{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd#导入csv文件的库\nimport math\nimport numpy as np#进行矩阵运算的库\nimport matplotlib.pyplot as plt#作图的库\nimport torch#一个深度学习的库Pytorch\nimport torch.nn as nn#neural network,神经网络\nimport torch.optim as optim#一个实现了各种优化算法的库\nimport torch.nn.functional as F#神经网络函数库\nimport warnings#避免一些可以忽略的报错\nwarnings.filterwarnings('ignore')","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-07-07T00:08:11.308058Z","iopub.execute_input":"2023-07-07T00:08:11.308509Z","iopub.status.idle":"2023-07-07T00:08:14.834924Z","shell.execute_reply.started":"2023-07-07T00:08:11.308473Z","shell.execute_reply":"2023-07-07T00:08:14.833976Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#设置随机种子\nimport random\ntorch.backends.cudnn.deterministic = True#将cudnn框架中的随机数生成器设为确定性模式\ntorch.backends.cudnn.benchmark = False#关闭CuDNN框架的自动寻找最优卷积算法的功能，以避免不同的算法对结果产生影响\ntorch.manual_seed(42)\nnp.random.seed(42)\nrandom.seed(42)","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:08:14.836986Z","iopub.execute_input":"2023-07-07T00:08:14.837617Z","iopub.status.idle":"2023-07-07T00:08:14.847472Z","shell.execute_reply.started":"2023-07-07T00:08:14.837582Z","shell.execute_reply":"2023-07-07T00:08:14.846535Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train=pd.read_csv(\"/kaggle/input/ece597697-sp2023/train.csv/train.csv\")\ntrain.head()","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:08:14.849336Z","iopub.execute_input":"2023-07-07T00:08:14.849690Z","iopub.status.idle":"2023-07-07T00:08:21.514998Z","shell.execute_reply.started":"2023-07-07T00:08:14.849658Z","shell.execute_reply":"2023-07-07T00:08:21.514082Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"datay=train['label'].values\ntrain=train.drop(['label','id'],axis=1)\ndataX=train.values","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:08:21.517719Z","iopub.execute_input":"2023-07-07T00:08:21.518347Z","iopub.status.idle":"2023-07-07T00:08:21.639259Z","shell.execute_reply.started":"2023-07-07T00:08:21.518313Z","shell.execute_reply":"2023-07-07T00:08:21.638089Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#划分训练集和测试集的函数\ndef train_test_split(dataX,datay,shuffle=True,percentage=0.8):\n    \"\"\"\n    将训练数据X和标签y以numpy.array数组的形式传入\n    划分的比例定为训练集:测试集=8:2\n    \"\"\"\n    if shuffle:\n        random_num=[index for index in range(len(dataX))]\n        np.random.shuffle(random_num)\n        dataX=dataX[random_num]\n        datay=datay[random_num]\n    split_num=int(len(dataX)*percentage)\n    train_X=dataX[:split_num]\n    train_y=datay[:split_num]\n    test_X=dataX[split_num:]\n    test_y=datay[split_num:]\n    return train_X,train_y,test_X,test_y","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:08:21.642859Z","iopub.execute_input":"2023-07-07T00:08:21.643208Z","iopub.status.idle":"2023-07-07T00:08:21.652142Z","shell.execute_reply.started":"2023-07-07T00:08:21.643159Z","shell.execute_reply":"2023-07-07T00:08:21.651227Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_X,train_y,valid_X,valid_y=train_test_split(dataX,datay,percentage=0.9)\nlabel_count=np.max(train_y)+1\nfor index in range(label_count):\n    print(f\"np.sum(train_y==index)={np.sum(train_y==index)}\")\nprint(f\"train_X.shape:{train_X.shape},valid_X.shape:{valid_X.shape}\")","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:08:21.654071Z","iopub.execute_input":"2023-07-07T00:08:21.654421Z","iopub.status.idle":"2023-07-07T00:08:22.233410Z","shell.execute_reply.started":"2023-07-07T00:08:21.654391Z","shell.execute_reply":"2023-07-07T00:08:22.232257Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#多头注意力机制\nclass MultiHeadSelfAttention(nn.Module):\n    #定义初始化函数\n    def __init__(self,dim_in,d_model,num_heads=4):\n\n        super(MultiHeadSelfAttention,self).__init__()\n        \n        self.dim_in=dim_in\n        \n        self.d_model=d_model\n        \n        self.num_heads=num_heads\n        \n        #向量的维度必须被头的个数整除,否则会抛出异常.\n        assert d_model %num_heads==0,\"d_model must be multiple of num_heads\"\n        \n        #定义线性变换矩阵\n        self.linear_q=nn.Linear(dim_in,d_model)\n        self.linear_k=nn.Linear(dim_in,d_model)\n        self.linear_v=nn.Linear(dim_in,d_model)\n        self.scale=1/math.sqrt(d_model//num_heads)\n        \n        #最后的线性层\n        self.fc=nn.Linear(d_model,d_model)\n        \n    def forward(self,x):\n        batch,n,dim_in=x.shape\n        \n        assert dim_in==self.dim_in\n        \n        nh=self.num_heads\n        \n        dk=self.d_model//nh\n        \n        q=self.linear_q(x).reshape(batch,n,nh,dk).transpose(1,2)\n        k=self.linear_k(x).reshape(batch,n,nh,dk).transpose(1,2)\n        v=self.linear_v(x).reshape(batch,n,nh,dk).transpose(1,2)\n        \n        \n        dist=torch.matmul(q,k.transpose(2,3))*self.scale\n        dist=torch.softmax(dist,dim=-1)\n        \n        att=torch.matmul(dist,v)\n        \n        att=att.transpose(1,2).reshape(batch,n,self.d_model)\n        \n        output=self.fc(att)\n        \n        return output ","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:08:22.235108Z","iopub.execute_input":"2023-07-07T00:08:22.235800Z","iopub.status.idle":"2023-07-07T00:08:22.248592Z","shell.execute_reply.started":"2023-07-07T00:08:22.235768Z","shell.execute_reply":"2023-07-07T00:08:22.247448Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class SELayer(nn.Module):\n    def __init__(self,channel=256,reduction=16):\n        super(SELayer,self).__init__()\n        self.avg_pool=nn.AdaptiveAvgPool2d(1)#输出为1*1\n        self.fc=nn.Sequential(\n            nn.Linear(channel,channel//reduction,bias=True),\n            nn.BatchNorm1d(channel//reduction),\n            nn.GELU(),\n            nn.Linear(channel//reduction,channel,bias=True),\n            nn.Sigmoid(),\n        )\n    def forward(self,x):\n        #batch_size,channels,\n        b,c,_,_=x.shape\n        \n        y=self.avg_pool(x).view(b,c)\n        y=self.fc(y).view(b,c,1,1)\n        return x*y.expand_as(x)#将y扩展到x同样的shape","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:08:22.250459Z","iopub.execute_input":"2023-07-07T00:08:22.250858Z","iopub.status.idle":"2023-07-07T00:08:22.265541Z","shell.execute_reply.started":"2023-07-07T00:08:22.250826Z","shell.execute_reply":"2023-07-07T00:08:22.264423Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#对特征图的每个位置也提取一次权重\nclass SEConv(nn.Module):\n    def __init__(self,area=36,reduction=4):\n        super(SEConv,self).__init__()\n        self.fc=nn.Sequential(\n            nn.Linear(area,area//reduction,bias=True),\n            nn.BatchNorm1d(area//reduction),\n            nn.GELU(),\n            nn.Linear(area//reduction,area,bias=True),\n            nn.Sigmoid(),\n        )\n    def forward(self,x):\n        #batch_size,channels,(height*width)\n        b,c,area=x.shape\n        y=torch.mean(x,dim=1)\n        y=self.fc(y)\n        y=y.view(-1,1,area)\n        return x*y.expand_as(x)#将y扩展到x同样的shape","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:08:22.267343Z","iopub.execute_input":"2023-07-07T00:08:22.268122Z","iopub.status.idle":"2023-07-07T00:08:22.281856Z","shell.execute_reply.started":"2023-07-07T00:08:22.268086Z","shell.execute_reply":"2023-07-07T00:08:22.280769Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#score:0.92976\nclass CNN(nn.Module):\n\n    def __init__(self):\n        \n        super(CNN,self).__init__()\n        \n        self.flag=0\n        self.center_array=[]\n        \n        #创建自注意机制的类\n        self.Self_Attention=MultiHeadSelfAttention(dim_in=36,d_model=36,num_heads=3)\n        \n        self.selayer=SELayer()\n        \n        self.seconv=SEConv()\n        \n        self.conv=nn.Sequential(\n        nn.Conv2d(1,16,3,1,0),#30*30->28*28\n        nn.BatchNorm2d(16),\n        nn.SiLU(),\n        nn.Conv2d(16,32,3,1,0),#28*28->26*26\n        nn.BatchNorm2d(32),\n        nn.ReLU(),\n        nn.Conv2d(32,72,5,1,0),#26*26->22*22\n        nn.BatchNorm2d(72),\n        nn.Tanh(),\n        nn.Conv2d(72,128,5,1,1),#20*20\n        nn.GELU(),\n        nn.MaxPool2d(2,2,0),#10*10\n        nn.BatchNorm2d(128),\n        nn.Conv2d(128,256,5,1,0),#6*6\n        nn.SiLU(),\n        nn.BatchNorm2d(256),\n        self.selayer,\n        )\n        \n        self.fc=nn.Sequential( \n        nn.Linear(256*6*6,128),\n        nn.BatchNorm1d(128),\n        nn.Dropout(p=0.2),\n        nn.GELU(),\n        nn.Linear(128,10),\n        )\n    def circle_padding(sellf,image, pad=1):\n        \"\"\"\n        input: torch.Tensor image (batch_size, channels, height, width)\n        output: pad_image (batch_size, channels, height+2*pad, width+2*pad)\n        \"\"\"\n        b, c, h, w = image.shape\n        pad_image = torch.zeros((b, c, h+2*pad, w+2*pad), device=image.device)\n\n        pad_image[:, :, pad:h+pad, pad:w+pad] = image\n        pad_image[:, :, 0:pad, pad:w+pad] = image[:, :, -pad:, :]\n        pad_image[:, :, -pad:, pad:w+pad] = image[:, :, 0:pad, :]\n        pad_image[:, :, pad:h+pad, 0:pad] = image[:, :, :, -pad:]\n        pad_image[:, :, pad:h+pad, -pad:] = image[:, :, :, 0:pad]\n        pad_image[:, :, 0:pad, 0:pad] = image[:, :, -pad:, -pad:]\n        pad_image[:, :, -pad:, -pad:] = image[:, :, 0:pad, 0:pad]\n        pad_image[:, :, 0:pad, -pad:] = image[:, :, -pad:, 0:pad]\n        pad_image[:, :, -pad:, 0:pad] = image[:, :, 0:pad, -pad:]\n\n        return pad_image\n    \n    def get_centering_array(self,image):\n        if self.flag==0:\n            #传入的是np.array的数组\n            batch_size,channels,row,col=image.shape\n            center_x=row/2\n            center_y=col/2\n            array=torch.randn(row,col).to(device)\n            for i in range(row):\n                for j in range(col):\n                    array[i][j]=math.sqrt(1- ( (i-center_x)**2+(j-center_y)**2)/( center_x**2+center_y**2 )/10)\n            self.flag=1\n            self.center_array=array\n        return image*self.center_array\n    #噪音注入\n    def noise_injection(self,features,noise_factor=0.002):\n        noise = torch.randn_like(features) * noise_factor\n        return features + noise\n    \n    def forward(self,input): \n        output=self.circle_padding(input)\n        output=self.get_centering_array(output)\n        output=self.noise_injection(output)\n        output=self.conv(output)\n        output=output.view(-1,256,6*6)#reshape\n        output=self.seconv(output)\n        output=output+self.Self_Attention(output)#跳连接\n        output=output.view(-1,256*6*6)#reshape\n        output=self.fc(output)\n        return F.log_softmax(output/5,dim=1)","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:08:22.285506Z","iopub.execute_input":"2023-07-07T00:08:22.285856Z","iopub.status.idle":"2023-07-07T00:08:22.309976Z","shell.execute_reply.started":"2023-07-07T00:08:22.285832Z","shell.execute_reply":"2023-07-07T00:08:22.308786Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n\ndevice='cuda' if torch.cuda.is_available() else\"cpu\"\n\n\ntrain_X=np.array(train_X).reshape(-1,1,28,28)/255.0-0.5\ntrain_y=np.array(train_y)\nvalid_X=np.array(valid_X).reshape(-1,1,28,28)/255.0-0.5\n\nvalid_X1=torch.Tensor(valid_X).to(device)\nnetC=CNN()\ntrain_accs=[]#存储训练集的准确率\nvalid_accs=[]#存储测试集的准确率\n#训练周期为1000次\nnum_epochs=1000\nbatch_size=200#一次训练的数据量\nweight_decay=0.0001\n\n#优化器\noptimizer=optim.Adam(netC.parameters(),lr=0.0005,betas=(0.5,0.999))\n#损失函数\ncriterion=nn.CrossEntropyLoss()\nnetC=netC.to(device)\nfor epoch in range(num_epochs):\n    \n    random_num=[index for index in range(len(train_X))]\n    np.random.shuffle(random_num)\n    \n    train_X=train_X[random_num]\n    \n    train_y=train_y[random_num]\n    \n    train_X1=torch.Tensor(train_X[:batch_size]).to(device)\n    train_y1=torch.Tensor(train_y[:batch_size]).long().to(device)\n    \n    #训练\n    netC.train()\n    #将数据放进去训练\n    output=netC(train_X1).to(device)\n    #计算每次的损失函数\n    loss=criterion(output,F.one_hot(train_y1,10).type(torch.FloatTensor).to(device)).to(device)\n    #L1正则化\n    l1_regularization = torch.tensor(0.).to(device)\n    for param in netC.parameters():\n        l1_regularization += torch.norm(param, 1)\n    loss += weight_decay * l1_regularization\n    #反向传播\n    loss.backward()\n    #优化器进行优化(梯度下降,降低误差)\n    optimizer.step()\n    #将梯度清空\n    optimizer.zero_grad()\n    if epoch%50==0:\n        netC.eval()\n        with torch.no_grad():\n            output=netC(train_X1).to(device)\n            output=output.detach().cpu().numpy()\n            train_pred=np.argmax(output,axis=1)\n\n            output=netC(valid_X1).to(device)\n            output=output.detach().cpu().numpy()\n            valid_pred=np.argmax(output,axis=1)\n        \n        train_acc=np.sum(train_pred==train_y[:batch_size])/len(train_y[:batch_size])\n        valid_acc=np.sum(valid_pred==valid_y)/len(valid_y)\n\n        train_accs.append(train_acc)\n        valid_accs.append(valid_acc)\n        print(f\"epoch:{epoch},loss:{loss}\\n train_acc:{train_acc},valid_acc:{valid_acc}\")","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:08:22.313081Z","iopub.execute_input":"2023-07-07T00:08:22.313505Z","iopub.status.idle":"2023-07-07T00:11:11.444202Z","shell.execute_reply.started":"2023-07-07T00:08:22.313479Z","shell.execute_reply":"2023-07-07T00:11:11.443237Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"percentage=0.25#剪枝的比例\nparameter=[]#每层的参数\nparameter_sorted=np.array([])\nfor name,module in netC.named_modules():\n    if isinstance(module,nn.BatchNorm2d): \n        parameter.append(module.weight.detach().cpu().numpy())\n        parameter_sorted=np.concatenate((parameter_sorted,module.weight.detach().cpu().numpy()),axis=0)\nparameter_sorted,index_sorted=torch.sort(torch.abs(torch.Tensor(parameter_sorted)))\nsplit_weight=parameter_sorted[int(percentage*len(parameter_sorted))]#小于这个数字的特征图不要\nfor i in range(len(parameter)):\n    for j in range(len(parameter[i])):\n        if abs(parameter[i][j])<split_weight:\n            parameter[i][j]=0\nfor index in range(len(parameter)):\n    print(f\"np.sum(parameter[index]!=0)={np.sum(parameter[index]!=0)}\")","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:11:11.445603Z","iopub.execute_input":"2023-07-07T00:11:11.446252Z","iopub.status.idle":"2023-07-07T00:11:11.483250Z","shell.execute_reply.started":"2023-07-07T00:11:11.446214Z","shell.execute_reply":"2023-07-07T00:11:11.482157Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#存储卷积层和batchNorm层剪枝剩下的参数\nlayer=0#记录一下这是第几层\ntotal_parameter=[]\nfor name,module in netC.named_modules():\n    if isinstance(module,nn.Conv2d):\n        conv_parameter=[]\n        conv_weight=module.weight.detach().cpu().numpy()\n        for index in range(len(conv_weight)):\n            if parameter[layer][index]:#如果这个特征图重要\n                #conv_weight[index]\n                weight=conv_weight[index]\n                remain_weight=[]\n                if layer==0:\n                    remain_weight=weight\n                for j in range(len(weight)):\n                    if layer and parameter[layer-1][j]:#上一层的这个位置重要吗?\n                        remain_weight.append(weight[j])\n                conv_parameter.append(np.array(remain_weight))\n        #print(f\"conv_weight[index].shape:{conv_weight[index].shape}\")\n        total_parameter.append(conv_parameter)\n    if isinstance(module,nn.BatchNorm2d): \n        bn_parameter=[]\n        bn_weight=module.weight.detach().cpu().numpy()\n        for index in range(len(bn_weight)):\n            if parameter[layer][index]:#如果这个特征图重要\n                bn_parameter.append(bn_weight[index])\n        total_parameter.append(bn_parameter)\n        layer+=1\nprint(f\"len(total_parameter):{len(total_parameter)}\")","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:11:11.484825Z","iopub.execute_input":"2023-07-07T00:11:11.485491Z","iopub.status.idle":"2023-07-07T00:11:11.549579Z","shell.execute_reply.started":"2023-07-07T00:11:11.485456Z","shell.execute_reply":"2023-07-07T00:11:11.548508Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#score:0.92976\nclass prune_CNN(nn.Module):\n\n    def __init__(self):\n        \n        super(prune_CNN,self).__init__()\n        \n        self.flag=0\n        self.center_array=[]\n        \n        #创建自注意机制的类\n        self.Self_Attention=MultiHeadSelfAttention(dim_in=36,d_model=36,num_heads=3)\n        \n        self.seconv=SEConv()\n        \n        self.conv=nn.Sequential(\n        nn.Conv2d(1,16,3,1,0),#30*30->28*28\n        nn.BatchNorm2d(16),\n        nn.SiLU(),\n        nn.Conv2d(16,32,3,1,0),#28*28->26*26\n        nn.BatchNorm2d(32),\n        nn.ReLU(),\n        nn.Conv2d(32,72,5,1,0),#26*26->22*22\n        nn.BatchNorm2d(72),\n        nn.Tanh(),\n        nn.Conv2d(72,115,5,1,1),#20*20\n        nn.GELU(),\n        nn.MaxPool2d(2,2,0),#10*10\n        nn.BatchNorm2d(115),\n        nn.Conv2d(115,143,5,1,0),#6*6\n        nn.SiLU(),\n        nn.BatchNorm2d(143),\n        )\n        \n        self.fc=nn.Sequential( \n        nn.Linear(143*6*6,128),\n        nn.BatchNorm1d(128),\n        nn.Dropout(p=0.2),\n        nn.GELU(),\n        nn.Linear(128,10),\n        )\n    def circle_padding(sellf,image, pad=1):\n        \"\"\"\n        input: torch.Tensor image (batch_size, channels, height, width)\n        output: pad_image (batch_size, channels, height+2*pad, width+2*pad)\n        \"\"\"\n        b, c, h, w = image.shape\n        pad_image = torch.zeros((b, c, h+2*pad, w+2*pad), device=image.device)\n\n        pad_image[:, :, pad:h+pad, pad:w+pad] = image\n        pad_image[:, :, 0:pad, pad:w+pad] = image[:, :, -pad:, :]\n        pad_image[:, :, -pad:, pad:w+pad] = image[:, :, 0:pad, :]\n        pad_image[:, :, pad:h+pad, 0:pad] = image[:, :, :, -pad:]\n        pad_image[:, :, pad:h+pad, -pad:] = image[:, :, :, 0:pad]\n        pad_image[:, :, 0:pad, 0:pad] = image[:, :, -pad:, -pad:]\n        pad_image[:, :, -pad:, -pad:] = image[:, :, 0:pad, 0:pad]\n        pad_image[:, :, 0:pad, -pad:] = image[:, :, -pad:, 0:pad]\n        pad_image[:, :, -pad:, 0:pad] = image[:, :, 0:pad, -pad:]\n\n        return pad_image\n    \n    def get_centering_array(self,image):\n        if self.flag==0:\n            #传入的是np.array的数组\n            batch_size,channels,row,col=image.shape\n            center_x=row/2\n            center_y=col/2\n            array=torch.randn(row,col).to(device)\n            for i in range(row):\n                for j in range(col):\n                    array[i][j]=math.sqrt(1- ( (i-center_x)**2+(j-center_y)**2)/( center_x**2+center_y**2 )/10)\n            self.flag=1\n            self.center_array=array\n        return image*self.center_array\n    #噪音注入\n    def noise_injection(self,features,noise_factor=0.002):\n        noise = torch.randn_like(features) * noise_factor\n        return features + noise\n    \n    def forward(self,input): \n        output=self.circle_padding(input)\n        output=self.get_centering_array(output)\n        output=self.noise_injection(output)\n        output=self.conv(output)\n        output=output.view(-1,143,6*6)#reshape\n        output=self.seconv(output)\n        output=output+self.Self_Attention(output)#跳连接\n        output=output.view(-1,143*6*6)#reshape\n        output=self.fc(output)\n        return F.log_softmax(output/5,dim=1)","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:15:05.275636Z","iopub.execute_input":"2023-07-07T00:15:05.276053Z","iopub.status.idle":"2023-07-07T00:15:05.302940Z","shell.execute_reply.started":"2023-07-07T00:15:05.276022Z","shell.execute_reply":"2023-07-07T00:15:05.301266Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"netC1=prune_CNN()\nlayer=0\nfor name,module in netC1.named_modules():\n    if isinstance(module,nn.Conv2d) or isinstance(module,nn.BatchNorm2d):  \n        module.weight.data=torch.Tensor(total_parameter[layer]).clone()\n        print(f\"module.weight.shape:{module.weight.shape}\\n total_parameter[layer].shape:{np.array(total_parameter[layer]).shape:}\")\n        print(f\"len(total_parameter[layer]):{len(total_parameter[layer])}\")\n        layer+=1","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:15:19.425238Z","iopub.execute_input":"2023-07-07T00:15:19.425947Z","iopub.status.idle":"2023-07-07T00:15:19.987957Z","shell.execute_reply.started":"2023-07-07T00:15:19.425908Z","shell.execute_reply":"2023-07-07T00:15:19.986748Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n\ntrain_accs=[]#存储训练集的准确率\nvalid_accs=[]#存储测试集的准确率\n#训练周期为1000次\nnum_epochs=1000\nbatch_size=200#一次训练的数据量\n\n#优化器\noptimizer=optim.Adam(netC1.parameters(),lr=0.00025,betas=(0.5,0.999))\n#交叉熵损失函数\ncriterion=nn.CrossEntropyLoss()\n\nnetC1.to(device)\n\nfor epoch in range(num_epochs):\n    \n    random_num=[index for index in range(len(train_X))]\n    np.random.shuffle(random_num)\n    \n    train_X=train_X[random_num]\n    \n    train_y=train_y[random_num]\n    \n    train_X1=torch.Tensor(train_X[:batch_size]).to(device)\n    train_y1=torch.Tensor(train_y[:batch_size]).long().to(device)\n    \n    #训练\n    netC1.train()\n    #将数据放进去训练\n    output=netC1(train_X1).to(device)\n    #计算每次的损失函数\n    loss=criterion(output,F.one_hot(train_y1,10).type(torch.FloatTensor).to(device)).to(device)\n    #反向传播\n    loss.backward()\n    #优化器进行优化(梯度下降,降低误差)\n    optimizer.step()\n    #将梯度清空\n    optimizer.zero_grad()\n    if epoch%50==0:\n        netC.eval()\n        with torch.no_grad():\n            output=netC1(train_X1).to(device)\n            output=output.detach().cpu().numpy()\n            train_pred=np.argmax(output,axis=1)\n\n            output=netC1(valid_X1).to(device)\n            output=output.detach().cpu().numpy()\n            valid_pred=np.argmax(output,axis=1)\n        \n        train_acc=np.sum(train_pred==train_y[:batch_size])/len(train_y[:batch_size])\n        valid_acc=np.sum(valid_pred==valid_y)/len(valid_y)\n\n        train_accs.append(train_acc)\n        valid_accs.append(valid_acc)\n        print(f\"epoch:{epoch},loss:{loss}\\n train_acc:{train_acc},valid_acc:{valid_acc}\")","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:15:45.138061Z","iopub.execute_input":"2023-07-07T00:15:45.139105Z","iopub.status.idle":"2023-07-07T00:18:25.868695Z","shell.execute_reply.started":"2023-07-07T00:15:45.139068Z","shell.execute_reply":"2023-07-07T00:18:25.867499Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"epochs=[i*50 for i in range(len(train_accs))]\nplt.title(\"Fashion_mnist_dataset\")\nplt.plot(epochs,train_accs,marker=\"o\",label=\"train_accs\")\nplt.plot(epochs,valid_accs,marker=\"x\",label=\"valid_accs\")\nplt.legend()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:18:43.557944Z","iopub.execute_input":"2023-07-07T00:18:43.558347Z","iopub.status.idle":"2023-07-07T00:18:43.916145Z","shell.execute_reply.started":"2023-07-07T00:18:43.558315Z","shell.execute_reply":"2023-07-07T00:18:43.915129Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test=pd.read_csv(\"/kaggle/input/ece597697-sp2023/test.csv/test.csv\")\ntest=test.drop(['id'],axis=1)\ntest_X=test.values/255.0-0.5\ny_pred=[]\nfor i in range(len(test_X)):\n    netC1.eval()\n    with torch.no_grad():\n        image=test_X[i].reshape((1,1,28,28))\n        pred=netC1(torch.Tensor(image).to(device))[0]\n        pred=np.argmax(pred.detach().cpu().numpy())\n        y_pred.append(pred)","metadata":{"execution":{"iopub.status.busy":"2023-07-07T00:19:43.858074Z","iopub.execute_input":"2023-07-07T00:19:43.858752Z","iopub.status.idle":"2023-07-07T00:20:09.174125Z","shell.execute_reply.started":"2023-07-07T00:19:43.858719Z","shell.execute_reply":"2023-07-07T00:20:09.172754Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#写入文件\nimport csv\nhead=[\"id\",\"label\"]\ndata=[]\nfor index in range(len(y_pred)):\n    data.append([index,y_pred[index]])\nwith open(\"fashion_mnsit_submission.csv\",'w',newline='') as f:\n    writer=csv.writer(f)\n    writer.writerow(head)\n    writer.writerows(data)","metadata":{},"execution_count":null,"outputs":[]}]}