外包公司做网站图片哪里整的,数据查询网站,陕西网站建设设计,企业网站后台内容如何修改本文为#x1f517;365天深度学习训练营 中的学习记录博客 原作者#xff1a;K同学啊|接辅导、项目定制
我的环境#xff1a;
1.语言#xff1a;python3.7
2.编译器#xff1a;pycharm
3.深度学习框架Tensorflow/Pytorch 1.8.0cu111 一、问题引出 CNN能够提取低、中、… 本文为365天深度学习训练营 中的学习记录博客 原作者K同学啊|接辅导、项目定制
我的环境
1.语言python3.7
2.编译器pycharm
3.深度学习框架Tensorflow/Pytorch 1.8.0cu111 一、问题引出 CNN能够提取低、中、高层的特征网络的层数越多意味着能够提取到不同level的特征越丰富。并且越深的网络提取的特征越抽象越具有语义信息。但是如果只是简单地增加深度会导致梯度爆炸。 最初对于该问题的解决方法是正则化初始化和中间的正则化层。这样的话可以训练几十层的网络。虽然通过上述方法能够训练了但是又会出现另一个问题就是退化问题网络层数增加但是在训练集上的准确率却饱和甚至下降了。退化问题说明了深度网络不能很简单地被很好地优化。
直白来讲 假设一个30层的网络跟一个15层的网络30层的网络解空间是包含了15层网络的解空间的一般来说30层的性能肯定优于15层的性能。但实验表明30层的网络无论是训练误差还是测试误差均大于15层的网络。因为我们在训练网络时采用的时随机梯度下降得到的往往不是最优解而是局部最优因为30层的网络解空间更加复杂导致利用随机梯度下降无法得到最优解
二、残差网络介绍 为了解决退化问题何恺明提出了深度残差网络ResNet。如果深层网络的后面那些层是恒等映射那么模型就退化为一个浅层网络。那现在要解决的就是学习恒等映射函数了。 但是直接让一些层去拟合一个潜在的恒等映射函数比较困难如果我们把网络设计为,我们可以转换为学习一个残差函数,只要就构成了一个恒等映射. 理论上对于“随着网络加深准确率下降”的问题Resnet提供了两种选择方式也就是identity mapping和residual mapping如果网络已经到达最优继续加深网络residual mapping将被push为0只剩下identity mapping这样理论上网络一直处于最优状态了网络的性能也就不会随着深度增加而降低了。 三、Tensorflow代码
import tensorflow as tf
gpus tf.config.list_physical_devices(GPU)if gpus:gpu0 gpus[0]tf.config.experimental.set_memory_growth(gpu0, True)tf.config.set_visible_devices([gpu0],GPU)import os, PIL, pathlib
import matplotlib.pyplot as pltdata_dir E:/TF环境/ResNet50/bird_photos
data_dir pathlib.Path(data_dir)
image_count len(list(data_dir.glob(*/*)))print(图片总数为, image_count)batch_size 8
img_height 224
img_width 224train_ds tf.keras.preprocessing.image_dataset_from_directory(data_dir,validation_split0.2,subsettraining,seed 123,image_size (img_height, img_width),batch_size batch_size
)val_ds tf.keras.preprocessing.image_dataset_from_directory(data_dir,validation_split0.2,subsetvalidation,seed 123,image_size (img_height, img_width),batch_size batch_size
)class_names train_ds.class_names
print(class_names)plt.figure(figsize (10, 5))for images, labels in train_ds.take(1):for i in range(8):ax plt.subplot(2, 4, i 1)plt.imshow(images[i].numpy().astype(uint8))plt.title(class_names[labels[i]])plt.axis(off)
plt.show()#再次检查数据
for image_batch, labels_batch in train_ds:print(image_batch.shape)print(labels_batch.shape)breakAUTOTUNE tf.data.AUTOTUNE
train_ds train_ds.cache().shuffle(1000).prefetch(buffer_sizeAUTOTUNE)
val_ds val_ds.cache().prefetch(buffer_sizeAUTOTUNE)from tensorflow.keras.layers import Dropout
import tensorflow as tf
import glob
import numpy as np
import matplotlib.pyplot as pltfrom tensorflow.keras.layers import Input
from tensorflow.keras.layers import Dense, Conv2D, MaxPooling2D, ZeroPadding2D, AveragePooling2D
from tensorflow.keras.layers import Activation, BatchNormalization, Flatten
from tensorflow.keras.models import Modelfrom tensorflow.keras import layersdef identity_block(input_tensor, kernel_size, filters, stage, block):# 64,64,256filters1, filters2, filters3 filtersname_base str(stage) block identity_block_# 降维x Conv2D(filters1, (1, 1),namename_base conv1)(input_tensor)x BatchNormalization(namename_base bn1)(x)x Activation(relu,namename_base relu1)(x)# 3x3卷积x Conv2D(filters2, kernel_size, paddingsame,namename_base conv2)(x)x BatchNormalization(namename_base bn2)(x)x Activation(relu, namename_base relu2)(x)# 升维x Conv2D(filters3, (1, 1), namename_base conv3)(x)x BatchNormalization(namename_base bn3)(x)x layers.add([x, input_tensor],namename_base add)x Activation(relu,namename_base relu4)(x)return xdef conv_block(input_tensor, kernel_size, filters, stage, block,strides (2,2)):filters1, filters2, filters3 filtersres_name_base str(stage) block _conv_block_res_name_base str(stage) block _conv_block_# 降维x Conv2D(filters1, (1, 1), strides strides ,namename_base conv1)(input_tensor)x BatchNormalization(namename_base bn1)(x)x Activation(relu,namename_base relu1)(x)# 3x3卷积x Conv2D(filters2, kernel_size, paddingsame, namename_base conv2)(x)x BatchNormalization(namename_base bn2)(x)x Activation(relu,namename_base relu2)(x)x Conv2D(filters3, (1,1), namename_base conv3)(x)x BatchNormalization(namename_base bn3)(x)shortcut Conv2D(filters3, (1,1),strides strides ,nameres_name_base conv)(input_tensor)shortcut BatchNormalization(name res_name_base bn)(shortcut)x layers.add([x, shortcut],namename_base add)x Activation(relu,namename_base relu4)(x)return xdef ResNet50(input_shape[224, 224, 3], classes1000):img_input Input(shapeinput_shape)x ZeroPadding2D((3, 3))(img_input) # [230,230,3]# [112,112,64]x Conv2D(64, (7, 7), strides(2, 2), nameconv1)(x) # [112,112,64]x BatchNormalization(namebn_conv1)(x)x Activation(relu)(x)x MaxPooling2D((3, 3), strides(2, 2))(x)x conv_block(x, 3, [64, 64, 256], stage2, blocka, strides(1, 1))x identity_block(x, 3, [64, 64, 256], stage2, blockb)x identity_block(x, 3, [64, 64, 256], stage2, blockc)# [28,28,512]x conv_block(x, 3, [128, 128, 512], stage3, blocka)x identity_block(x, 3, [128, 128, 512], stage3, blockb)x identity_block(x, 3, [128, 128, 512], stage3, blockc)x identity_block(x, 3, [128, 128, 512], stage3, blockd)# [14,14,1024]x conv_block(x, 3, [256, 256, 1024], stage4, blocka)x identity_block(x, 3, [256, 256, 1024], stage4, blockb)x identity_block(x, 3, [256, 256, 1024], stage4, blockc)x identity_block(x, 3, [256, 256, 1024], stage4, blockd)x identity_block(x, 3, [256, 256, 1024], stage4, blocke)x identity_block(x, 3, [256, 256, 1024], stage4, blockf)# [7,7,2048]x conv_block(x, 3, [512, 512, 2048], stage5, blocka)x identity_block(x, 3, [512, 512, 2048], stage5, blockb)x identity_block(x, 3, [512, 512, 2048], stage5, blockc)# 代替全连接层x AveragePooling2D((7, 7), nameavg_pool)(x)# 进行预测x Flatten()(x)x Dense(classes, activationsoftmax, namefc1000)(x)model Model(img_input, x, nameresnet50)model.load_weights(E:/TF环境/ResNet50/resnet50_weights_tf_dim_ordering_tf_kernels.h5)return modelmodel ResNet50()
model.summary()opt tf.keras.optimizers.Adam(learning_rate1e-7)
model.compile(optimizeradam,losssparse_categorical_crossentropy,metrics[accuracy]
)epochs 10
history model.fit(train_ds,validation_dataval_ds,epochsepochs,)acc history.history[accuracy]
val_acc history.history[val_accuracy]loss history.history[loss]
val_loss history.history[val_loss]epochs_range range(epochs)plt.figure(figsize(12, 4))
plt.subplot(1, 2, 1)plt.plot(epochs_range, acc, labelTraining Accuracy)
plt.plot(epochs_range, val_acc, labelValidation Accuracy)
plt.legend(loclower right)
plt.title(Training and Validation Accuracy)plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, labelTraining Loss)
plt.plot(epochs_range, val_loss, labelValidation Loss)
plt.legend(locupper right)
plt.title(Training and Validation Loss)
plt.show()for images,labels in val_ds.take(1):for i in range(8):ax plt.subplot(2,4,i1)plt.imshow(images[i].numpy().astype(uint8))img_array tf.expand_dims(imges[i],0)predictions model.predict(img_array)plt.title(class_names[np.argmax(predictions)])plt.axis(off)plt.show() 四、pytorch 代码
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warningswarnings.filterwarnings(ignore) #忽略警告信息device torch.device(cuda if torch.cuda.is_available() else cpu)
print(device)data_dir E:/TF环境/ResNet50/bird_photos
data_dir pathlib.Path(data_dir)data_paths list(data_dir.glob(*))
classeNames [str(path).split(\\)[4] for path in data_paths]
print(classeNames)train_transforms transforms.Compose([transforms.Resize([224,224]),transforms.ToTensor(),transforms.Normalize(mean [0.485,0.456,0.406],std [0.229,0.224,0.225])
])test_transforms transforms.Compose([transforms.Resize([224,224]),transforms.ToTensor(),transforms.Normalize(mean [0.485,0.456,0.406],std [0.229,0.224,0.225])
])total_data datasets.ImageFolder(E:/TF环境/ResNet50/bird_photos,transform train_transforms)
print(total_data)train_size int(0.8 * len(total_data))
test_size len(total_data) - train_size
train_dataset, test_dataset torch.utils.data.random_split(total_data, [train_size, test_size])
print(train_dataset)
print(test_dataset)batch_size 8train_dl torch.utils.data.DataLoader(train_dataset,batch_sizebatch_size,shuffleTrue,#num_workers1)
test_dl torch.utils.data.DataLoader(test_dataset,batch_sizebatch_size,shuffleTrue,#num_workers1)for X, y in test_dl:print(Shape of X [N, C, H, W]: , X.shape)print(Shape of y: , y.shape, y.dtype)breakfrom torch import nn
from torch.nn import functional as Fimport torch.nn.functional as F# 构造ResNet50模型
class ResNetblock(nn.Module):def __init__(self, in_channels, out_channels, stride1):super(ResNetblock, self).__init__()self.blockconv nn.Sequential(nn.Conv2d(in_channels, out_channels, kernel_size1, stridestride),nn.BatchNorm2d(out_channels),nn.ReLU(),nn.Conv2d(out_channels, out_channels, kernel_size3, stride1, padding1),nn.BatchNorm2d(out_channels),nn.ReLU(),nn.Conv2d(out_channels, out_channels * 4, kernel_size1, stride1),nn.BatchNorm2d(out_channels * 4))if stride ! 1 or in_channels ! out_channels * 4:self.shortcut nn.Sequential(nn.Conv2d(in_channels, out_channels * 4, kernel_size1, stridestride),nn.BatchNorm2d(out_channels * 4))def forward(self, x):residual xout self.blockconv(x)if hasattr(self, shortcut): # 如果self中含有shortcut属性residual self.shortcut(x)out residualout F.relu(out)return outclass ResNet50(nn.Module):def __init__(self, block, num_classes1000):super(ResNet50, self).__init__()self.conv1 nn.Sequential(nn.ZeroPad2d(3),nn.Conv2d(3, 64, kernel_size7, stride2),nn.BatchNorm2d(64),nn.ReLU(),nn.MaxPool2d((3, 3), stride2))self.in_channels 64# ResNet50中的四大层每大层都是由ConvBlock与IdentityBlock堆叠而成self.layer1 self.make_layer(ResNetblock, 64, 3, stride1)self.layer2 self.make_layer(ResNetblock, 128, 4, stride2)self.layer3 self.make_layer(ResNetblock, 256, 6, stride2)self.layer4 self.make_layer(ResNetblock, 512, 3, stride2)self.avgpool nn.AvgPool2d((7, 7))self.fc nn.Linear(512 * 4, num_classes)# 每个大层的定义函数def make_layer(self, block, channels, num_blocks, stride1):strides [stride] [1] * (num_blocks - 1)layers []for stride in strides:layers.append(block(self.in_channels, channels, stride))self.in_channels channels * 4return nn.Sequential(*layers)def forward(self, x):out self.conv1(x)out self.layer1(out)out self.layer2(out)out self.layer3(out)out self.layer4(out)out self.avgpool(out)out out.view(out.size(0), -1)out self.fc(out)return outmodel ResNet50(blockResNetblock, num_classeslen(classeNames)).to(device)
model# 统计模型参数量以及其他指标
import torchsummary as summary
summary.summary(model, (3, 224, 224))def train(dataloader,model,optimizer,loss_fn):size len(dataloader.dataset)num_batches len(dataloader)train_acc,train_loss 0,0for X,y in dataloader:X,y X.to(device),y.to(device)pred model(X)loss loss_fn(pred,y)optimizer.zero_grad()loss.backward()optimizer.step()train_loss loss.item()train_acc (pred.argmax(1) y).type(torch.float).sum().item()train_loss / num_batchestrain_acc / sizereturn train_acc,train_lossdef test(dataloader, model, loss_fn):size len(dataloader.dataset) # 测试集的大小num_batches len(dataloader) # 批次数目, (size/batch_size向上取整)test_loss, test_acc 0, 0# 当不进行训练时停止梯度更新节省计算内存消耗with torch.no_grad():for imgs, target in dataloader:imgs, target imgs.to(device), target.to(device)# 计算losstarget_pred model(imgs)loss loss_fn(target_pred, target)test_loss loss.item()test_acc (target_pred.argmax(1) target).type(torch.float).sum().item()test_acc / sizetest_loss / num_batchesreturn test_acc, test_lossloss_fn nn.CrossEntropyLoss()
learn_rate 1e-2
opt torch.optim.SGD(model.parameters(),lrlearn_rate)import copyepochs 10train_loss[]
train_acc[]
test_loss[]
test_acc[]
best_acc 0for epoch in range(epochs):model.train()epoch_train_acc,epoch_train_loss train(train_dl,model,opt,loss_fn)model.eval()epoch_test_acc,epoch_test_loss test(test_dl,model,loss_fn)if epoch_test_acc best_acc:best_acc epoch_test_accbest_model copy.deepcopy(model)train_acc.append(epoch_train_acc)train_loss.append(epoch_train_loss)test_acc.append(epoch_test_acc)test_loss.append(epoch_test_loss)lr opt.state_dict()[param_groups][0][lr]template (Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E})print(template.format(epoch1, epoch_train_acc*100, epoch_train_loss,epoch_test_acc*100, epoch_test_loss, lr))# 保存最佳模型到文件中
PATH E:/pythonProject pytorch/J1_birds_model.pth # 保存的参数文件名
torch.save(best_model.state_dict(), PATH)print(Done)import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings(ignore) #忽略警告信息
plt.rcParams[font.sans-serif] [SimHei] # 用来正常显示中文标签
plt.rcParams[axes.unicode_minus] False # 用来正常显示负号
plt.rcParams[figure.dpi] 100 #分辨率epochs_range range(epochs)plt.figure(figsize(12, 3))
plt.subplot(1, 2, 1)plt.plot(epochs_range, train_acc, labelTraining Accuracy)
plt.plot(epochs_range, test_acc, labelTest Accuracy)
plt.legend(loclower right)
plt.title(Training and Validation Accuracy)plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, labelTraining Loss)
plt.plot(epochs_range, test_loss, labelTest Loss)
plt.legend(locupper right)
plt.title(Training and Validation Loss)
plt.show()Layer (type) Output Shape Param # ZeroPad2d-1 [-1, 3, 230, 230] 0 Conv2d-2 [-1, 64, 112, 112] 9,472 BatchNorm2d-3 [-1, 64, 112, 112] 128 ReLU-4 [-1, 64, 112, 112] 0 MaxPool2d-5 [-1, 64, 55, 55] 0 Conv2d-6 [-1, 64, 55, 55] 4,160 BatchNorm2d-7 [-1, 64, 55, 55] 128 ReLU-8 [-1, 64, 55, 55] 0 Conv2d-9 [-1, 64, 55, 55] 36,928 BatchNorm2d-10 [-1, 64, 55, 55] 128 ReLU-11 [-1, 64, 55, 55] 0 Conv2d-12 [-1, 256, 55, 55] 16,640 BatchNorm2d-13 [-1, 256, 55, 55] 512 Conv2d-14 [-1, 256, 55, 55] 16,640 BatchNorm2d-15 [-1, 256, 55, 55] 512 ResNetblock-16 [-1, 256, 55, 55] 0 Conv2d-17 [-1, 64, 55, 55] 16,448 BatchNorm2d-18 [-1, 64, 55, 55] 128 ReLU-19 [-1, 64, 55, 55] 0 Conv2d-20 [-1, 64, 55, 55] 36,928 BatchNorm2d-21 [-1, 64, 55, 55] 128 ReLU-22 [-1, 64, 55, 55] 0 Conv2d-23 [-1, 256, 55, 55] 16,640 BatchNorm2d-24 [-1, 256, 55, 55] 512 ResNetblock-25 [-1, 256, 55, 55] 0 Conv2d-26 [-1, 64, 55, 55] 16,448 BatchNorm2d-27 [-1, 64, 55, 55] 128 ReLU-28 [-1, 64, 55, 55] 0 Conv2d-29 [-1, 64, 55, 55] 36,928 BatchNorm2d-30 [-1, 64, 55, 55] 128 ReLU-31 [-1, 64, 55, 55] 0 Conv2d-32 [-1, 256, 55, 55] 16,640 BatchNorm2d-33 [-1, 256, 55, 55] 512 ResNetblock-34 [-1, 256, 55, 55] 0 Conv2d-35 [-1, 128, 28, 28] 32,896 BatchNorm2d-36 [-1, 128, 28, 28] 256 ReLU-37 [-1, 128, 28, 28] 0 Conv2d-38 [-1, 128, 28, 28] 147,584 BatchNorm2d-39 [-1, 128, 28, 28] 256 ReLU-40 [-1, 128, 28, 28] 0 Conv2d-41 [-1, 512, 28, 28] 66,048 BatchNorm2d-42 [-1, 512, 28, 28] 1,024 Conv2d-43 [-1, 512, 28, 28] 131,584 BatchNorm2d-44 [-1, 512, 28, 28] 1,024 ResNetblock-45 [-1, 512, 28, 28] 0 Conv2d-46 [-1, 128, 28, 28] 65,664 BatchNorm2d-47 [-1, 128, 28, 28] 256 ReLU-48 [-1, 128, 28, 28] 0 Conv2d-49 [-1, 128, 28, 28] 147,584 BatchNorm2d-50 [-1, 128, 28, 28] 256 ReLU-51 [-1, 128, 28, 28] 0 Conv2d-52 [-1, 512, 28, 28] 66,048 BatchNorm2d-53 [-1, 512, 28, 28] 1,024 ResNetblock-54 [-1, 512, 28, 28] 0 Conv2d-55 [-1, 128, 28, 28] 65,664 BatchNorm2d-56 [-1, 128, 28, 28] 256 ReLU-57 [-1, 128, 28, 28] 0 Conv2d-58 [-1, 128, 28, 28] 147,584 BatchNorm2d-59 [-1, 128, 28, 28] 256 ReLU-60 [-1, 128, 28, 28] 0 Conv2d-61 [-1, 512, 28, 28] 66,048 BatchNorm2d-62 [-1, 512, 28, 28] 1,024 ResNetblock-63 [-1, 512, 28, 28] 0 Conv2d-64 [-1, 128, 28, 28] 65,664 BatchNorm2d-65 [-1, 128, 28, 28] 256 ReLU-66 [-1, 128, 28, 28] 0 Conv2d-67 [-1, 128, 28, 28] 147,584 BatchNorm2d-68 [-1, 128, 28, 28] 256 ReLU-69 [-1, 128, 28, 28] 0 Conv2d-70 [-1, 512, 28, 28] 66,048 BatchNorm2d-71 [-1, 512, 28, 28] 1,024 ResNetblock-72 [-1, 512, 28, 28] 0 Conv2d-73 [-1, 256, 14, 14] 131,328 BatchNorm2d-74 [-1, 256, 14, 14] 512 ReLU-75 [-1, 256, 14, 14] 0 Conv2d-76 [-1, 256, 14, 14] 590,080 BatchNorm2d-77 [-1, 256, 14, 14] 512 ReLU-78 [-1, 256, 14, 14] 0 Conv2d-79 [-1, 1024, 14, 14] 263,168 BatchNorm2d-80 [-1, 1024, 14, 14] 2,048 Conv2d-81 [-1, 1024, 14, 14] 525,312 BatchNorm2d-82 [-1, 1024, 14, 14] 2,048 ResNetblock-83 [-1, 1024, 14, 14] 0 Conv2d-84 [-1, 256, 14, 14] 262,400 BatchNorm2d-85 [-1, 256, 14, 14] 512 ReLU-86 [-1, 256, 14, 14] 0 Conv2d-87 [-1, 256, 14, 14] 590,080 BatchNorm2d-88 [-1, 256, 14, 14] 512 ReLU-89 [-1, 256, 14, 14] 0 Conv2d-90 [-1, 1024, 14, 14] 263,168 BatchNorm2d-91 [-1, 1024, 14, 14] 2,048 ResNetblock-92 [-1, 1024, 14, 14] 0 Conv2d-93 [-1, 256, 14, 14] 262,400 BatchNorm2d-94 [-1, 256, 14, 14] 512 ReLU-95 [-1, 256, 14, 14] 0 Conv2d-96 [-1, 256, 14, 14] 590,080 BatchNorm2d-97 [-1, 256, 14, 14] 512 ReLU-98 [-1, 256, 14, 14] 0 Conv2d-99 [-1, 1024, 14, 14] 263,168 BatchNorm2d-100 [-1, 1024, 14, 14] 2,048 ResNetblock-101 [-1, 1024, 14, 14] 0 Conv2d-102 [-1, 256, 14, 14] 262,400 BatchNorm2d-103 [-1, 256, 14, 14] 512 ReLU-104 [-1, 256, 14, 14] 0 Conv2d-105 [-1, 256, 14, 14] 590,080 BatchNorm2d-106 [-1, 256, 14, 14] 512 ReLU-107 [-1, 256, 14, 14] 0 Conv2d-108 [-1, 1024, 14, 14] 263,168 BatchNorm2d-109 [-1, 1024, 14, 14] 2,048 ResNetblock-110 [-1, 1024, 14, 14] 0 Conv2d-111 [-1, 256, 14, 14] 262,400 BatchNorm2d-112 [-1, 256, 14, 14] 512 ReLU-113 [-1, 256, 14, 14] 0 Conv2d-114 [-1, 256, 14, 14] 590,080 BatchNorm2d-115 [-1, 256, 14, 14] 512 ReLU-116 [-1, 256, 14, 14] 0 Conv2d-117 [-1, 1024, 14, 14] 263,168 BatchNorm2d-118 [-1, 1024, 14, 14] 2,048 ResNetblock-119 [-1, 1024, 14, 14] 0 Conv2d-120 [-1, 256, 14, 14] 262,400 BatchNorm2d-121 [-1, 256, 14, 14] 512 ReLU-122 [-1, 256, 14, 14] 0 Conv2d-123 [-1, 256, 14, 14] 590,080 BatchNorm2d-124 [-1, 256, 14, 14] 512 ReLU-125 [-1, 256, 14, 14] 0 Conv2d-126 [-1, 1024, 14, 14] 263,168 BatchNorm2d-127 [-1, 1024, 14, 14] 2,048 ResNetblock-128 [-1, 1024, 14, 14] 0 Conv2d-129 [-1, 512, 7, 7] 524,800 BatchNorm2d-130 [-1, 512, 7, 7] 1,024 ReLU-131 [-1, 512, 7, 7] 0 Conv2d-132 [-1, 512, 7, 7] 2,359,808 BatchNorm2d-133 [-1, 512, 7, 7] 1,024 ReLU-134 [-1, 512, 7, 7] 0 Conv2d-135 [-1, 2048, 7, 7] 1,050,624 BatchNorm2d-136 [-1, 2048, 7, 7] 4,096 Conv2d-137 [-1, 2048, 7, 7] 2,099,200 BatchNorm2d-138 [-1, 2048, 7, 7] 4,096 ResNetblock-139 [-1, 2048, 7, 7] 0 Conv2d-140 [-1, 512, 7, 7] 1,049,088 BatchNorm2d-141 [-1, 512, 7, 7] 1,024 ReLU-142 [-1, 512, 7, 7] 0 Conv2d-143 [-1, 512, 7, 7] 2,359,808 BatchNorm2d-144 [-1, 512, 7, 7] 1,024 ReLU-145 [-1, 512, 7, 7] 0 Conv2d-146 [-1, 2048, 7, 7] 1,050,624 BatchNorm2d-147 [-1, 2048, 7, 7] 4,096 ResNetblock-148 [-1, 2048, 7, 7] 0 Conv2d-149 [-1, 512, 7, 7] 1,049,088 BatchNorm2d-150 [-1, 512, 7, 7] 1,024 ReLU-151 [-1, 512, 7, 7] 0 Conv2d-152 [-1, 512, 7, 7] 2,359,808 BatchNorm2d-153 [-1, 512, 7, 7] 1,024 ReLU-154 [-1, 512, 7, 7] 0 Conv2d-155 [-1, 2048, 7, 7] 1,050,624 BatchNorm2d-156 [-1, 2048, 7, 7] 4,096 ResNetblock-157 [-1, 2048, 7, 7] 0 AvgPool2d-158 [-1, 2048, 1, 1] 0 Linear-159 [-1, 4] 8,196 Total params: 23,542,788 Trainable params: 23,542,788 Non-trainable params: 0 ---------------------------------------------------------------- Input size (MB): 0.57 Forward/backward pass size (MB): 230.18 Params size (MB): 89.81 Estimated Total Size (MB): 320.56 ---------------------------------------------------------------- Epoch: 1, Train_acc:38.7%, Train_loss:2.877, Test_acc:34.5%, Test_loss:4.936, Lr:1.00E-02 Epoch: 2, Train_acc:53.1%, Train_loss:1.403, Test_acc:64.6%, Test_loss:1.721, Lr:1.00E-02 Epoch: 3, Train_acc:58.8%, Train_loss:1.243, Test_acc:49.6%, Test_loss:1.154, Lr:1.00E-02 Epoch: 4, Train_acc:60.2%, Train_loss:1.238, Test_acc:16.8%, Test_loss:48.591, Lr:1.00E-02 Epoch: 5, Train_acc:53.1%, Train_loss:1.455, Test_acc:46.9%, Test_loss:2.093, Lr:1.00E-02 Epoch: 6, Train_acc:61.9%, Train_loss:1.073, Test_acc:31.9%, Test_loss:38.314, Lr:1.00E-02 Epoch: 7, Train_acc:63.3%, Train_loss:0.964, Test_acc:72.6%, Test_loss:0.938, Lr:1.00E-02 Epoch: 8, Train_acc:67.3%, Train_loss:0.911, Test_acc:47.8%, Test_loss:1.117, Lr:1.00E-02 Epoch: 9, Train_acc:67.3%, Train_loss:0.892, Test_acc:54.0%, Test_loss:16.555, Lr:1.00E-02 Epoch:10, Train_acc:71.9%, Train_loss:0.765, Test_acc:67.3%, Test_loss:1.575, Lr:1.00E-02 Done
