint
"save_checkpoint_path": "./checkpoint", # path of checkpoint "save_checkpoint_path": "./", # path of checkpoint
"mindrecord_dir": "/home/maskrcnn/MindRecord_COCO2017_Train", # path of mindrecord "mindrecord_dir": "/home/maskrcnn/MindRecord_COCO2017_Train", # path of mindrecord
"coco_root": "/home/maskrcnn/", # path of coco root dateset "coco_root": "/home/maskrcnn/", # path of coco root dateset
@ -335,13 +335,13 @@ Training result will be stored in the example path, whose folder name begins wit
``` ```
# distribute training result(8p) # distribute training result(8p)
epoch: 1 step: 7393 ,rpn_loss: 0.10626, rcnn_loss: 0.81592, rpn_cls_loss: 0.05862, rpn_reg_loss: 0.04761, rcnn_cls_loss: 0.32642, rcnn_reg_loss: 0.15503, rcnn_mask_loss: 0.33447, total_loss: 0.92218 epoch: 1 step: 7393 ,rpn_loss: 0.05716, rcnn_loss: 0.81152, rpn_cls_loss: 0.04828, rpn_reg_loss: 0.00889, rcnn_cls_loss: 0.28784, rcnn_reg_loss: 0.17590, rcnn_mask_loss: 0.34790, total_loss: 0.86868
epoch: 2 step: 7393 ,rpn_loss: 0.00911, rcnn_loss: 0.34082, rpn_cls_loss: 0.00341, rpn_reg_loss: 0.00571, rcnn_cls_loss: 0.07440, rcnn_reg_loss: 0.05872, rcnn_mask_loss: 0.20764, total_loss: 0.34993 epoch: 2 step: 7393 ,rpn_loss: 0.00434, rcnn_loss: 0.36572, rpn_cls_loss: 0.00339, rpn_reg_loss: 0.00095, rcnn_cls_loss: 0.08240, rcnn_reg_loss: 0.05554, rcnn_mask_loss: 0.22778, total_loss: 0.37006
epoch: 3 step: 7393 ,rpn_loss: 0.02087, rcnn_loss: 0.98633, rpn_cls_loss: 0.00665, rpn_reg_loss: 0.01422, rcnn_cls_loss: 0.35913, rcnn_reg_loss: 0.21375, rcnn_mask_loss: 0.41382, total_loss: 1.00720 epoch: 3 step: 7393 ,rpn_loss: 0.00996, rcnn_loss: 0.83789, rpn_cls_loss: 0.00701, rpn_reg_loss: 0.00294, rcnn_cls_loss: 0.39478, rcnn_reg_loss: 0.14917, rcnn_mask_loss: 0.29370, total_loss: 0.84785
... ...
epoch: 10 step: 7393 ,rpn_loss: 0.02122, rcnn_loss: 0.55176, rpn_cls_loss: 0.00620, rpn_reg_loss: 0.01503, rcnn_cls_loss: 0.12708, rcnn_reg_loss: 0.10254, rcnn_mask_loss: 0.32227, total_loss: 0.57298 epoch: 10 step: 7393 ,rpn_loss: 0.00667, rcnn_loss: 0.65625, rpn_cls_loss: 0.00536, rpn_reg_loss: 0.00131, rcnn_cls_loss: 0.17590, rcnn_reg_loss: 0.16199, rcnn_mask_loss: 0.31812, total_loss: 0.66292
epoch: 11 step: 7393 ,rpn_loss: 0.03772, rcnn_loss: 0.60791, rpn_cls_loss: 0.03058, rpn_reg_loss: 0.00713, rcnn_cls_loss: 0.23987, rcnn_reg_loss: 0.11743, rcnn_mask_loss: 0.25049, total_loss: 0.64563 epoch: 11 step: 7393 ,rpn_loss: 0.02003, rcnn_loss: 0.52051, rpn_cls_loss: 0.01761, rpn_reg_loss: 0.00241, rcnn_cls_loss: 0.16028, rcnn_reg_loss: 0.08411, rcnn_mask_loss: 0.27588, total_loss: 0.54054
epoch: 12 step: 7393 ,rpn_loss: 0.06482, rcnn_loss: 0.47681, rpn_cls_loss: 0.04770, rpn_reg_loss: 0.01709, rcnn_cls_loss: 0.16492, rcnn_reg_loss: 0.04990, rcnn_mask_loss: 0.26196, total_loss: 0.54163 epoch: 12 step: 7393 ,rpn_loss: 0.00547, rcnn_loss: 0.39258, rpn_cls_loss: 0.00285, rpn_reg_loss: 0.00262, rcnn_cls_loss: 0.08002, rcnn_reg_loss: 0.04990, rcnn_mask_loss: 0.26245, total_loss: 0.39804
``` ```
## [Evaluation Process](#contents) ## [Evaluation Process](#contents)
@ -363,39 +363,39 @@ Inference result will be stored in the example path, whose folder name is "eval"
``` ```
Evaluate annotation type *bbox* Evaluate annotation type *bbox*
Accumulating evaluation results... Accumulating evaluation results...
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.376 Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.378
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.598 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.602
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.405 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.407
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.239 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.242
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.414 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.417
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.475 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.480
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.311 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.311
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.500 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.497
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.528 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.524
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.371 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.363
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.572 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.567
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.653 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.647
Evaluate annotation type *segm* Evaluate annotation type *segm*
Accumulating evaluation results... Accumulating evaluation results...
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.326 Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.335
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.553 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.557
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.344 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.351
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.169 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.169
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.356 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.365
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.462 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.480
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.278 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.284
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.426 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.433
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.445 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.451
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.294 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.285
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.484 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.490
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.558 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.586
``` ```
# Model Description # Model Description
## Performance ## Performance
### Training Performance ### Evaluation Performance
| Parameters | MaskRCNN | | Parameters | MaskRCNN |
| -------------------------- | ----------------------------------------------------------- | | -------------------------- | ----------------------------------------------------------- |
@ -406,14 +406,18 @@ Accumulating evaluation results...
| Dataset | COCO2017 | | Dataset | COCO2017 |
| Training Parameters | epoch=12, batch_size = 2 | | Training Parameters | epoch=12, batch_size = 2 |
| Optimizer | SGD | | Optimizer | SGD |
| Loss Function | Softmax Cross Entropy ,Sigmoid Cross Entropy,SmoothL1Loss | | Loss Function | Softmax Cross Entropy, Sigmoid Cross Entropy, SmoothL1Loss |
| Speed | 1pc: 250 ms/step; 8pcs: 260 ms/step | | Output | Probability |
| Total time | 1pc: 52 hours; 8pcs: 6.6 hours | | Loss | 0.39804 |
| Parameters (M) | 280 | | Speed | 1pc: 193 ms/step; 8pcs: 207 ms/step |
| Scripts | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/maskrcnn | | Total time | 1pc: 46 hours; 8pcs: 5.38 hours |
| Parameters (M) | 84.8 |
| Checkpoint for Fine tuning | 85M(.ckpt file) |
| Model for inference | 571M(.air file) |
| Scripts | [maskrcnn script](https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/official/cv/maskrcnn) |
### Evaluation Performance ### Inference Performance
| Parameters | MaskRCNN | | Parameters | MaskRCNN |
| ------------------- | --------------------------- | | ------------------- | --------------------------- |
@ -424,12 +428,12 @@ Accumulating evaluation results...
| Dataset | COCO2017 | | Dataset | COCO2017 |
| batch_size | 2 | | batch_size | 2 |
| outputs | mAP | | outputs | mAP |
| Accuracy | IoU=0.50:0.95 32.4% | | Accuracy | IoU=0.50:0.95 (BoundingBox 37.0%, Mask 33.5) |
| Model for inference | 254M (.ckpt file) | | Model for inference | 170M (.ckpt file) |
# [Description of Random Situation](#contents) # [Description of Random Situation](#contents)
In dataset.py, we set the seed inside “create_dataset" function. We also use random seed in train.py for weight initialization. In dataset.py, we set the seed inside “create_dataset" function. We also use random seed in train.py for weight initialization.
# [ModelZoo Homepage](#contents) # [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/r1.0/model_zoo).

1
model_zoo/official/cv/maskrcnn/scripts/run_distribute_train.sh
Unescape View File

@ -46,6 +46,7 @@ exit 1
fi fi
ulimit -u unlimited ulimit -u unlimited
export HCCL_CONNECT_TIMEOUT=600
export DEVICE_NUM=8 export DEVICE_NUM=8
export RANK_SIZE=8 export RANK_SIZE=8
export RANK_TABLE_FILE=$PATH1 export RANK_TABLE_FILE=$PATH1

1
model_zoo/official/cv/maskrcnn/src/config.py
Unescape View File

@ -126,7 +126,6 @@ config = ed({
"warmup_step": 500, "warmup_step": 500,
"warmup_mode": "linear", "warmup_mode": "linear",
"warmup_ratio": 1/3.0, "warmup_ratio": 1/3.0,
"sgd_step": [8, 11],
"sgd_momentum": 0.9, "sgd_momentum": 0.9,
# train # train

92
model_zoo/official/cv/resnet/README.md
Unescape View File

@ -15,6 +15,7 @@
- [Model Description](#model-description) - [Model Description](#model-description)
- [Performance](#performance) - [Performance](#performance)
- [Evaluation Performance](#evaluation-performance) - [Evaluation Performance](#evaluation-performance)
- [Inference Performance](#inference-performance)
- [Description of Random Situation](#description-of-random-situation) - [Description of Random Situation](#description-of-random-situation)
- [ModelZoo Homepage](#modelzoo-homepage) - [ModelZoo Homepage](#modelzoo-homepage)
@ -136,9 +137,11 @@ sh run_eval_gpu.sh [resnet50|resnet101] [cifar10|imagenet2012] [DATASET_PATH] [C
├── src ├── src
├── config.py # parameter configuration ├── config.py # parameter configuration
├── dataset.py # data preprocessing ├── dataset.py # data preprocessing
├── CrossEntropySmooth.py # loss definition for ImageNet2012 dataset ├── CrossEntropySmooth.py # loss definition for ImageNet2012 dataset
├── lr_generator.py # generate learning rate for each step ├── lr_generator.py # generate learning rate for each step
└── resnet.py # resnet backbone, including resnet50 and resnet101 and se-resnet50 └── resnet.py # resnet backbone, including resnet50 and resnet101 and se-resnet50
├── export.py # export model for inference
├── mindspore_hub_conf.py # mindspore hub interface
├── eval.py # eval net ├── eval.py # eval net
└── train.py # train net └── train.py # train net
``` ```
@ -172,7 +175,7 @@ Parameters for both training and evaluation can be set in config.py.
``` ```
"class_num": 1001, # dataset class number "class_num": 1001, # dataset class number
"batch_size": 256, # batch size of input tensor "batch_size": 256, # batch size of input tensor
"loss_scale": 1024, # loss scale "loss_scale": 1024, # loss scale
"momentum": 0.9, # momentum optimizer "momentum": 0.9, # momentum optimizer
"weight_decay": 1e-4, # weight decay "weight_decay": 1e-4, # weight decay
@ -184,7 +187,7 @@ Parameters for both training and evaluation can be set in config.py.
"save_checkpoint_path": "./", # path to save checkpoint relative to the executed path "save_checkpoint_path": "./", # path to save checkpoint relative to the executed path
"warmup_epochs": 0, # number of warmup epoch "warmup_epochs": 0, # number of warmup epoch
"lr_decay_mode": "Linear", # decay mode for generating learning rate "lr_decay_mode": "Linear", # decay mode for generating learning rate
"use_label_smooth": True, # label smooth "use_label_smooth": True, # label smooth
"label_smooth_factor": 0.1, # label smooth factor "label_smooth_factor": 0.1, # label smooth factor
"lr_init": 0, # initial learning rate "lr_init": 0, # initial learning rate
"lr_max": 0.8, # maximum learning rate "lr_max": 0.8, # maximum learning rate
@ -207,7 +210,7 @@ Parameters for both training and evaluation can be set in config.py.
"save_checkpoint_path": "./", # path to save checkpoint relative to the executed path "save_checkpoint_path": "./", # path to save checkpoint relative to the executed path
"warmup_epochs": 0, # number of warmup epoch "warmup_epochs": 0, # number of warmup epoch
"lr_decay_mode": "cosine" # decay mode for generating learning rate "lr_decay_mode": "cosine" # decay mode for generating learning rate
"use_label_smooth": True, # label_smooth "use_label_smooth": True, # label_smooth
"label_smooth_factor": 0.1, # label_smooth_factor "label_smooth_factor": 0.1, # label_smooth_factor
"lr": 0.1 # base learning rate "lr": 0.1 # base learning rate
``` ```
@ -229,7 +232,7 @@ Parameters for both training and evaluation can be set in config.py.
"save_checkpoint_path": "./", # path to save checkpoint relative to the executed path "save_checkpoint_path": "./", # path to save checkpoint relative to the executed path
"warmup_epochs": 3, # number of warmup epoch "warmup_epochs": 3, # number of warmup epoch
"lr_decay_mode": "cosine" # decay mode for generating learning rate "lr_decay_mode": "cosine" # decay mode for generating learning rate
"use_label_smooth": True, # label_smooth "use_label_smooth": True, # label_smooth
"label_smooth_factor": 0.1, # label_smooth_factor "label_smooth_factor": 0.1, # label_smooth_factor
"lr_init": 0.0, # initial learning rate "lr_init": 0.0, # initial learning rate
"lr_max": 0.3, # maximum learning rate "lr_max": 0.3, # maximum learning rate
@ -254,7 +257,7 @@ Usage: sh run_eval.sh [resnet50|resnet101|se-resnet50] [cifar10|imagenet2012] [D
``` ```
For distributed training, a hccl configuration file with JSON format needs to be created in advance. For distributed training, a hccl configuration file with JSON format needs to be created in advance.
Please follow the instructions in the link [hccn_tools](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/utils/hccl_tools). Please follow the instructions in the link [hccn_tools](https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/utils/hccl_tools).
Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". Under this, you can find checkpoint file together with result like the followings in log. Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". Under this, you can find checkpoint file together with result like the followings in log.
@ -313,18 +316,13 @@ epoch: 5 step: 5004, loss is 3.1978393
- Training ResNet101 with ImageNet2012 dataset - Training ResNet101 with ImageNet2012 dataset
``` ```
# distribute training result(8p) # distribute training result(8 pcs)
epoch: 1 step: 5004, loss is 4.805483 epoch: 1 step: 5004, loss is 4.805483
epoch: 2 step: 5004, loss is 3.2121816 epoch: 2 step: 5004, loss is 3.2121816
epoch: 3 step: 5004, loss is 3.429647 epoch: 3 step: 5004, loss is 3.429647
epoch: 4 step: 5004, loss is 3.3667371 epoch: 4 step: 5004, loss is 3.3667371
epoch: 5 step: 5004, loss is 3.1718972 epoch: 5 step: 5004, loss is 3.1718972
... ...
epoch: 67 step: 5004, loss is 2.2768745
epoch: 68 step: 5004, loss is 1.7223864
epoch: 69 step: 5004, loss is 2.0665488
epoch: 70 step: 5004, loss is 1.8717369
...
``` ```
- Training SE-ResNet50 with ImageNet2012 dataset - Training SE-ResNet50 with ImageNet2012 dataset
@ -411,14 +409,14 @@ result: {'top_5_accuracy': 0.9342589628681178, 'top_1_accuracy': 0.7680657810499
| Total time | 6 mins | 20.2 mins| | Total time | 6 mins | 20.2 mins|
| Parameters (M) | 25.5 | 25.5 | | Parameters (M) | 25.5 | 25.5 |
| Checkpoint for Fine tuning | 179.7M (.ckpt file) |179.7M (.ckpt file)| | Checkpoint for Fine tuning | 179.7M (.ckpt file) |179.7M (.ckpt file)|
| Scripts | [Link](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/resnet) | [Link](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/resnet) | | Scripts | [Link](https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/official/cv/resnet) | [Link](https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/official/cv/resnet) |
#### ResNet50 on ImageNet2012 #### ResNet50 on ImageNet2012
| Parameters | Ascend 910 | GPU | | Parameters | Ascend 910 | GPU |
| -------------------------- | -------------------------------------- |---------------------------------- | | -------------------------- | -------------------------------------- |---------------------------------- |
| Model Version | ResNet50-v1.5 |ResNet50-v1.5| | Model Version | ResNet50-v1.5 |ResNet50-v1.5|
| Resource | Ascend 910，CPU 2.60GHz 56cores，Memory 314G | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24cores，Memory 128G | Resource | Ascend 910，CPU 2.60GHz 56cores，Memory 314G | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24cores，Memory 128G
| uploaded Date | 04/01/2020 (month/day/year) ； | 08/01/2020 (month/day/year) | uploaded Date | 04/01/2020 (month/day/year) | 08/01/2020 (month/day/year)
| MindSpore Version | 0.1.0-alpha |0.6.0-alpha | | MindSpore Version | 0.1.0-alpha |0.6.0-alpha |
| Dataset | ImageNet2012 | ImageNet2012| | Dataset | ImageNet2012 | ImageNet2012|
| Training Parameters | epoch=90, steps per epoch=626, batch_size = 256 |epoch=90, steps per epoch=5004, batch_size = 32 | | Training Parameters | epoch=90, steps per epoch=626, batch_size = 256 |epoch=90, steps per epoch=5004, batch_size = 32 |
@ -430,7 +428,7 @@ result: {'top_5_accuracy': 0.9342589628681178, 'top_1_accuracy': 0.7680657810499
| Total time | 114 mins | 500 mins| | Total time | 114 mins | 500 mins|
| Parameters (M) | 25.5 | 25.5 | | Parameters (M) | 25.5 | 25.5 |
| Checkpoint for Fine tuning | 197M (.ckpt file) |197M (.ckpt file) | | Checkpoint for Fine tuning | 197M (.ckpt file) |197M (.ckpt file) |
| Scripts | [Link](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/resnet) | [Link](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/resnet) | | Scripts | [Link](https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/official/cv/resnet) | [Link](https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/official/cv/resnet) |
#### ResNet101 on ImageNet2012 #### ResNet101 on ImageNet2012
| Parameters | Ascend 910 | GPU | | Parameters | Ascend 910 | GPU |
@ -449,15 +447,14 @@ result: {'top_5_accuracy': 0.9342589628681178, 'top_1_accuracy': 0.7680657810499
| Total time | 301 mins | 1100 mins| | Total time | 301 mins | 1100 mins|
| Parameters (M) | 44.6 | 44.6 | | Parameters (M) | 44.6 | 44.6 |
| Checkpoint for Fine tuning | 343M (.ckpt file) |343M (.ckpt file) | | Checkpoint for Fine tuning | 343M (.ckpt file) |343M (.ckpt file) |
| Scripts | [Link](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/resnet) | [Link](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/resnet) | | Scripts | [Link](https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/official/cv/resnet) | [Link](https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/official/cv/resnet) |
#### SE-ResNet50 on ImageNet2012 #### SE-ResNet50 on ImageNet2012
| Parameters | Ascend 910 | Parameters | Ascend 910
| -------------------------- | ------------------------------------------------------------------------ | | -------------------------- | ------------------------------------------------------------------------ |
| Model Version | SE-ResNet50 | | Model Version | SE-ResNet50 |
| Resource | Ascend 910，CPU 2.60GHz 56cores，Memory 314G | | Resource | Ascend 910，CPU 2.60GHz 56cores，Memory 314G |
| uploaded Date | 08/16/2020 (month/day/year) ； | | uploaded Date | 08/16/2020 (month/day/year) |
| MindSpore Version | 0.7.0-alpha | | MindSpore Version | 0.7.0-alpha |
| Dataset | ImageNet2012 | | Dataset | ImageNet2012 |
| Training Parameters | epoch=24, steps per epoch=5004, batch_size = 32 | | Training Parameters | epoch=24, steps per epoch=5004, batch_size = 32 |
@ -469,7 +466,62 @@ result: {'top_5_accuracy': 0.9342589628681178, 'top_1_accuracy': 0.7680657810499
| Total time | 49.3 mins | | Total time | 49.3 mins |
| Parameters (M) | 25.5 | | Parameters (M) | 25.5 |
| Checkpoint for Fine tuning | 215.9M (.ckpt file) | | Checkpoint for Fine tuning | 215.9M (.ckpt file) |
| Scripts | [Link](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/resnet) | | Scripts | [Link](https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/official/cv/resnet) |
### Inference Performance
#### ResNet50 on CIFAR-10
| Parameters | Ascend | GPU |
| ------------------- | --------------------------- | --------------------------- |
| Model Version | ResNet50-v1.5 | ResNet50-v1.5 |
| Resource | Ascend 910 | GPU |
| Uploaded Date | 04/01/2020 (month/day/year) | 08/01/2020 (month/day/year) |
| MindSpore Version | 0.1.0-alpha | 0.6.0-alpha |
| Dataset | CIFAR-10 | CIFAR-10 |
| batch_size | 32 | 32 |
| outputs | probability | probability |
| Accuracy | 91.44% | 91.37% |
| Model for inference | 91M (.air file) | |
#### ResNet50 on ImageNet2012
| Parameters | Ascend | GPU |
| ------------------- | --------------------------- | --------------------------- |
| Model Version | ResNet50-v1.5 | ResNet50-v1.5 |
| Resource | Ascend 910 | GPU |
| Uploaded Date | 04/01/2020 (month/day/year) | 08/01/2020 (month/day/year) |
| MindSpore Version | 0.1.0-alpha | 0.6.0-alpha |
| Dataset | ImageNet2012 | ImageNet2012 |
| batch_size | 256 | 32 |
| outputs | probability | probability |
| Accuracy | 76.70% | 76.74% |
| Model for inference | 98M (.air file) | |
#### ResNet101 on ImageNet2012
| Parameters | Ascend | GPU |
| ------------------- | --------------------------- | --------------------------- |
| Model Version | ResNet101 | ResNet101 |
| Resource | Ascend 910 | GPU |
| Uploaded Date | 04/01/2020 (month/day/year) | 08/01/2020 (month/day/year) |
| MindSpore Version | 0.1.0-alpha | 0.6.0-alpha |
| Dataset | ImageNet2012 | ImageNet2012 |
| batch_size | 32 | 32 |
| outputs | probability | probability |
| Accuracy | 78.53% | 78.64% |
| Model for inference | 171M (.air file) | |
#### SE-ResNet50 on ImageNet2012
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | SE-ResNet50 |
| Resource | Ascend 910 |
| Uploaded Date | 08/16/2020 (month/day/year) |
| MindSpore Version | 0.7.0-alpha |
| Dataset | ImageNet2012 |
| batch_size | 32 |
| outputs | probability |
| Accuracy | 76.80% |
| Model for inference | 109M (.air file) |
# [Description of Random Situation](#contents) # [Description of Random Situation](#contents)
@ -477,4 +529,4 @@ In dataset.py, we set the seed inside “create_dataset" function. We also use r
# [ModelZoo Homepage](#contents) # [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/r1.0/model_zoo).
Write Preview
Loading…
Cancel
Save