From 0e1f2a686591946f6f4c950c8754ea3f0e6b175a Mon Sep 17 00:00:00 2001 From: Guanghua Yu <742925032@qq.com> Date: Thu, 11 Aug 2022 15:29:17 +0800 Subject: [PATCH] add picodet-npu model (#6622) * add picodet-npu model * fix modelingf --- configs/picodet/README.md | 8 ++ configs/picodet/picodet_s_416_coco_npu.yml | 106 +++++++++++++++++++++ ppdet/modeling/backbones/lcnet.py | 39 +++++--- ppdet/modeling/heads/pico_head.py | 2 + 4 files changed, 142 insertions(+), 13 deletions(-) create mode 100644 configs/picodet/picodet_s_416_coco_npu.yml diff --git a/configs/picodet/README.md b/configs/picodet/README.md index b65624283..4b5dd9ed1 100644 --- a/configs/picodet/README.md +++ b/configs/picodet/README.md @@ -6,6 +6,8 @@ ## 最新动态 +- 发布PicoDet-NPU模型，支持模型全量化部署。**（2022.08.10）** + - 发布全新系列PP-PicoDet模型：**（2022.03.20）** - (1)引入TAL及ETA Head，优化PAN等结构，精度提升2个点以上； - (2)优化CPU端预测速度，同时训练速度提升一倍； @@ -45,6 +47,12 @@ PP-PicoDet模型有如下特点： | PicoDet-L | 416*416 | 39.4 | 55.7 | 5.80 | 7.10 | 20.7ms | 42.23ms | [model](https://paddledet.bj.bcebos.com/models/picodet_l_416_coco_lcnet.pdparams) | [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_416_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_416_coco_lcnet.yml) | [w/ 后处理](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_l_416_coco_lcnet.tar) | [w/o 后处理](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_l_416_coco_lcnet_non_postprocess.tar) | | PicoDet-L | 640*640 | 42.6 | 59.2 | 5.80 | 16.81 | 62.5ms | 108.1ms | [model](https://paddledet.bj.bcebos.com/models/picodet_l_640_coco_lcnet.pdparams) | [log](https://paddledet.bj.bcebos.com/logs/train_picodet_l_640_coco_lcnet.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_l_640_coco_lcnet.yml) | [w/ 后处理](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_l_640_coco_lcnet.tar) | [w/o 后处理](https://paddledet.bj.bcebos.com/deploy/Inference/picodet_l_640_coco_lcnet_non_postprocess.tar) | +- 特色模型 + +| 模型 | 输入尺寸 | mAPval
0.5:0.95 | mAPval
0.5 | 参数量
(M) | FLOPS
(G) | 预测时延[CPU](#latency)
(ms) | 预测时延[Lite](#latency)
(ms) | 权重下载 | 配置文件 | +| :-------- | :--------: | :---------------------: | :----------------: | :----------------: | :---------------: | :-----------------------------: | :-----------------------------: | :----------------------------------------: | :--------------------------------------- | +| PicoDet-S-NPU | 416*416 | 30.1 | 44.2 | - | - | - | - | [model](https://paddledet.bj.bcebos.com/models/picodet_s_416_coco_npu.pdparams) | [log](https://paddledet.bj.bcebos.com/logs/train_picodet_s_416_coco_npu.log) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet/picodet_s_416_coco_npu.yml) | +
注意事项: diff --git a/configs/picodet/picodet_s_416_coco_npu.yml b/configs/picodet/picodet_s_416_coco_npu.yml new file mode 100644 index 000000000..761cfde11 --- /dev/null +++ b/configs/picodet/picodet_s_416_coco_npu.yml @@ -0,0 +1,106 @@ +_BASE_: [ + '../datasets/coco_detection.yml', + '../runtime.yml', + '_base_/picodet_v2.yml', + '_base_/optimizer_300e.yml', +] + +pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/legendary_models/PPLCNet_x0_75_pretrained.pdparams +weights: output/picodet_s_416_coco/best_model +find_unused_parameters: True +keep_best_weight: True +use_ema: True +epoch: 300 +snapshot_epoch: 10 + +PicoDet: + backbone: LCNet + neck: CSPPAN + head: PicoHeadV2 + +LCNet: + scale: 0.75 + feature_maps: [3, 4, 5] + act: relu6 + +CSPPAN: + out_channels: 96 + use_depthwise: True + num_csp_blocks: 1 + num_features: 4 + act: relu6 + +PicoHeadV2: + conv_feat: + name: PicoFeat + feat_in: 96 + feat_out: 96 + num_convs: 4 + num_fpn_stride: 4 + norm_type: bn + share_cls_reg: True + use_se: True + act: relu6 + feat_in_chan: 96 + act: relu6 + +LearningRate: + base_lr: 0.2 + schedulers: + - !CosineDecay + max_epochs: 300 + min_lr_ratio: 0.08 + last_plateau_epochs: 30 + - !ExpWarmup + epochs: 2 + +worker_num: 6 +eval_height: &eval_height 416 +eval_width: &eval_width 416 +eval_size: &eval_size [*eval_height, *eval_width] + +TrainReader: + sample_transforms: + - Decode: {} + - Mosaic: + prob: 0.6 + input_dim: [640, 640] + degrees: [-10, 10] + scale: [0.1, 2.0] + shear: [-2, 2] + translate: [-0.1, 0.1] + enable_mixup: True + - AugmentHSV: {is_bgr: False, hgain: 5, sgain: 30, vgain: 30} + - RandomFlip: {prob: 0.5} + batch_transforms: + - BatchRandomResize: {target_size: [320, 352, 384, 416, 448, 480, 512], random_size: True, random_interp: True, keep_ratio: False} + - NormalizeImage: {mean: [0, 0, 0], std: [1, 1, 1], is_scale: True} + - Permute: {} + - PadGT: {} + batch_size: 40 + shuffle: true + drop_last: true + mosaic_epoch: 180 + + +EvalReader: + sample_transforms: + - Decode: {} + - Resize: {interp: 2, target_size: *eval_size, keep_ratio: False} + - NormalizeImage: {mean: [0, 0, 0], std: [1, 1, 1], is_scale: True} + - Permute: {} + batch_transforms: + - PadBatch: {pad_to_stride: 32} + batch_size: 8 + shuffle: false + + +TestReader: + inputs_def: + image_shape: [1, 3, *eval_height, *eval_width] + sample_transforms: + - Decode: {} + - Resize: {interp: 2, target_size: *eval_size, keep_ratio: False} + - NormalizeImage: {mean: [0, 0, 0], std: [1, 1, 1], is_scale: True} + - Permute: {} + batch_size: 1 diff --git a/ppdet/modeling/backbones/lcnet.py b/ppdet/modeling/backbones/lcnet.py index 4242b4c81..76da139ee 100644 --- a/ppdet/modeling/backbones/lcnet.py +++ b/ppdet/modeling/backbones/lcnet.py @@ -68,7 +68,8 @@ class ConvBNLayer(nn.Layer): filter_size, num_filters, stride, - num_groups=1): + num_groups=1, + act='hard_swish'): super().__init__() self.conv = Conv2D( @@ -85,12 +86,15 @@ class ConvBNLayer(nn.Layer): num_filters, weight_attr=ParamAttr(regularizer=L2Decay(0.0)), bias_attr=ParamAttr(regularizer=L2Decay(0.0))) - self.hardswish = nn.Hardswish() + if act == 'hard_swish': + self.act = nn.Hardswish() + elif act == 'relu6': + self.act = nn.ReLU6() def forward(self, x): x = self.conv(x) x = self.bn(x) - x = self.hardswish(x) + x = self.act(x) return x @@ -100,7 +104,8 @@ class DepthwiseSeparable(nn.Layer): num_filters, stride, dw_size=3, - use_se=False): + use_se=False, + act='hard_swish'): super().__init__() self.use_se = use_se self.dw_conv = ConvBNLayer( @@ -108,14 +113,16 @@ class DepthwiseSeparable(nn.Layer): num_filters=num_channels, filter_size=dw_size, stride=stride, - num_groups=num_channels) + num_groups=num_channels, + act=act) if use_se: self.se = SEModule(num_channels) self.pw_conv = ConvBNLayer( num_channels=num_channels, filter_size=1, num_filters=num_filters, - stride=1) + stride=1, + act=act) def forward(self, x): x = self.dw_conv(x) @@ -158,7 +165,7 @@ class SEModule(nn.Layer): @register @serializable class LCNet(nn.Layer): - def __init__(self, scale=1.0, feature_maps=[3, 4, 5]): + def __init__(self, scale=1.0, feature_maps=[3, 4, 5], act='hard_swish'): super().__init__() self.scale = scale self.feature_maps = feature_maps @@ -169,7 +176,8 @@ class LCNet(nn.Layer): num_channels=3, filter_size=3, num_filters=make_divisible(16 * scale), - stride=2) + stride=2, + act=act) self.blocks2 = nn.Sequential(* [ DepthwiseSeparable( @@ -177,7 +185,8 @@ class LCNet(nn.Layer): num_filters=make_divisible(out_c * scale), dw_size=k, stride=s, - use_se=se) + use_se=se, + act=act) for i, (k, in_c, out_c, s, se) in enumerate(NET_CONFIG["blocks2"]) ]) @@ -187,7 +196,8 @@ class LCNet(nn.Layer): num_filters=make_divisible(out_c * scale), dw_size=k, stride=s, - use_se=se) + use_se=se, + act=act) for i, (k, in_c, out_c, s, se) in enumerate(NET_CONFIG["blocks3"]) ]) @@ -200,7 +210,8 @@ class LCNet(nn.Layer): num_filters=make_divisible(out_c * scale), dw_size=k, stride=s, - use_se=se) + use_se=se, + act=act) for i, (k, in_c, out_c, s, se) in enumerate(NET_CONFIG["blocks4"]) ]) @@ -213,7 +224,8 @@ class LCNet(nn.Layer): num_filters=make_divisible(out_c * scale), dw_size=k, stride=s, - use_se=se) + use_se=se, + act=act) for i, (k, in_c, out_c, s, se) in enumerate(NET_CONFIG["blocks5"]) ]) @@ -226,7 +238,8 @@ class LCNet(nn.Layer): num_filters=make_divisible(out_c * scale), dw_size=k, stride=s, - use_se=se) + use_se=se, + act=act) for i, (k, in_c, out_c, s, se) in enumerate(NET_CONFIG["blocks6"]) ]) diff --git a/ppdet/modeling/heads/pico_head.py b/ppdet/modeling/heads/pico_head.py index a63e7c90c..07cc3c7ca 100644 --- a/ppdet/modeling/heads/pico_head.py +++ b/ppdet/modeling/heads/pico_head.py @@ -155,6 +155,8 @@ class PicoFeat(nn.Layer): x = F.leaky_relu(x) elif self.act == "hard_swish": x = F.hardswish(x) + elif self.act == "relu6": + x = F.relu6(x) return x def forward(self, fpn_feat, stage_idx): -- GitLab