{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"# NowcastNet: 融入物理机制的生成式短临降水预报模型\n",
"\n",
"[](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/master/mindearth/zh_cn/nowcasting/mindspore_Nowcastnet.ipynb) [](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/master/mindearth/zh_cn/nowcasting/mindspore_Nowcastnet.py) [](https://gitee.com/mindspore/docs/blob/master/docs/mindearth/docs/source_zh_cn/nowcasting/Nowcastnet.ipynb)\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"## 概述\n",
"\n",
"NowcastNet是由清华大学龙明盛老师团队开发的一个基于雷达数据的短临降水预报模型。 它提供了0-3h的短临降水预报结果，空间分辨率为1km左右。\n",
"该模型主要分为evolution和generation两大模块，其中evolution模块融入了物理机制，给出一个粗糙的预测结果。接着，generation模块在此\n",
"基础上生成精细化的结果，从而得到最终的降水预报。模型框架图入下图所示(图片来源于论文 [Skilful nowcasting of extreme precipitation with NowcastNet](https://www.nature.com/articles/s41586-023-06184-4))\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"## NowcastNet\n",
"\n",
"NowcastNet网络框架如下图所示\n",
"\n",
"\n",
"\n",
"1. Evolution network：融入物理机制，以历史的$x_{-T:0}$为输入，通过U-Net预测动量$v$和残差$s$，再经过evolution operator得到预测$x_{1:T}^{''}$。形式如下：\n",
"\n",
"$$\n",
"x_{1:T}^{''} = Evolution(x_{-T:0})\n",
"$$\n",
"\n",
"2. Nowcast encoder & decoder：采用[Semantic Image Synthesis with Spatially-Adaptive Normalization](https://openaccess.thecvf.com/content_CVPR_2019/papers/Park_Semantic_Image_Synthesis_With_Spatially-Adaptive_Normalization_CVPR_2019_paper.pdf)架构把Evolution network的输出$x_{1:T}^{''}$做为conditioning进行GAN训练。"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"## 技术路径\n",
"\n",
"MindSpore Earth求解该问题的具体流程如下:\n",
"\n",
"1. 创建数据集\n",
"2. 模型构建\n",
"3. 损失函数\n",
"4. 模型训练\n",
"5. 模型评估与可视化"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"训练和测试所用的数据集可以在: [Nowcastnet/dataset](https://download-mindspore.osinfra.cn/mindscience/mindearth/dataset/nowcastnet/tiny_datasets/) 下载"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"ExecuteTime": {
"end_time": "2024-01-30T12:21:07.849115100Z",
"start_time": "2024-01-30T12:21:01.986652Z"
},
"collapsed": false
},
"outputs": [],
"source": [
"import random\n",
"\n",
"import mindspore as ms\n",
"import numpy as np\n",
"from mindspore import context, nn, amp, set_seed, load_checkpoint, load_param_into_net"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"ExecuteTime": {
"end_time": "2024-01-31T05:59:25.475709500Z",
"start_time": "2024-01-31T05:59:25.432825200Z"
},
"collapsed": false
},
"outputs": [],
"source": [
"from src import get_logger\n",
"from src import EvolutionTrainer, GenerationTrainer, GenerateLoss, DiscriminatorLoss, EvolutionLoss\n",
"from src import EvolutionPredictor, GenerationPredictor\n",
"from src import RadarData, NowcastDataset\n",
"from src.evolution import EvolutionNet\n",
"from src.generator import GenerationNet\n",
"from src.discriminator import TemporalDiscriminator\n",
"from src.visual import plt_img\n",
"from mindearth.utils.tools import load_yaml_config"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"ExecuteTime": {
"end_time": "2024-01-30T12:21:12.488547200Z",
"start_time": "2024-01-30T12:21:12.479570700Z"
},
"collapsed": false
},
"outputs": [],
"source": [
"np.random.seed(0)\n",
"set_seed(0)\n",
"random.seed(0)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"ExecuteTime": {
"end_time": "2024-01-30T12:21:14.948562900Z",
"start_time": "2024-01-30T12:21:14.931578100Z"
},
"collapsed": false
},
"outputs": [],
"source": [
"config = load_yaml_config(\"./configs/Nowcastnet.yaml\")\n",
"context.set_context(mode=context.GRAPH_MODE, device_target=\"Ascend\", device_id=1)"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"## 创建数据集\n",
"\n",
"在[dataset](https://download-mindspore.osinfra.cn/mindscience/mindearth/dataset/nowcastnet/tiny_datasets/)路径下，下载训练数据集，验证数据集到`./dataset`目录，修改[Nowcastnet.yaml](https://gitee.com/mindspore/mindscience/blob/master/MindEarth/applications/nowcasting/Nowcastnet/configs/Nowcastnet.yaml)配置文件中的`root_dir`。\n",
"\n",
"`./dataset`中的目录结构如下所示：\n",
"\n",
"```markdown\n",
"├── train\n",
"├── valid\n",
"├── test\n",
"```"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"## Evolution"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"ExecuteTime": {
"end_time": "2024-01-30T12:21:28.111872100Z",
"start_time": "2024-01-30T12:21:19.226508600Z"
},
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-01-30 20:21:45,539 - utils.py[line:55] - INFO: {'name': 'NowcastNet', 'ngf': 32, 'pool_ensemble_num': 4, 'module_name': 'generation'}\n",
"2024-01-30 20:21:45,539 - utils.py[line:55] - INFO: {'name': 'us', 'root_dir': './datasets', 't_in': 9, 't_out': 20, 'h_size': 512, 'w_size': 512, 'time_interval': 10, 'num_workers': 1, 'data_sink': False, 'batch_size': 1, 'noise_scale': 32}\n",
"2024-01-30 20:21:45,540 - utils.py[line:55] - INFO: {'name': 'adam', 'beta1': 0.01, 'beta2': 0.9, 'g_lr': 1.5e-05, 'd_lr': '6e-5', 'epochs': 10}\n",
"2024-01-30 20:21:45,541 - utils.py[line:55] - INFO: {'name': 'adam', 'lr': 0.001, 'weight_decay': 0.1, 'gamma': 0.5, 'epochs': 5}\n",
"2024-01-30 20:21:45,541 - utils.py[line:55] - INFO: {'summary_dir': './summary/', 'eval_interval': 2, 'save_checkpoint_epochs': 2, 'keep_checkpoint_max': 4, 'key_info_timestep': [10, 60, 120], 'generate_ckpt_path': '', 'evolution_ckpt_path': '', 'visual': True, 'csin_threshold': 16}\n",
"2024-01-30 20:21:45,542 - utils.py[line:55] - INFO: {'distribute': False, 'mixed_precision': True, 'amp_level': 'O2', 'load_ckpt': False}\n"
]
},
{
"data": {
"text/plain": [
"EvolutionNet<\n",
" (evo_net): EvolutionNetwork<\n",
" (inc): DoubleConv<\n",
" (single_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=9, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.inc.single_conv.0.gamma, shape=(9,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.inc.single_conv.0.beta, shape=(9,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.inc.single_conv.0.moving_mean, shape=(9,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.inc.single_conv.0.moving_variance, shape=(9,), dtype=Float32, requires_grad=False)>\n",
" (1): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=9, output_channels=32, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe7c6c2df0>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe777e12b0>, format=NCHW>\n",
" >\n",
" >\n",
" (double_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=9, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.inc.double_conv.0.gamma, shape=(9,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.inc.double_conv.0.beta, shape=(9,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.inc.double_conv.0.moving_mean, shape=(9,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.inc.double_conv.0.moving_variance, shape=(9,), dtype=Float32, requires_grad=False)>\n",
" (1): ReLU<>\n",
" (2): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=9, output_channels=32, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe777f1d90>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe777f1f10>, format=NCHW>\n",
" >\n",
" (3): BatchNorm2d<num_features=32, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.inc.double_conv.3.gamma, shape=(32,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.inc.double_conv.3.beta, shape=(32,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.inc.double_conv.3.moving_mean, shape=(32,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.inc.double_conv.3.moving_variance, shape=(32,), dtype=Float32, requires_grad=False)>\n",
" (4): ReLU<>\n",
" (5): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=32, output_channels=32, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74306640>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe743067c0>, format=NCHW>\n",
" >\n",
" >\n",
" >\n",
" (down1): Down<\n",
" (maxpool_conv): SequentialCell<\n",
" (0): MaxPool2d<kernel_size=2, stride=2, pad_mode=VALID>\n",
" (1): DoubleConv<\n",
" (single_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=32, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.down1.maxpool_conv.1.single_conv.0.gamma, shape=(32,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.down1.maxpool_conv.1.single_conv.0.beta, shape=(32,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.down1.maxpool_conv.1.single_conv.0.moving_mean, shape=(32,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.down1.maxpool_conv.1.single_conv.0.moving_variance, shape=(32,), dtype=Float32, requires_grad=False)>\n",
" (1): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=32, output_channels=64, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74306a30>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74306a60>, format=NCHW>\n",
" >\n",
" >\n",
" (double_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=32, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.down1.maxpool_conv.1.double_conv.0.gamma, shape=(32,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.down1.maxpool_conv.1.double_conv.0.beta, shape=(32,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.down1.maxpool_conv.1.double_conv.0.moving_mean, shape=(32,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.down1.maxpool_conv.1.double_conv.0.moving_variance, shape=(32,), dtype=Float32, requires_grad=False)>\n",
" (1): ReLU<>\n",
" (2): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=32, output_channels=64, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74306c10>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe7cec2e20>, format=NCHW>\n",
" >\n",
" (3): BatchNorm2d<num_features=64, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.down1.maxpool_conv.1.double_conv.3.gamma, shape=(64,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.down1.maxpool_conv.1.double_conv.3.beta, shape=(64,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.down1.maxpool_conv.1.double_conv.3.moving_mean, shape=(64,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.down1.maxpool_conv.1.double_conv.3.moving_variance, shape=(64,), dtype=Float32, requires_grad=False)>\n",
" (4): ReLU<>\n",
" (5): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=64, output_channels=64, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74306e80>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74306f40>, format=NCHW>\n",
" >\n",
" >\n",
" >\n",
" >\n",
" >\n",
" (down2): Down<\n",
" (maxpool_conv): SequentialCell<\n",
" (0): MaxPool2d<kernel_size=2, stride=2, pad_mode=VALID>\n",
" (1): DoubleConv<\n",
" (single_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=64, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.down2.maxpool_conv.1.single_conv.0.gamma, shape=(64,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.down2.maxpool_conv.1.single_conv.0.beta, shape=(64,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.down2.maxpool_conv.1.single_conv.0.moving_mean, shape=(64,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.down2.maxpool_conv.1.single_conv.0.moving_variance, shape=(64,), dtype=Float32, requires_grad=False)>\n",
" (1): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=64, output_channels=128, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe742d1070>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe742d11c0>, format=NCHW>\n",
" >\n",
" >\n",
" (double_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=64, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.down2.maxpool_conv.1.double_conv.0.gamma, shape=(64,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.down2.maxpool_conv.1.double_conv.0.beta, shape=(64,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.down2.maxpool_conv.1.double_conv.0.moving_mean, shape=(64,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.down2.maxpool_conv.1.double_conv.0.moving_variance, shape=(64,), dtype=Float32, requires_grad=False)>\n",
" (1): ReLU<>\n",
" (2): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=64, output_channels=128, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe742d1490>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe742d1550>, format=NCHW>\n",
" >\n",
" (3): BatchNorm2d<num_features=128, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.down2.maxpool_conv.1.double_conv.3.gamma, shape=(128,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.down2.maxpool_conv.1.double_conv.3.beta, shape=(128,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.down2.maxpool_conv.1.double_conv.3.moving_mean, shape=(128,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.down2.maxpool_conv.1.double_conv.3.moving_variance, shape=(128,), dtype=Float32, requires_grad=False)>\n",
" (4): ReLU<>\n",
" (5): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=128, output_channels=128, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe742d1310>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe742d1610>, format=NCHW>\n",
" >\n",
" >\n",
" >\n",
" >\n",
" >\n",
" (down3): Down<\n",
" (maxpool_conv): SequentialCell<\n",
" (0): MaxPool2d<kernel_size=2, stride=2, pad_mode=VALID>\n",
" (1): DoubleConv<\n",
" (single_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=128, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.down3.maxpool_conv.1.single_conv.0.gamma, shape=(128,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.down3.maxpool_conv.1.single_conv.0.beta, shape=(128,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.down3.maxpool_conv.1.single_conv.0.moving_mean, shape=(128,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.down3.maxpool_conv.1.single_conv.0.moving_variance, shape=(128,), dtype=Float32, requires_grad=False)>\n",
" (1): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=128, output_channels=256, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe742d13a0>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe742d1760>, format=NCHW>\n",
" >\n",
" >\n",
" (double_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=128, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.down3.maxpool_conv.1.double_conv.0.gamma, shape=(128,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.down3.maxpool_conv.1.double_conv.0.beta, shape=(128,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.down3.maxpool_conv.1.double_conv.0.moving_mean, shape=(128,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.down3.maxpool_conv.1.double_conv.0.moving_variance, shape=(128,), dtype=Float32, requires_grad=False)>\n",
" (1): ReLU<>\n",
" (2): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=128, output_channels=256, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe742d1a90>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe742d1b50>, format=NCHW>\n",
" >\n",
" (3): BatchNorm2d<num_features=256, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.down3.maxpool_conv.1.double_conv.3.gamma, shape=(256,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.down3.maxpool_conv.1.double_conv.3.beta, shape=(256,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.down3.maxpool_conv.1.double_conv.3.moving_mean, shape=(256,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.down3.maxpool_conv.1.double_conv.3.moving_variance, shape=(256,), dtype=Float32, requires_grad=False)>\n",
" (4): ReLU<>\n",
" (5): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=256, output_channels=256, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe742d1a00>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe742d19d0>, format=NCHW>\n",
" >\n",
" >\n",
" >\n",
" >\n",
" >\n",
" (down4): Down<\n",
" (maxpool_conv): SequentialCell<\n",
" (0): MaxPool2d<kernel_size=2, stride=2, pad_mode=VALID>\n",
" (1): DoubleConv<\n",
" (single_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=256, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.down4.maxpool_conv.1.single_conv.0.gamma, shape=(256,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.down4.maxpool_conv.1.single_conv.0.beta, shape=(256,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.down4.maxpool_conv.1.single_conv.0.moving_mean, shape=(256,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.down4.maxpool_conv.1.single_conv.0.moving_variance, shape=(256,), dtype=Float32, requires_grad=False)>\n",
" (1): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=256, output_channels=256, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe742d1f40>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe742d1f10>, format=NCHW>\n",
" >\n",
" >\n",
" (double_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=256, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.down4.maxpool_conv.1.double_conv.0.gamma, shape=(256,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.down4.maxpool_conv.1.double_conv.0.beta, shape=(256,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.down4.maxpool_conv.1.double_conv.0.moving_mean, shape=(256,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.down4.maxpool_conv.1.double_conv.0.moving_variance, shape=(256,), dtype=Float32, requires_grad=False)>\n",
" (1): ReLU<>\n",
" (2): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=256, output_channels=256, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74243130>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe742431f0>, format=NCHW>\n",
" >\n",
" (3): BatchNorm2d<num_features=256, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.down4.maxpool_conv.1.double_conv.3.gamma, shape=(256,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.down4.maxpool_conv.1.double_conv.3.beta, shape=(256,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.down4.maxpool_conv.1.double_conv.3.moving_mean, shape=(256,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.down4.maxpool_conv.1.double_conv.3.moving_variance, shape=(256,), dtype=Float32, requires_grad=False)>\n",
" (4): ReLU<>\n",
" (5): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=256, output_channels=256, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe742d1940>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe742d16d0>, format=NCHW>\n",
" >\n",
" >\n",
" >\n",
" >\n",
" >\n",
" (up1): Up<\n",
" (up): Upsample<>\n",
" (conv): DoubleConv<\n",
" (single_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=512, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up1.conv.single_conv.0.gamma, shape=(512,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up1.conv.single_conv.0.beta, shape=(512,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up1.conv.single_conv.0.moving_mean, shape=(512,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up1.conv.single_conv.0.moving_variance, shape=(512,), dtype=Float32, requires_grad=False)>\n",
" (1): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=512, output_channels=128, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74243760>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74243790>, format=NCHW>\n",
" >\n",
" >\n",
" (double_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=512, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up1.conv.double_conv.0.gamma, shape=(512,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up1.conv.double_conv.0.beta, shape=(512,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up1.conv.double_conv.0.moving_mean, shape=(512,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up1.conv.double_conv.0.moving_variance, shape=(512,), dtype=Float32, requires_grad=False)>\n",
" (1): ReLU<>\n",
" (2): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=512, output_channels=256, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74243670>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe742434c0>, format=NCHW>\n",
" >\n",
" (3): BatchNorm2d<num_features=256, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up1.conv.double_conv.3.gamma, shape=(256,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up1.conv.double_conv.3.beta, shape=(256,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up1.conv.double_conv.3.moving_mean, shape=(256,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up1.conv.double_conv.3.moving_variance, shape=(256,), dtype=Float32, requires_grad=False)>\n",
" (4): ReLU<>\n",
" (5): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=256, output_channels=128, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74243b50>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74243c10>, format=NCHW>\n",
" >\n",
" >\n",
" >\n",
" >\n",
" (up2): Up<\n",
" (up): Upsample<>\n",
" (conv): DoubleConv<\n",
" (single_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=256, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up2.conv.single_conv.0.gamma, shape=(256,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up2.conv.single_conv.0.beta, shape=(256,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up2.conv.single_conv.0.moving_mean, shape=(256,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up2.conv.single_conv.0.moving_variance, shape=(256,), dtype=Float32, requires_grad=False)>\n",
" (1): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=256, output_channels=64, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74243cd0>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74243df0>, format=NCHW>\n",
" >\n",
" >\n",
" (double_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=256, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up2.conv.double_conv.0.gamma, shape=(256,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up2.conv.double_conv.0.beta, shape=(256,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up2.conv.double_conv.0.moving_mean, shape=(256,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up2.conv.double_conv.0.moving_variance, shape=(256,), dtype=Float32, requires_grad=False)>\n",
" (1): ReLU<>\n",
" (2): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=256, output_channels=128, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe742340a0>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74243e50>, format=NCHW>\n",
" >\n",
" (3): BatchNorm2d<num_features=128, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up2.conv.double_conv.3.gamma, shape=(128,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up2.conv.double_conv.3.beta, shape=(128,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up2.conv.double_conv.3.moving_mean, shape=(128,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up2.conv.double_conv.3.moving_variance, shape=(128,), dtype=Float32, requires_grad=False)>\n",
" (4): ReLU<>\n",
" (5): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=128, output_channels=64, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74234130>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74234220>, format=NCHW>\n",
" >\n",
" >\n",
" >\n",
" >\n",
" (up3): Up<\n",
" (up): Upsample<>\n",
" (conv): DoubleConv<\n",
" (single_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=128, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up3.conv.single_conv.0.gamma, shape=(128,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up3.conv.single_conv.0.beta, shape=(128,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up3.conv.single_conv.0.moving_mean, shape=(128,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up3.conv.single_conv.0.moving_variance, shape=(128,), dtype=Float32, requires_grad=False)>\n",
" (1): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=128, output_channels=32, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74243a90>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74234460>, format=NCHW>\n",
" >\n",
" >\n",
" (double_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=128, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up3.conv.double_conv.0.gamma, shape=(128,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up3.conv.double_conv.0.beta, shape=(128,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up3.conv.double_conv.0.moving_mean, shape=(128,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up3.conv.double_conv.0.moving_variance, shape=(128,), dtype=Float32, requires_grad=False)>\n",
" (1): ReLU<>\n",
" (2): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=128, output_channels=64, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe742346d0>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74234790>, format=NCHW>\n",
" >\n",
" (3): BatchNorm2d<num_features=64, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up3.conv.double_conv.3.gamma, shape=(64,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up3.conv.double_conv.3.beta, shape=(64,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up3.conv.double_conv.3.moving_mean, shape=(64,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up3.conv.double_conv.3.moving_variance, shape=(64,), dtype=Float32, requires_grad=False)>\n",
" (4): ReLU<>\n",
" (5): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=64, output_channels=32, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe742348e0>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74234400>, format=NCHW>\n",
" >\n",
" >\n",
" >\n",
" >\n",
" (up4): Up<\n",
" (up): Upsample<>\n",
" (conv): DoubleConv<\n",
" (single_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=64, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up4.conv.single_conv.0.gamma, shape=(64,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up4.conv.single_conv.0.beta, shape=(64,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up4.conv.single_conv.0.moving_mean, shape=(64,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up4.conv.single_conv.0.moving_variance, shape=(64,), dtype=Float32, requires_grad=False)>\n",
" (1): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=64, output_channels=32, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74234be0>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74306d30>, format=NCHW>\n",
" >\n",
" >\n",
" (double_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=64, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up4.conv.double_conv.0.gamma, shape=(64,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up4.conv.double_conv.0.beta, shape=(64,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up4.conv.double_conv.0.moving_mean, shape=(64,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up4.conv.double_conv.0.moving_variance, shape=(64,), dtype=Float32, requires_grad=False)>\n",
" (1): ReLU<>\n",
" (2): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=64, output_channels=32, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74234940>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74234cd0>, format=NCHW>\n",
" >\n",
" (3): BatchNorm2d<num_features=32, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up4.conv.double_conv.3.gamma, shape=(32,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up4.conv.double_conv.3.beta, shape=(32,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up4.conv.double_conv.3.moving_mean, shape=(32,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up4.conv.double_conv.3.moving_variance, shape=(32,), dtype=Float32, requires_grad=False)>\n",
" (4): ReLU<>\n",
" (5): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=32, output_channels=32, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74234d90>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe741a1100>, format=NCHW>\n",
" >\n",
" >\n",
" >\n",
" >\n",
" (outc): OutConv<\n",
" (conv): Conv2d<input_channels=32, output_channels=20, kernel_size=(1, 1), stride=(1, 1), pad_mode=pad, padding=0, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe742342b0>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74234d00>, format=NCHW>\n",
" >\n",
" (up1_v): Up<\n",
" (up): Upsample<>\n",
" (conv): DoubleConv<\n",
" (single_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=512, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up1_v.conv.single_conv.0.gamma, shape=(512,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up1_v.conv.single_conv.0.beta, shape=(512,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up1_v.conv.single_conv.0.moving_mean, shape=(512,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up1_v.conv.single_conv.0.moving_variance, shape=(512,), dtype=Float32, requires_grad=False)>\n",
" (1): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=512, output_channels=128, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe741a1400>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe741a1430>, format=NCHW>\n",
" >\n",
" >\n",
" (double_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=512, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up1_v.conv.double_conv.0.gamma, shape=(512,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up1_v.conv.double_conv.0.beta, shape=(512,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up1_v.conv.double_conv.0.moving_mean, shape=(512,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up1_v.conv.double_conv.0.moving_variance, shape=(512,), dtype=Float32, requires_grad=False)>\n",
" (1): ReLU<>\n",
" (2): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=512, output_channels=256, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe741a1610>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe741a10a0>, format=NCHW>\n",
" >\n",
" (3): BatchNorm2d<num_features=256, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up1_v.conv.double_conv.3.gamma, shape=(256,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up1_v.conv.double_conv.3.beta, shape=(256,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up1_v.conv.double_conv.3.moving_mean, shape=(256,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up1_v.conv.double_conv.3.moving_variance, shape=(256,), dtype=Float32, requires_grad=False)>\n",
" (4): ReLU<>\n",
" (5): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=256, output_channels=128, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe741a1820>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe741a18e0>, format=NCHW>\n",
" >\n",
" >\n",
" >\n",
" >\n",
" (up2_v): Up<\n",
" (up): Upsample<>\n",
" (conv): DoubleConv<\n",
" (single_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=256, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up2_v.conv.single_conv.0.gamma, shape=(256,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up2_v.conv.single_conv.0.beta, shape=(256,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up2_v.conv.single_conv.0.moving_mean, shape=(256,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up2_v.conv.single_conv.0.moving_variance, shape=(256,), dtype=Float32, requires_grad=False)>\n",
" (1): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=256, output_channels=64, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe741a19d0>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe741a19a0>, format=NCHW>\n",
" >\n",
" >\n",
" (double_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=256, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up2_v.conv.double_conv.0.gamma, shape=(256,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up2_v.conv.double_conv.0.beta, shape=(256,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up2_v.conv.double_conv.0.moving_mean, shape=(256,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up2_v.conv.double_conv.0.moving_variance, shape=(256,), dtype=Float32, requires_grad=False)>\n",
" (1): ReLU<>\n",
" (2): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=256, output_channels=128, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe741a1d00>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe741a1af0>, format=NCHW>\n",
" >\n",
" (3): BatchNorm2d<num_features=128, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up2_v.conv.double_conv.3.gamma, shape=(128,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up2_v.conv.double_conv.3.beta, shape=(128,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up2_v.conv.double_conv.3.moving_mean, shape=(128,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up2_v.conv.double_conv.3.moving_variance, shape=(128,), dtype=Float32, requires_grad=False)>\n",
" (4): ReLU<>\n",
" (5): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=128, output_channels=64, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe741a1e20>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe741a1ee0>, format=NCHW>\n",
" >\n",
" >\n",
" >\n",
" >\n",
" (up3_v): Up<\n",
" (up): Upsample<>\n",
" (conv): DoubleConv<\n",
" (single_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=128, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up3_v.conv.single_conv.0.gamma, shape=(128,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up3_v.conv.single_conv.0.beta, shape=(128,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up3_v.conv.single_conv.0.moving_mean, shape=(128,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up3_v.conv.single_conv.0.moving_variance, shape=(128,), dtype=Float32, requires_grad=False)>\n",
" (1): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=128, output_channels=32, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe741a1a60>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe741a1ac0>, format=NCHW>\n",
" >\n",
" >\n",
" (double_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=128, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up3_v.conv.double_conv.0.gamma, shape=(128,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up3_v.conv.double_conv.0.beta, shape=(128,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up3_v.conv.double_conv.0.moving_mean, shape=(128,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up3_v.conv.double_conv.0.moving_variance, shape=(128,), dtype=Float32, requires_grad=False)>\n",
" (1): ReLU<>\n",
" (2): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=128, output_channels=64, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74111370>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74111430>, format=NCHW>\n",
" >\n",
" (3): BatchNorm2d<num_features=64, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up3_v.conv.double_conv.3.gamma, shape=(64,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up3_v.conv.double_conv.3.beta, shape=(64,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up3_v.conv.double_conv.3.moving_mean, shape=(64,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up3_v.conv.double_conv.3.moving_variance, shape=(64,), dtype=Float32, requires_grad=False)>\n",
" (4): ReLU<>\n",
" (5): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=64, output_channels=32, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74111490>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74111400>, format=NCHW>\n",
" >\n",
" >\n",
" >\n",
" >\n",
" (up4_v): Up<\n",
" (up): Upsample<>\n",
" (conv): DoubleConv<\n",
" (single_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=64, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up4_v.conv.single_conv.0.gamma, shape=(64,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up4_v.conv.single_conv.0.beta, shape=(64,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up4_v.conv.single_conv.0.moving_mean, shape=(64,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up4_v.conv.single_conv.0.moving_variance, shape=(64,), dtype=Float32, requires_grad=False)>\n",
" (1): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=64, output_channels=32, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe741118e0>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74111910>, format=NCHW>\n",
" >\n",
" >\n",
" (double_conv): SequentialCell<\n",
" (0): BatchNorm2d<num_features=64, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up4_v.conv.double_conv.0.gamma, shape=(64,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up4_v.conv.double_conv.0.beta, shape=(64,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up4_v.conv.double_conv.0.moving_mean, shape=(64,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up4_v.conv.double_conv.0.moving_variance, shape=(64,), dtype=Float32, requires_grad=False)>\n",
" (1): ReLU<>\n",
" (2): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=64, output_channels=32, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe741117c0>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74111a00>, format=NCHW>\n",
" >\n",
" (3): BatchNorm2d<num_features=32, eps=1e-05, momentum=0.9, gamma=Parameter (name=evo_net.up4_v.conv.double_conv.3.gamma, shape=(32,), dtype=Float32, requires_grad=True), beta=Parameter (name=evo_net.up4_v.conv.double_conv.3.beta, shape=(32,), dtype=Float32, requires_grad=True), moving_mean=Parameter (name=evo_net.up4_v.conv.double_conv.3.moving_mean, shape=(32,), dtype=Float32, requires_grad=False), moving_variance=Parameter (name=evo_net.up4_v.conv.double_conv.3.moving_variance, shape=(32,), dtype=Float32, requires_grad=False)>\n",
" (4): ReLU<>\n",
" (5): SpectralNormal<\n",
" (parametrizations): Conv2d<input_channels=32, output_channels=32, kernel_size=(3, 3), stride=(1, 1), pad_mode=pad, padding=1, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74111cd0>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe74111d90>, format=NCHW>\n",
" >\n",
" >\n",
" >\n",
" >\n",
" (outc_v): OutConv<\n",
" (conv): Conv2d<input_channels=32, output_channels=40, kernel_size=(1, 1), stride=(1, 1), pad_mode=pad, padding=0, dilation=(1, 1), group=1, has_bias=True, weight_init=<mindspore.common.initializer.HeUniform object at 0xfffe74111c10>, bias_init=<mindspore.common.initializer.Uniform object at 0xfffe741116a0>, format=NCHW>\n",
" >\n",
" >\n",
" >"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"logger = get_logger(config)\n",
"config[\"model\"][\"module_name\"] = 'evolution'\n",
"config[\"data\"][\"batch_size\"] = 4\n",
"config[\"summary\"][\"eval_interval\"] = 1\n",
"config[\"summary\"][\"visual\"] = False\n",
"train_params = config.get(\"train\")\n",
"summary_params = config.get(\"summary\")\n",
"evo_model = EvolutionNet(config)\n",
"evo_model.set_train()"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"### 模型训练"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"ExecuteTime": {
"end_time": "2024-01-31T03:24:30.164901700Z",
"start_time": "2024-01-31T01:01:39.614516800Z"
},
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch: 1 step: 398, loss is 6.6358147\n",
"epoch: 1 step: 399, loss is 11.47153\n",
"epoch: 1 step: 400, loss is 7.2303286\n",
"Train epoch time: 1794325.439 ms, per step time: 4485.814 ms\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-01-31 09:32:00,659 - forecast.py[line:191] - INFO: ================================Start Evaluation================================\n",
"2024-01-31 09:32:00,661 - forecast.py[line:192] - INFO: The length of data is: 1\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"-\r"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-01-31 09:32:04,107 - forecast.py[line:179] - INFO: CSI Neighborhood threshold 16 T+10 min: 0.4054458796087876 T+60 min: 0.16474475307855177 T+120 min: 0.09442198339292594\n",
"2024-01-31 09:32:04,181 - forecast.py[line:211] - INFO: ================================End Evaluation================================\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch: 2 step: 398, loss is 7.7851076\n",
"epoch: 2 step: 399, loss is 6.364196\n",
"epoch: 2 step: 400, loss is 11.064963\n",
"Train epoch time: 1688639.108 ms, per step time: 4221.598 ms\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-01-31 10:00:12,836 - forecast.py[line:191] - INFO: ================================Start Evaluation================================\n",
"2024-01-31 10:00:12,838 - forecast.py[line:192] - INFO: The length of data is: 1\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\\\r"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-01-31 10:00:16,213 - forecast.py[line:179] - INFO: CSI Neighborhood threshold 16 T+10 min: 0.41709989523909563 T+60 min: 0.16894114336218546 T+120 min: 0.10467792846088278\n",
"2024-01-31 10:00:16,291 - forecast.py[line:211] - INFO: ================================End Evaluation================================\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch: 3 step: 398, loss is 5.818244\n",
"epoch: 3 step: 399, loss is 6.7248154\n",
"epoch: 3 step: 400, loss is 10.864609\n",
"Train epoch time: 1690693.724 ms, per step time: 4226.734 ms\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-01-31 10:28:27,000 - forecast.py[line:191] - INFO: ================================Start Evaluation================================\n",
"2024-01-31 10:28:27,002 - forecast.py[line:192] - INFO: The length of data is: 1\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"|\r"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-01-31 10:28:30,512 - forecast.py[line:179] - INFO: CSI Neighborhood threshold 16 T+10 min: 0.3993438740760541 T+60 min: 0.16725303802177002 T+120 min: 0.0959103616970071\n",
"2024-01-31 10:28:30,583 - forecast.py[line:211] - INFO: ================================End Evaluation================================\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch: 4 step: 398, loss is 7.879731\n",
"epoch: 4 step: 399, loss is 9.270348\n",
"epoch: 4 step: 400, loss is 10.59611\n",
"Train epoch time: 1687615.214 ms, per step time: 4219.038 ms\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-01-31 10:56:38,214 - forecast.py[line:191] - INFO: ================================Start Evaluation================================\n",
"2024-01-31 10:56:38,216 - forecast.py[line:192] - INFO: The length of data is: 1\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"/\r"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-01-31 10:56:41,586 - forecast.py[line:179] - INFO: CSI Neighborhood threshold 16 T+10 min: 0.4119070738020246 T+60 min: 0.16328413060990918 T+120 min: 0.10628156308461514\n",
"2024-01-31 10:56:41,656 - forecast.py[line:211] - INFO: ================================End Evaluation================================\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch: 5 step: 398, loss is 14.705731\n",
"epoch: 5 step: 399, loss is 10.468576\n",
"epoch: 5 step: 400, loss is 6.882686\n",
"Train epoch time: 1691109.624 ms, per step time: 4227.774 ms\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-01-31 11:24:52,789 - forecast.py[line:191] - INFO: ================================Start Evaluation================================\n",
"2024-01-31 11:24:52,790 - forecast.py[line:192] - INFO: The length of data is: 1\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"-\r"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-01-31 11:24:56,256 - forecast.py[line:179] - INFO: CSI Neighborhood threshold 16 T+10 min: 0.4118216017414204 T+60 min: 0.15679251293172677 T+120 min: 0.10144497020636714\n",
"2024-01-31 11:24:56,322 - forecast.py[line:211] - INFO: ================================End Evaluation================================\n"
]
}
],
"source": [
"loss_scale = ms.train.loss_scale_manager.FixedLossScaleManager(loss_scale=2048)\n",
"evo_loss_fn = EvolutionLoss(evo_model, config)\n",
"trainer = EvolutionTrainer(config, evo_model, evo_loss_fn, logger, loss_scale)\n",
"trainer.train()"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"### evolution评估和可视化\n",
"\n",
"完成训练后，我们使用ckpt进行推理，下述展示了推理的可视化图片\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"ExecuteTime": {
"end_time": "2024-01-31T03:27:47.291549200Z",
"start_time": "2024-01-31T03:27:46.401222Z"
},
"collapsed": false
},
"outputs": [],
"source": [
"config[\"data\"][\"batch_size\"] = 1\n",
"config[\"summary\"][\"visual\"] = True\n",
"params = load_checkpoint('./summary/ckpt/evolution-3_200.ckpt')\n",
"evo_model.set_train(False)\n",
"load_param_into_net(evo_model, params)\n",
"evo_inference = EvolutionPredictor(config, evo_model, logger)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"ExecuteTime": {
"end_time": "2024-01-31T06:11:02.019387Z",
"start_time": "2024-01-31T06:11:00.391020800Z"
},
"collapsed": false
},
"outputs": [],
"source": [
"data_params = config.get(\"data\")\n",
"test_dataset_generator = RadarData(data_params, run_mode='test', module_name=\"evolution\")\n",
"test_dataset = NowcastDataset(test_dataset_generator,\n",
" module_name=\"evolution\",\n",
" distribute=train_params.get('distribute', False),\n",
" num_workers=data_params.get('num_workers', 1),\n",
" shuffle=False)\n",
"test_dataset = test_dataset.create_dataset(data_params.get('batch_size', 1))\n",
"# data = next(test_dataset.create_dict_iterator())\n",
"steps = 1\n",
"for d in test_dataset.create_dict_iterator():\n",
" if steps == 6:\n",
" data = d\n",
" break\n",
" steps += 1\n",
"inputs = data['inputs']\n",
"pred = evo_inference.forecast(inputs)\n",
"labels = inputs[:, data_params.get(\"t_in\"):]\n",
"plt_idx = [x // data_params.get(\"time_interval\") - 1 for x in data_params.get(\"key_info_timestep\", [10, 60, 120])]\n",
"plt_img(field=pred[0].asnumpy(), label=labels[0].asnumpy(), idx=plt_idx, fig_name=\"./evolution_example.png\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"## Generation"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"### 模型训练"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"config[\"model\"][\"module_name\"] = 'generation'\n",
"config[\"data\"][\"batch_size\"] = 1\n",
"config[\"summary\"][\"visual\"] = False\n",
"config[\"summary\"][\"save_checkpoint_epochs\"] = 1\n",
"train_params = config.get(\"train\")\n",
"summary_params = config.get(\"summary\")\n",
"g_model = GenerationNet(config)\n",
"d_model = TemporalDiscriminator(data_params.get(\"t_in\", 9) + data_params.get(\"t_out\", 20))\n",
"g_model.set_train()\n",
"d_model.set_train()\n",
"g_model = amp.auto_mixed_precision(g_model, amp_level=train_params.get(\"amp_level\", 'O2'))\n",
"d_model = amp.auto_mixed_precision(d_model, amp_level=train_params.get(\"amp_level\", 'O2'))\n",
"loss_scale = nn.DynamicLossScaleUpdateCell(loss_scale_value=2 ** 12, scale_factor=2, scale_window=1000)\n",
"g_loss_fn = GenerateLoss(g_model, d_model)\n",
"d_loss_fn = DiscriminatorLoss(g_model, d_model)\n",
"trainer = GenerationTrainer(config, g_model, d_model, g_loss_fn, d_loss_fn, logger, loss_scale)\n",
"trainer.train()"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"### generation评估和可视化\n",
"\n",
"完成训练后，我们使用ckpt进行推理，下述展示了推理的可视化图片"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"config[\"summary\"][\"visual\"] = True\n",
"config[\"train\"][\"load_ckpt\"] = True\n",
"gen_inference = GenerationPredictor(config, g_model, logger)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"data_params = config.get(\"data\")\n",
"model_params = config.get(\"model\")\n",
"test_dataset_generator = RadarData(data_params, run_mode='test', module_name=\"generation\")\n",
"test_dataset = NowcastDataset(test_dataset_generator,\n",
" module_name=\"generation\",\n",
" distribute=train_params.get('distribute', False),\n",
" num_workers=data_params.get('num_workers', 1),\n",
" shuffle=False)\n",
"test_dataset = test_dataset.create_dataset(data_params.get('batch_size', 1))\n",
"data = next(test_dataset.create_dict_iterator())\n",
"inp, evo_result, labels = data.get(\"inputs\"), data.get(\"evo\"), data.get(\"labels\")\n",
"noise_scale = data_params.get(\"noise_scale\", 32)\n",
"threshold = summary_params.get(\"csin_threshold\", 16)\n",
"batch_size = data_params.get(\"batch_size\", 1)\n",
"w_size = data_params.get(\"w_size\", 512)\n",
"h_size = data_params.get(\"h_size\", 512)\n",
"ngf = model_params.get(\"ngf\", 32)\n",
"noise = ms.tensor(ms.numpy.randn((batch_size, ngf, h_size // noise_scale, w_size // noise_scale)), inp.dtype)\n",
"pred = gen_inference.generator(inp, evo_result, noise)\n",
"plt_img(field=pred[0].asnumpy(), label=labels[0].asnumpy(), idx=plt_idx, fig_name=\"./generation_example.png\", evo=evo_result[0].asnumpy() * 128, plot_evo=True)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 0
}