diff --git a/demo/auto_compression/image_classification/README.md b/demo/auto_compression/image_classification/README.md index 347012b09a621ceb8469178a02e73eee8739a20b..4a2c230960e4f70580175491fb1ace64ba30baf9 100644 --- a/demo/auto_compression/image_classification/README.md +++ b/demo/auto_compression/image_classification/README.md @@ -16,16 +16,40 @@ 本示例将以图像分类模型MobileNetV1为例，介绍如何使用PaddleClas中Inference部署模型进行自动压缩。本示例使用的自动压缩策略为量化训练和蒸馏。 ## 2. Benchmark -- PaddlePaddle MobileNetV1模型 -| 模型 | 策略 | Top-1 Acc | 耗时(ms) threads=4 | -|:------:|:------:|:------:|:------:| -| MobileNetV1 | Base模型 | 70.90 | 39.041 | -| MobileNetV1 | 量化+蒸馏 | 70.49 | 29.238| +### PaddleClas模型 -- 测试环境：`SDM710 2*A75(2.2GHz) 6*A55(1.7GHz)` - -- TensorFlow MobileNetV1模型 +| 模型 | 策略 | Top-1 Acc | GPU 耗时(ms) | ARM CPU 耗时(ms) | +|:------:|:------:|:------:|:------:|:------:| +| MobileNetV1 | Baseline | 70.90 | - | 33.15 | +| MobileNetV1 | 量化+蒸馏 | 70.49 | - | 13.64 | +| ResNet50_vd | Baseline | 79.12 | 3.19 | - | +| ResNet50_vd | 量化+蒸馏 | 78.55 | 0.92 | - | +| ShuffleNetV2_x1_0 | Baseline | 68.65 | - | 10.43 | +| ShuffleNetV2_x1_0 | 量化+蒸馏 | 67.78 | - | 5.51 | +| SqueezeNet1_0_infer | Baseline | 59.60 | - | 35.98 | +| SqueezeNet1_0_infer | 量化+蒸馏 | 59.13 | - | 16.96 | +| PPLCNetV2_base | Baseline | 76.86 | - | 36.50 | +| PPLCNetV2_base | 量化+蒸馏 | 76.43 | - | 15.79 | +| PPHGNet_tiny | Baseline | 79.59 | 2.82 | - | +| PPHGNet_tiny | 量化+蒸馏 | 79.19 | 0.98 | - | +| EfficientNetB0 | Baseline | 77.02 | 1.95 | - | +| EfficientNetB0 | 量化+蒸馏 | 73.61 | 1.44 | - | +| GhostNet_x1_0 | Baseline | 74.02 | 2.93 | - | +| GhostNet_x1_0 | 量化+蒸馏 | 71.11 | 1.03 | - | +| InceptionV3 | Baseline | 79.14 | 4.79 | - | +| InceptionV3 | 量化+蒸馏 | 73.16 | 1.47 | - | +| MobileNetV3_large_x1_0 | Baseline | 75.32 | - | 16.62 | +| MobileNetV3_large_x1_0 | 量化+蒸馏 | 68.84 | - | 9.85 | + +- ARM CPU 测试环境：`SDM865(4xA77+4xA55)` +- Nvidia GPU 测试环境： + - 硬件：NVIDIA Tesla T4 单卡 + - 软件：CUDA 11.2, cuDNN 8.0, TensorRT 8.4 + - 测试配置：batch_size: 1, image size: 224 + + +### TensorFlow MobileNetV1模型 | 模型 | 策略 | Top-1 Acc | 耗时(ms) threads=1 | Inference模型 | |:------:|:------:|:------:|:------:|:------:| @@ -35,14 +59,8 @@ - 测试环境：`骁龙865 4*A77 4*A55` 说明： -- MobileNetV1模型源自[tensorflow/models](http://download.tensorflow.org/models/mobilenet_v1_2018_02_22/mobilenet_v1_1.0_224.tgz)，通过[X2Paddle](https://github.com/PaddlePaddle/X2Paddle)工具转换MobileNetV1预测模型步骤： - -(1) 安装X2Paddle的1.3.6以上版本；（pip install x2paddle） - -(2) 转换模型： -x2paddle --framework=tensorflow --model=tf_model.pb --save_dir=pd_model +- MobileNetV1模型源自[tensorflow/models](http://download.tensorflow.org/models/mobilenet_v1_2018_02_22/mobilenet_v1_1.0_224.tgz) -即可得到MobileNetV1模型的预测模型（`model.pdmodel` 和 `model.pdiparams`）。如想快速体验，可直接下载上方表格中MobileNetV1的Base预测模型。 ## 3. 自动压缩流程 @@ -90,24 +108,11 @@ tar -xf MobileNetV1_infer.tar ```shell # 单卡启动 export CUDA_VISIBLE_DEVICES=0 -python run.py \ - --model_dir='MobileNetV1_infer' \ - --model_filename='inference.pdmodel' \ - --params_filename='inference.pdiparams' \ - --save_dir='./output' \ - --batch_size=128 \ - --config_path='./configs/mobilenetv1_qat_dis.yaml'\ - --data_dir='ILSVRC2012' - # 多卡启动 -python -m paddle.distributed.launch run.py \ - --model_dir='MobileNetV1_infer' \ - --model_filename='inference.pdmodel' \ - --params_filename='inference.pdiparams' \ - --save_dir='./output' \ - --batch_size=128 \ - --config_path='./configs/mobilenetv1_qat_dis.yaml'\ - --data_dir='ILSVRC2012' +export CUDA_VISIBLE_DEVICES=0,1,2,3 + +python run.py --save_dir='./save_quant_mobilev1/' --config_path='./configs/MobileNetV1/qat_dis.yaml' + ``` @@ -118,4 +123,3 @@ python -m paddle.distributed.launch run.py \ - [Paddle Lite部署](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.5/docs/deployment/lite/lite.md) ## 5.FAQ -[1.] 如果遇到报错 ```ValueError: var inputs not in this block``` ，则说明模型中的输入变量的名字不是 ```inputs``` ，可以先用netron可视化查看输入变量的名称，然后修改 ```run.py``` 中的第35行中 ``` yield {"inputs": imgs}``` 为 ```yield {${input_tensor_name}: imgs}```。一般PaddleClas产出部署模型的输入名字如果不是 ```inputs```，则是 ```x```。 diff --git a/demo/auto_compression/image_classification/configs/EfficientNetB0/prune_dis.yaml b/demo/auto_compression/image_classification/configs/EfficientNetB0/prune_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..999ac32b69b70954bc86543807a865548ede292a --- /dev/null +++ b/demo/auto_compression/image_classification/configs/EfficientNetB0/prune_dis.yaml @@ -0,0 +1,93 @@ +Global: + input_name: x + model_dir: EfficientNetB0_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_1.tmp_0 +ChannelPrune: + pruned_ratio: 0.25 + prune_params_name: + - _blocks.0._se_reduce_weights + - _blocks.0._se_expand_weights + - _blocks.0._project_conv_weights + - _blocks.1._expand_conv_weights + - _blocks.1._se_reduce_weights + - _blocks.1._se_expand_weights + - _blocks.1._project_conv_weights + - _blocks.2._expand_conv_weights + - _blocks.2._se_reduce_weights + - _blocks.2._se_expand_weights + - _blocks.2._project_conv_weights + - _blocks.3._expand_conv_weights + - _blocks.3._se_reduce_weights + - _blocks.3._se_expand_weights + - _blocks.3._project_conv_weights + - _blocks.4._expand_conv_weights + - _blocks.4._se_reduce_weights + - _blocks.4._se_expand_weights + - _blocks.4._project_conv_weights + - _blocks.5._expand_conv_weights + - _blocks.5._se_reduce_weights + - _blocks.5._se_expand_weights + - _blocks.5._project_conv_weights + - _blocks.6._expand_conv_weights + - _blocks.6._se_reduce_weights + - _blocks.6._se_expand_weights + - _blocks.6._project_conv_weights + - _blocks.7._expand_conv_weights + - _blocks.7._se_reduce_weights + - _blocks.7._se_expand_weights + - _blocks.7._project_conv_weights + - _blocks.8._expand_conv_weights + - _blocks.8._se_reduce_weights + - _blocks.8._se_expand_weights + - _blocks.8._project_conv_weights + - _blocks.9._expand_conv_weights + - _blocks.9._se_reduce_weights + - _blocks.9._se_expand_weights + - _blocks.9._project_conv_weights + - _blocks.10._expand_conv_weights + - _blocks.10._se_reduce_weights + - _blocks.10._se_expand_weights + - _blocks.10._project_conv_weights + - _blocks.11._expand_conv_weights + - _blocks.11._se_reduce_weights + - _blocks.11._se_expand_weights + - _blocks.11._project_conv_weights + - _blocks.12._expand_conv_weights + - _blocks.12._se_reduce_weights + - _blocks.12._se_expand_weights + - _blocks.12._project_conv_weights + - _blocks.13._expand_conv_weights + - _blocks.13._se_reduce_weights + - _blocks.13._se_expand_weights + - _blocks.13._project_conv_weights + - _blocks.14._expand_conv_weights + - _blocks.14._se_reduce_weights + - _blocks.14._se_expand_weights + - _blocks.14._project_conv_weights + - _blocks.15._expand_conv_weights + - _blocks.15._se_reduce_weights + - _blocks.15._se_expand_weights + - _blocks.15._project_conv_weights + - _conv_head_weights + criterion: l1_norm +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 500 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.7738 diff --git a/demo/auto_compression/image_classification/configs/EfficientNetB0/qat_dis.yaml b/demo/auto_compression/image_classification/configs/EfficientNetB0/qat_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..1738c9f70bff3cb99cc3a315c754fda4af29aaf1 --- /dev/null +++ b/demo/auto_compression/image_classification/configs/EfficientNetB0/qat_dis.yaml @@ -0,0 +1,37 @@ +Global: + input_name: x + model_dir: EfficientNetB0_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_1.tmp_0 +Quantization: + use_pact: true + activation_bits: 8 + is_full_quantize: false + activation_quantize_type: range_abs_max + weight_quantize_type: channel_wise_abs_max + not_quant_pattern: + - skip_quant + quantize_op_types: + - conv2d + - depthwise_conv2d + weight_bits: 8 +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.7738 diff --git a/demo/auto_compression/image_classification/configs/GhostNet_x1_0/prune_dis.yaml b/demo/auto_compression/image_classification/configs/GhostNet_x1_0/prune_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..44fcfc5332193e93dc3501e0ba70cfd499516545 --- /dev/null +++ b/demo/auto_compression/image_classification/configs/GhostNet_x1_0/prune_dis.yaml @@ -0,0 +1,69 @@ +Global: + input_name: inputs + model_dir: GhostNet_x1_0_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_0.tmp_0 +ChannelPrune: + pruned_ratio: 0.25 + criterion: l1_norm + prune_params_name: + - conv1_weights + - _ghostbottleneck_0_ghost_module_1_primary_conv_weights + - _ghostbottleneck_0_ghost_module_2_primary_conv_weights + - _ghostbottleneck_1_ghost_module_1_primary_conv_weights + - _ghostbottleneck_1_ghost_module_2_primary_conv_weights + - _ghostbottleneck_1_shortcut_conv_weights + - _ghostbottleneck_2_ghost_module_1_primary_conv_weights + - _ghostbottleneck_2_ghost_module_2_primary_conv_weights + - _ghostbottleneck_3_ghost_module_1_primary_conv_weights + - _ghostbottleneck_3_ghost_module_2_primary_conv_weights + - _ghostbottleneck_3_shortcut_conv_weights + - _ghostbottleneck_4_ghost_module_1_primary_conv_weights + - _ghostbottleneck_4_ghost_module_2_primary_conv_weights + - _ghostbottleneck_5_ghost_module_1_primary_conv_weights + - _ghostbottleneck_5_ghost_module_2_primary_conv_weights + - _ghostbottleneck_5_shortcut_conv_weights + - _ghostbottleneck_6_ghost_module_1_primary_conv_weights + - _ghostbottleneck_6_ghost_module_2_primary_conv_weights + - _ghostbottleneck_7_ghost_module_1_primary_conv_weights + - _ghostbottleneck_7_ghost_module_2_primary_conv_weights + - _ghostbottleneck_8_ghost_module_1_primary_conv_weights + - _ghostbottleneck_8_ghost_module_2_primary_conv_weights + - _ghostbottleneck_9_ghost_module_1_primary_conv_weights + - _ghostbottleneck_9_ghost_module_2_primary_conv_weights + - _ghostbottleneck_9_shortcut_conv_weights + - _ghostbottleneck_10_ghost_module_1_primary_conv_weights + - _ghostbottleneck_10_ghost_module_2_primary_conv_weights + - _ghostbottleneck_11_ghost_module_1_primary_conv_weights + - _ghostbottleneck_11_ghost_module_2_primary_conv_weights + - _ghostbottleneck_11_shortcut_conv_weights + - _ghostbottleneck_12_ghost_module_1_primary_conv_weights + - _ghostbottleneck_12_ghost_module_2_primary_conv_weights + - _ghostbottleneck_13_ghost_module_1_primary_conv_weights + - _ghostbottleneck_13_ghost_module_2_primary_conv_weights + - _ghostbottleneck_14_ghost_module_1_primary_conv_weights + - _ghostbottleneck_14_ghost_module_2_primary_conv_weights + - _ghostbottleneck_15_ghost_module_1_primary_conv_weights + - _ghostbottleneck_15_ghost_module_2_primary_conv_weights + - conv_last_weights + - fc_0_weights +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.7402 diff --git a/demo/auto_compression/image_classification/configs/GhostNet_x1_0/qat_dis.yaml b/demo/auto_compression/image_classification/configs/GhostNet_x1_0/qat_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f5b612b879fc5dc9a94d644cab351af022eea7b9 --- /dev/null +++ b/demo/auto_compression/image_classification/configs/GhostNet_x1_0/qat_dis.yaml @@ -0,0 +1,36 @@ +Global: + input_name: inputs + model_dir: GhostNet_x1_0_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_0.tmp_0 +Quantization: + use_pact: true + activation_bits: 8 + is_full_quantize: false + activation_quantize_type: range_abs_max + weight_quantize_type: channel_wise_abs_max + not_quant_pattern: + - skip_quant + quantize_op_types: + - conv2d + - depthwise_conv2d + weight_bits: 8 +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 diff --git a/demo/auto_compression/image_classification/configs/InceptionV3/prune_dis.yaml b/demo/auto_compression/image_classification/configs/InceptionV3/prune_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a7f0ef20987680db6d2475f2c883d6c6f87066b8 --- /dev/null +++ b/demo/auto_compression/image_classification/configs/InceptionV3/prune_dis.yaml @@ -0,0 +1,123 @@ +Global: + input_name: x + model_dir: InceptionV3_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_1.tmp_0 +ChannelPrune: + pruned_ratio: 0.25 + criterion: l1_norm + prune_params_name: + - conv2d_0.w_0 + - conv2d_1.w_0 + - conv2d_2.w_0 + - conv2d_3.w_0 + - conv2d_4.w_0 + - conv2d_5.w_0 + - conv2d_6.w_0 + - conv2d_7.w_0 + - conv2d_8.w_0 + - conv2d_9.w_0 + - conv2d_10.w_0 + - conv2d_11.w_0 + - conv2d_12.w_0 + - conv2d_13.w_0 + - conv2d_14.w_0 + - conv2d_15.w_0 + - conv2d_16.w_0 + - conv2d_17.w_0 + - conv2d_18.w_0 + - conv2d_19.w_0 + - conv2d_20.w_0 + - conv2d_21.w_0 + - conv2d_22.w_0 + - conv2d_23.w_0 + - conv2d_24.w_0 + - conv2d_25.w_0 + - conv2d_26.w_0 + - conv2d_27.w_0 + - conv2d_28.w_0 + - conv2d_29.w_0 + - conv2d_30.w_0 + - conv2d_31.w_0 + - conv2d_32.w_0 + - conv2d_33.w_0 + - conv2d_34.w_0 + - conv2d_35.w_0 + - conv2d_36.w_0 + - conv2d_37.w_0 + - conv2d_38.w_0 + - conv2d_39.w_0 + - conv2d_40.w_0 + - conv2d_41.w_0 + - conv2d_42.w_0 + - conv2d_43.w_0 + - conv2d_44.w_0 + - conv2d_45.w_0 + - conv2d_46.w_0 + - conv2d_47.w_0 + - conv2d_48.w_0 + - conv2d_49.w_0 + - conv2d_50.w_0 + - conv2d_51.w_0 + - conv2d_52.w_0 + - conv2d_53.w_0 + - conv2d_54.w_0 + - conv2d_55.w_0 + - conv2d_56.w_0 + - conv2d_57.w_0 + - conv2d_58.w_0 + - conv2d_59.w_0 + - conv2d_60.w_0 + - conv2d_61.w_0 + - conv2d_62.w_0 + - conv2d_63.w_0 + - conv2d_64.w_0 + - conv2d_65.w_0 + - conv2d_66.w_0 + - conv2d_67.w_0 + - conv2d_68.w_0 + - conv2d_69.w_0 + - conv2d_70.w_0 + - conv2d_71.w_0 + - conv2d_72.w_0 + - conv2d_73.w_0 + - conv2d_74.w_0 + - conv2d_75.w_0 + - conv2d_76.w_0 + - conv2d_77.w_0 + - conv2d_78.w_0 + - conv2d_79.w_0 + - conv2d_80.w_0 + - conv2d_81.w_0 + - conv2d_82.w_0 + - conv2d_83.w_0 + - conv2d_84.w_0 + - conv2d_85.w_0 + - conv2d_86.w_0 + - conv2d_87.w_0 + - conv2d_88.w_0 + - conv2d_89.w_0 + - conv2d_90.w_0 + - conv2d_91.w_0 + - conv2d_92.w_0 + - conv2d_93.w_0 +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.7914 diff --git a/demo/auto_compression/image_classification/configs/InceptionV3/qat_dis.yaml b/demo/auto_compression/image_classification/configs/InceptionV3/qat_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..80df97f85147a8f03094bc4334ace46c8dada9ee --- /dev/null +++ b/demo/auto_compression/image_classification/configs/InceptionV3/qat_dis.yaml @@ -0,0 +1,35 @@ +Global: + input_name: x + model_dir: InceptionV3_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 10.0 + loss: l2 + node: + - softmax_1.tmp_0 +Quantization: + is_full_quantize: false + activation_quantize_type: range_abs_max + weight_quantize_type: channel_wise_abs_max + not_quant_pattern: + - skip_quant + quantize_op_types: + - conv2d + - depthwise_conv2d + weight_bits: 8 +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.7914 diff --git a/demo/auto_compression/image_classification/configs/MobileNetV1/prune_dis.yaml b/demo/auto_compression/image_classification/configs/MobileNetV1/prune_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..1e338c02709df6942fdbeeaafaa1e4b10f5d197d --- /dev/null +++ b/demo/auto_compression/image_classification/configs/MobileNetV1/prune_dis.yaml @@ -0,0 +1,38 @@ +Global: + input_name: inputs + model_dir: MobileNetV1_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_0.tmp_0 +UnstructurePrune: + prune_strategy: gmp + prune_mode: ratio + ratio: 0.75 + gmp_config: + stable_iterations: 0 + pruning_iterations: 4500 + tunning_iterations: 4500 + resume_iteration: -1 + pruning_steps: 100 + initial_ratio: 0.15 + prune_params_type: conv1x1_only + local_sparsity: True +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 10000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.70898 diff --git a/demo/auto_compression/image_classification/configs/MobileNetV1/qat_dis.yaml b/demo/auto_compression/image_classification/configs/MobileNetV1/qat_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..33e8c807516a84faf9b6d88e4bf3b1c47e8a660c --- /dev/null +++ b/demo/auto_compression/image_classification/configs/MobileNetV1/qat_dis.yaml @@ -0,0 +1,37 @@ +Global: + input_name: inputs + model_dir: MobileNetV1_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /workspace/dataset/ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_0.tmp_0 +Quantization: + use_pact: true + activation_bits: 8 + is_full_quantize: false + activation_quantize_type: range_abs_max + weight_quantize_type: channel_wise_abs_max + not_quant_pattern: + - skip_quant + quantize_op_types: + - conv2d + - depthwise_conv2d + weight_bits: 8 +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 10000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.70898 diff --git a/demo/auto_compression/image_classification/configs/MobileNetV3_large_x1_0/prune_dis.yaml b/demo/auto_compression/image_classification/configs/MobileNetV3_large_x1_0/prune_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..6a4dddf7b6f82cd836a625b00841b3b85c7cfa73 --- /dev/null +++ b/demo/auto_compression/image_classification/configs/MobileNetV3_large_x1_0/prune_dis.yaml @@ -0,0 +1,38 @@ +Global: + input_name: inputs + model_dir: MobileNetV3_large_x1_0_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_0.tmp_0 +UnstructurePrune: + prune_strategy: gmp + prune_mode: ratio + ratio: 0.75 + gmp_config: + stable_iterations: 0 + pruning_iterations: 4500 + tunning_iterations: 4500 + resume_iteration: -1 + pruning_steps: 100 + initial_ratio: 0.15 + prune_params_type: conv1x1_only + local_sparsity: True +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.7532 diff --git a/demo/auto_compression/image_classification/configs/MobileNetV3_large_x1_0/qat_dis.yaml b/demo/auto_compression/image_classification/configs/MobileNetV3_large_x1_0/qat_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b65cf322aa14eb625fdf6d954c9053dc9a46c86b --- /dev/null +++ b/demo/auto_compression/image_classification/configs/MobileNetV3_large_x1_0/qat_dis.yaml @@ -0,0 +1,37 @@ +Global: + input_name: inputs + model_dir: MobileNetV3_large_x1_0_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_0.tmp_0 +Quantization: + activation_bits: 8 + is_full_quantize: false + use_pact: true + activation_quantize_type: range_abs_max + weight_quantize_type: channel_wise_abs_max + not_quant_pattern: + - skip_quant + quantize_op_types: + - conv2d + - depthwise_conv2d + weight_bits: 8 +TrainConfig: + epochs: 1 + eval_iter: 2000 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.0001 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.7532 diff --git a/demo/auto_compression/image_classification/configs/PPLCNetV2_base/prune_dis.yaml b/demo/auto_compression/image_classification/configs/PPLCNetV2_base/prune_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..907a21028bae70fc2f45ad9ac299084db9352694 --- /dev/null +++ b/demo/auto_compression/image_classification/configs/PPLCNetV2_base/prune_dis.yaml @@ -0,0 +1,38 @@ +Global: + input_name: x + model_dir: PPLCNetV2_base_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_1.tmp_0 +UnstructurePrune: + prune_strategy: gmp + prune_mode: ratio + ratio: 0.75 + gmp_config: + stable_iterations: 0 + pruning_iterations: 4500 + tunning_iterations: 4500 + resume_iteration: -1 + pruning_steps: 100 + initial_ratio: 0.15 + prune_params_type: conv1x1_only + local_sparsity: True +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.7704 diff --git a/demo/auto_compression/image_classification/configs/PPLCNetV2_base/qat_dis.yaml b/demo/auto_compression/image_classification/configs/PPLCNetV2_base/qat_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a83a52449578be0f3c9d3353b1b041ffd5e43cea --- /dev/null +++ b/demo/auto_compression/image_classification/configs/PPLCNetV2_base/qat_dis.yaml @@ -0,0 +1,37 @@ +Global: + input_name: x + model_dir: PPLCNetV2_base_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_1.tmp_0 +Quantization: + use_pact: true + activation_bits: 8 + is_full_quantize: false + activation_quantize_type: range_abs_max + weight_quantize_type: channel_wise_abs_max + not_quant_pattern: + - skip_quant + quantize_op_types: + - conv2d + - depthwise_conv2d + weight_bits: 8 +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.7704 diff --git a/demo/auto_compression/image_classification/configs/PPLCNet_x1_0/prune_dis.yaml b/demo/auto_compression/image_classification/configs/PPLCNet_x1_0/prune_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..aa3b74be8b07dd19333acef71e818d5ae1ad3664 --- /dev/null +++ b/demo/auto_compression/image_classification/configs/PPLCNet_x1_0/prune_dis.yaml @@ -0,0 +1,38 @@ +Global: + input_name: x + model_dir: PPLCNet_x1_0_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_1.tmp_0 +UnstructurePrune: + prune_strategy: gmp + prune_mode: ratio + ratio: 0.75 + gmp_config: + stable_iterations: 0 + pruning_iterations: 4500 + tunning_iterations: 4500 + resume_iteration: -1 + pruning_steps: 100 + initial_ratio: 0.15 + prune_params_type: conv1x1_only + local_sparsity: True +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.7132 diff --git a/demo/auto_compression/image_classification/configs/PPLCNet_x1_0/qat_dis.yaml b/demo/auto_compression/image_classification/configs/PPLCNet_x1_0/qat_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..73f9540a69e2146e4e046e4f186069c1fa0beef9 --- /dev/null +++ b/demo/auto_compression/image_classification/configs/PPLCNet_x1_0/qat_dis.yaml @@ -0,0 +1,37 @@ +Global: + input_name: x + model_dir: PPLCNet_x1_0_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_1.tmp_0 +Quantization: + use_pact: true + activation_bits: 8 + is_full_quantize: false + activation_quantize_type: range_abs_max + weight_quantize_type: channel_wise_abs_max + not_quant_pattern: + - skip_quant + quantize_op_types: + - conv2d + - depthwise_conv2d + weight_bits: 8 +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 10000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.7132 diff --git a/demo/auto_compression/image_classification/configs/ResNet50_vd/prune_dis.yaml b/demo/auto_compression/image_classification/configs/ResNet50_vd/prune_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ee4fed2c26a5a37e76ff9c217e7d37b3c6064746 --- /dev/null +++ b/demo/auto_compression/image_classification/configs/ResNet50_vd/prune_dis.yaml @@ -0,0 +1,84 @@ +Global: + input_name: inputs + model_dir: ResNet50_vd_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_0.tmp_0 +ChannelPrune: + pruned_ratio: 0.25 + criterion: l1_norm + prune_params_name: + - conv1_1_weights + - conv1_2_weights + - conv1_3_weights + - res2a_branch2a_weights + - res2a_branch2b_weights + - res2a_branch2c_weights + - res2a_branch1_weights + - res2b_branch2a_weights + - res2b_branch2b_weights + - res2b_branch2c_weights + - res2c_branch2a_weights + - res2c_branch2b_weights + - res2c_branch2c_weights + - res3a_branch2a_weights + - res3a_branch2b_weights + - res3a_branch2c_weights + - res3a_branch1_weights + - res3b_branch2a_weights + - res3b_branch2b_weights + - res3b_branch2c_weights + - res3c_branch2a_weights + - res3c_branch2b_weights + - res3c_branch2c_weights + - res3d_branch2a_weights + - res3d_branch2b_weights + - res3d_branch2c_weights + - res4a_branch2a_weights + - res4a_branch2b_weights + - res4a_branch2c_weights + - res4a_branch1_weights + - res4b_branch2a_weights + - res4b_branch2b_weights + - res4b_branch2c_weights + - res4c_branch2a_weights + - res4c_branch2b_weights + - res4c_branch2c_weights + - res4d_branch2a_weights + - res4d_branch2b_weights + - res4d_branch2c_weights + - res4e_branch2a_weights + - res4e_branch2b_weights + - res4e_branch2c_weights + - res4f_branch2a_weights + - res4f_branch2b_weights + - res4f_branch2c_weights + - res5a_branch2a_weights + - res5a_branch2b_weights + - res5a_branch2c_weights + - res5a_branch1_weights + - res5b_branch2a_weights + - res5b_branch2b_weights + - res5b_branch2c_weights + - res5c_branch2a_weights + - res5c_branch2b_weights + - res5c_branch2c_weights +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 500 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.7912 diff --git a/demo/auto_compression/image_classification/configs/ResNet50_vd/qat_dis.yaml b/demo/auto_compression/image_classification/configs/ResNet50_vd/qat_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..4d8ff6610275b4fe75415e03c4be0b7b88863c2f --- /dev/null +++ b/demo/auto_compression/image_classification/configs/ResNet50_vd/qat_dis.yaml @@ -0,0 +1,37 @@ +Global: + input_name: inputs + model_dir: ResNet50_vd_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_0.tmp_0 +Quantization: + use_pact: true + activation_bits: 8 + is_full_quantize: false + activation_quantize_type: range_abs_max + weight_quantize_type: channel_wise_abs_max + not_quant_pattern: + - skip_quant + quantize_op_types: + - conv2d + - depthwise_conv2d + weight_bits: 8 +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.7912 diff --git a/demo/auto_compression/image_classification/configs/ShuffleNetV2_x1_0/prune_dis.yaml b/demo/auto_compression/image_classification/configs/ShuffleNetV2_x1_0/prune_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0786dc4fc39ece86e97a87713c00473a1f387db5 --- /dev/null +++ b/demo/auto_compression/image_classification/configs/ShuffleNetV2_x1_0/prune_dis.yaml @@ -0,0 +1,38 @@ +Global: + input_name: inputs + model_dir: ShuffleNetV2_x1_0_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_0.tmp_0 +UnstructurePrune: + prune_strategy: gmp + prune_mode: ratio + ratio: 0.75 + gmp_config: + stable_iterations: 0 + pruning_iterations: 4500 + tunning_iterations: 4500 + resume_iteration: -1 + pruning_steps: 100 + initial_ratio: 0.15 + prune_params_type: conv1x1_only + local_sparsity: True +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.6880 diff --git a/demo/auto_compression/image_classification/configs/ShuffleNetV2_x1_0/qat_dis.yaml b/demo/auto_compression/image_classification/configs/ShuffleNetV2_x1_0/qat_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7b862d480d077d2f47c4627d2a09bb8b2c072a3a --- /dev/null +++ b/demo/auto_compression/image_classification/configs/ShuffleNetV2_x1_0/qat_dis.yaml @@ -0,0 +1,37 @@ +Global: + input_name: inputs + model_dir: ShuffleNetV2_x1_0_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_0.tmp_0 +Quantization: + use_pact: true + activation_bits: 8 + is_full_quantize: false + activation_quantize_type: range_abs_max + weight_quantize_type: channel_wise_abs_max + not_quant_pattern: + - skip_quant + quantize_op_types: + - conv2d + - depthwise_conv2d + weight_bits: 8 +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.6880 diff --git a/demo/auto_compression/image_classification/configs/SqueezeNet1_0/prune_dis.yaml b/demo/auto_compression/image_classification/configs/SqueezeNet1_0/prune_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f2a25b46e913c3b9894124d65d552a68d0ff1683 --- /dev/null +++ b/demo/auto_compression/image_classification/configs/SqueezeNet1_0/prune_dis.yaml @@ -0,0 +1,38 @@ +Global: + input_name: inputs + model_dir: SqueezeNet1_0_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_0.tmp_0 +UnstructurePrune: + prune_strategy: gmp + prune_mode: ratio + ratio: 0.75 + gmp_config: + stable_iterations: 0 + pruning_iterations: 4500 + tunning_iterations: 4500 + resume_iteration: -1 + pruning_steps: 100 + initial_ratio: 0.15 + prune_params_type: conv1x1_only + local_sparsity: True +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.596 diff --git a/demo/auto_compression/image_classification/configs/SqueezeNet1_0/qat_dis.yaml b/demo/auto_compression/image_classification/configs/SqueezeNet1_0/qat_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c0d380169f36e404399fa0b439737b06b39337e9 --- /dev/null +++ b/demo/auto_compression/image_classification/configs/SqueezeNet1_0/qat_dis.yaml @@ -0,0 +1,39 @@ +Global: + input_name: inputs + model_dir: SqueezeNet1_0_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_0.tmp_0 + teacher_model_dir: SqueezeNet1_0_infer + teacher_model_filename: inference.pdmodel + teacher_params_filename: inference.pdiparams +Quantization: + activation_bits: 8 + is_full_quantize: false + activation_quantize_type: range_abs_max + weight_quantize_type: channel_wise_abs_max + not_quant_pattern: + - skip_quant + quantize_op_types: + - conv2d + - depthwise_conv2d + weight_bits: 8 +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.596 \ No newline at end of file diff --git a/demo/auto_compression/image_classification/configs/SwinTransformer_base_patch4_window7_224/qat_dis.yaml b/demo/auto_compression/image_classification/configs/SwinTransformer_base_patch4_window7_224/qat_dis.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cf0b410fc068e5a2a80b199e838b37e8971c822d --- /dev/null +++ b/demo/auto_compression/image_classification/configs/SwinTransformer_base_patch4_window7_224/qat_dis.yaml @@ -0,0 +1,37 @@ +Global: + input_name: inputs + model_dir: SwinTransformer_base_patch4_window7_224_infer + model_filename: inference.pdmodel + params_filename: inference.pdiparams + batch_size: 32 + data_dir: /ILSVRC2012 + +Distillation: + alpha: 1.0 + loss: l2 + node: + - softmax_48.tmp_0 +Quantization: + use_pact: true + activation_bits: 8 + is_full_quantize: false + activation_quantize_type: range_abs_max + weight_quantize_type: channel_wise_abs_max + not_quant_pattern: + - skip_quant + quantize_op_types: + - conv2d + - depthwise_conv2d + weight_bits: 8 +TrainConfig: + epochs: 1 + eval_iter: 500 + learning_rate: + type: CosineAnnealingDecay + learning_rate: 0.015 + T_max: 5000 + optimizer_builder: + optimizer: + type: Momentum + weight_decay: 0.00002 + origin_metric: 0.83 diff --git a/demo/auto_compression/image_classification/configs/mobilenetv1_qat_dis.yaml b/demo/auto_compression/image_classification/configs/mobilenetv1_qat_dis.yaml deleted file mode 100644 index 6b48e525c19b8b4d48e49ea7ce79aed33f4137fc..0000000000000000000000000000000000000000 --- a/demo/auto_compression/image_classification/configs/mobilenetv1_qat_dis.yaml +++ /dev/null @@ -1,23 +0,0 @@ -Distillation: - alpha: 1.0 - loss: l2 -Quantization: - activation_bits: 8 - is_full_quantize: false - activation_quantize_type: range_abs_max - weight_quantize_type: abs_max - not_quant_pattern: - - skip_quant - quantize_op_types: - - conv2d - - depthwise_conv2d - weight_bits: 8 -TrainConfig: - epochs: 1 - eval_iter: 500 - learning_rate: 0.004 - optimizer_builder: - optimizer: - type: Momentum - weight_decay: 0.00003 - origin_metric: 0.70898 diff --git a/demo/auto_compression/image_classification/run.py b/demo/auto_compression/image_classification/run.py index 817afa1d11327362ee8c255dcea301797d4f930a..72e31d526b50972fa18071746d6748e2353dac49 100644 --- a/demo/auto_compression/image_classification/run.py +++ b/demo/auto_compression/image_classification/run.py @@ -10,34 +10,38 @@ import numpy as np import paddle import paddle.nn as nn from paddle.io import Dataset, BatchSampler, DataLoader -import imagenet_reader as pd_imagenet_reader -import tf_imagenet_reader -from paddleslim.auto_compression.config_helpers import load_config +import imagenet_reader as reader +from paddleslim.auto_compression.config_helpers import load_config as load_slim_config from paddleslim.auto_compression import AutoCompression from utility import add_arguments, print_arguments -parser = argparse.ArgumentParser(description=__doc__) -add_arg = functools.partial(add_arguments, argparser=parser) - -# yapf: disable -add_arg('model_dir', str, None, "inference model directory.") -add_arg('model_filename', str, None, "inference model filename.") -add_arg('params_filename', str, None, "inference params filename.") -add_arg('save_dir', str, None, "directory to save compressed model.") -add_arg('batch_size', int, 1, "train batch size.") -add_arg('config_path', str, None, "path of compression strategy config.") -add_arg('data_dir', str, None, "path of dataset") -add_arg('input_name', str, "inputs", "input name of the model") -add_arg('input_shape', int, [3,224,224], "input shape of the model except batch_size", nargs='+') -add_arg('image_reader_type', str, "paddle", "the preprocess of data. choice in [\"paddle\", \"tensorflow\"]") - - +def argsparser(): + parser = argparse.ArgumentParser(description=__doc__) + parser.add_argument( + '--config_path', + type=str, + default=None, + help="path of compression strategy config.", + required=True) + parser.add_argument( + '--save_dir', + type=str, + default='output', + help="directory to save compressed model.") + return parser + + +def print_arguments(args): + print('----------- Running Arguments -----------') + for arg, value in sorted(vars(args).items()): + print('%s: %s' % (arg, value)) + print('------------------------------------------') + # yapf: enable -def reader_wrapper(reader, input_name, input_shape): +def reader_wrapper(reader, input_name): def gen(): for i, data in enumerate(reader()): imgs = np.float32([item[0] for item in data]) - imgs = imgs.reshape([len(data)] + input_shape) yield {input_name: imgs} return gen @@ -50,9 +54,9 @@ def eval_reader(data_dir, batch_size): def eval_function(exe, compiled_test_program, test_feed_names, test_fetch_list): - val_reader = eval_reader(data_dir, batch_size=args.batch_size) + val_reader = eval_reader(data_dir, batch_size=global_config['batch_size']) image = paddle.static.data( - name=args.input_name, shape=[None] + args.input_shape, dtype='float32') + name=global_config['input_name'], shape=[None, 3, 224, 224], dtype='float32') label = paddle.static.data(name='label', shape=[None, 1], dtype='int64') results = [] @@ -60,7 +64,7 @@ def eval_function(exe, compiled_test_program, test_feed_names, test_fetch_list): # top1_acc, top5_acc if len(test_feed_names) == 1: image = np.array([[d[0]] for d in data]) - image = image.reshape([len(data)] + args.input_shape) + image = image.reshape((len(data), 3, 224, 224)) label = [[d[1]] for d in data] pred = exe.run(compiled_test_program, feed={test_feed_names[0]: image}, @@ -80,8 +84,7 @@ def eval_function(exe, compiled_test_program, test_feed_names, test_fetch_list): else: # eval "eval model", which inputs are image and label, output is top1 and top5 accuracy image = np.array([[d[0]] for d in data]) - image = image.reshape([len(data)] + args.input_shape) - label = [[d[1]] for d in data] + image = image.reshape((len(data), 3, 224, 224)) label = [[d[1]] for d in data] result = exe.run( compiled_test_program, @@ -96,35 +99,33 @@ def eval_function(exe, compiled_test_program, test_feed_names, test_fetch_list): return result[0] -if __name__ == '__main__': - args = parser.parse_args() - print_arguments(args) - paddle.enable_static() - data_dir = args.data_dir +def main(): + global global_config + all_config = load_slim_config(args.config_path) + assert "Global" in all_config, f"Key 'Global' not found in config file. \n{all_config}" + global_config = all_config["Global"] + global data_dir + data_dir = global_config['data_dir'] - if args.image_reader_type == 'paddle': - reader = pd_imagenet_reader - elif args.image_reader_type == 'tensorflow': - reader = tf_imagenet_reader - else: - raise NotImplementedError( - "image_reader_type only can be set to paddle or tensorflow, but now is {}". - format(args.image_reader_type)) train_reader = paddle.batch( - reader.train(data_dir=data_dir), batch_size=args.batch_size) - train_dataloader = reader_wrapper(train_reader, args.input_name, - args.input_shape) + reader.train(data_dir=data_dir), batch_size=global_config['batch_size']) + train_dataloader = reader_wrapper(train_reader, global_config['input_name']) ac = AutoCompression( - model_dir=args.model_dir, - model_filename=args.model_filename, - params_filename=args.params_filename, + model_dir=global_config['model_dir'], + model_filename=global_config['model_filename'], + params_filename=global_config['params_filename'], save_dir=args.save_dir, - config=args.config_path, + config=all_config, train_dataloader=train_dataloader, eval_callback=eval_function, - eval_dataloader=reader_wrapper( - eval_reader(data_dir, args.batch_size), args.input_name, - args.input_shape)) + eval_dataloader=reader_wrapper(eval_reader(data_dir, global_config['batch_size']), global_config['input_name'])) ac.compress() + +if __name__ == '__main__': + paddle.enable_static() + parser = argsparser() + args = parser.parse_args() + print_arguments(args) + main() diff --git a/paddleslim/auto_compression/compressor.py b/paddleslim/auto_compression/compressor.py index 08ae28f069e4470967b7ee8a9641b0d72ed91c96..17e052bcccdcc208d2baba273fa7450e71759273 100644 --- a/paddleslim/auto_compression/compressor.py +++ b/paddleslim/auto_compression/compressor.py @@ -729,21 +729,24 @@ class AutoCompression: test_program_info.feed_target_names, test_program_info.fetch_targets) - _logger.info( - "epoch: {} metric of compressed model is: {:.6f}, best metric of compressed model is {:.6f}". - format(epoch_id, metric, best_metric)) - if metric > best_metric: paddle.static.save( program=test_program_info.program._program, model_path=os.path.join(self.tmp_dir, 'best_model')) best_metric = metric + _logger.info( + "epoch: {} metric of compressed model is: {:.6f}, best metric of compressed model is {:.6f}". + format(epoch_id, metric, best_metric)) if self.metric_before_compressed is not None and float( abs(best_metric - self.metric_before_compressed) ) / self.metric_before_compressed <= 0.005: break + else: + _logger.info( + "epoch: {} metric of compressed model is: {:.6f}, best metric of compressed model is {:.6f}". + format(epoch_id, metric, best_metric)) if train_config.target_metric is not None: if metric > float(train_config.target_metric): break