苏州网站建设信息网络,wordpress抓取别人网站,微琅 网站建设,广告机器设备的价格表目录 1. 第一题2. 第二题3. 第三题 ⏰ 时间#xff1a;2024/08/19 #x1f504; 输入输出#xff1a;ACM格式 ⏳ 时长#xff1a;2h 本试卷分为单选#xff0c;自我评价题#xff0c;编程题
单选和自我评价这里不再介绍#xff0c;4399的编程题一如既往地抽象#xff… 目录 1. 第一题2. 第二题3. 第三题 ⏰ 时间2024/08/19 输入输出ACM格式 ⏳ 时长2h 本试卷分为单选自我评价题编程题
单选和自我评价这里不再介绍4399的编程题一如既往地抽象明明是NLP岗位的笔试题却考了OpenCV相关的知识。btw跟网友讨论了下4399似乎不同时间节点的笔试题是一样的
1. 第一题
第一题是LC原题441. 排列硬币题目和题解请前往LC查看。
2. 第二题
题目描述
请使用OpenCV库编写程序实现在视频文件中实时追踪一个人手持手机绿幕的四个顶点的坐标。
要求
使用颜色分割技术检测绿幕区域。(8分)使用适当的方法如轮廓检测找到绿幕的四个顶点。(10分)在视频帧中标记出这四个顶点。(8分)
手机绿幕指手机屏幕显示全绿色图片用于后期处理替换为其他界面绿色范围lower_green np.array([35, 100, 100])upper_green np.array([85, 255, 255])。
测试用例
输入green_screen_track.mp4
输出带顶点标记的视频序列帧图片 题解
import cv2
import numpy as nplower_green np.array([35, 100, 100])
upper_green np.array([85, 255, 255])def get_largest_contour(contours): 获取最大轮廓 max_contour max(contours, keycv2.contourArea)return max_contourdef get_four_vertices(contour): 近似轮廓为四边形 epsilon 0.02 * cv2.arcLength(contour, True)approx cv2.approxPolyDP(contour, epsilon, True)if len(approx) 4:return approx.reshape(4, 2)else:return Nonedef main(video_path):cap cv2.VideoCapture(video_path)while cap.isOpened():ret, frame cap.read()if not ret:breakhsv_frame cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)mask cv2.inRange(hsv_frame, lower_green, upper_green)contours, _ cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)if contours:largest_contour get_largest_contour(contours)vertices get_four_vertices(largest_contour)if vertices is not None:for (x, y) in vertices:cv2.circle(frame, (x, y), 5, (0, 0, 255), -1)cv2.polylines(frame, [vertices], isClosedTrue, color(0, 255, 0), thickness2)cv2.imshow(Green Screen Tracking, frame)if cv2.waitKey(1) 0xFF ord(q):breakcap.release()cv2.destroyAllWindows()if __name__ __main__:video_path green_screen_track.mp4main(video_path)3. 第三题
You can use Chinese to answer the questions.
Problem Description
You need to use the Swin Transformer model to train a binary classifier to identify whether an image contains a green screen. Green screens are commonly used in video production and photography for background replacement in post-production. Your task is to write a program that uses the Swin Transformer model to train and evaluate the performance of this classifier.
Input Data
Training Dataset: A set of images, including images with and without green screens.Labels: Labels for each image, where 0 indicates no green screen and 1 indicates the presence of a green screen.
Output Requirements
Trained Model: Train a binary classifier using the Swin Transformer model.Model Evaluation: Evaluate the model’s accuracy, precision, recall, and F1-score on a validation or test set.
Programming Requirements
Data Preprocessing: Including image loading, normalization, and label processing.Model Definition: Using the Swin Transformer model.Training Process: Including loss function, optimizer, and training loop.Evaluation Process: Evaluate the model’s performance on the validation or test set.Results Presentation: Output evaluation metrics and visualize some prediction results.
Here is a sample code framework to help you get started:
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, Dataset
from torchvision import transforms, datasets
from swin_transformer_pytorch import SwinTransformer
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
from PIL import Image# Dataset class definition
class GreenScreenDataset(Dataset):def __init__(self, image_paths, labels, transformNone):self.image_paths image_pathsself.labels labelsself.transform transformdef __len__(self):return len(self.image_paths)def __getitem__(self, idx):image Image.open(self.image_paths[idx]).convert(RGB)label self.labels[idx]if self.transform:image self.transform(image)return image, label# Data preprocessing, please define transform
# TODO# Load datasets
train_dataset GreenScreenDataset(train_image_paths, train_labels, transformtransform)
train_loader DataLoader(train_dataset, batch_size32, shuffleTrue)val_dataset GreenScreenDataset(val_image_paths, val_labels, transformtransform)
val_loader DataLoader(val_dataset, batch_size32, shuffleFalse)# Define the SwinTransformer model
# TODO# Loss function and optimizer
criterion nn.CrossEntropyLoss()
# TODO# Training process
def train(model, train_loader, criterion, optimizer, num_epochs10):model.train()for epoch in range(num_epochs):running_loss 0.0for images, labels in train_loader:# TODO: forward pass, compute loss, backpropagation, optimizer steprunning_loss loss.item()print(fEpoch [{epoch1}/{num_epochs}], Loss: {running_loss/len(train_loader):.4f})# Evaluation process
def evaluate(model, val_loader):model.eval()all_preds []all_labels []with torch.no_grad():for images, labels in val_loader:outputs model(images)_, preds torch.max(outputs, 1)all_preds.extend(preds.cpu().numpy())all_labels.extend(labels.cpu().numpy())accuracy accuracy_score(all_labels, all_preds)# TODO: Calculate precision, recall, and F1-scoreprint(fAccuracy: {accuracy:.4f}, Precision: {precision:.4f}, Recall: {recall:.4f}, F1-score: {f1:.4f})# Train the model
train(model, train_loader, criterion, optimizer, num_epochs10)# Evaluate the model
evaluate(model, val_loader)题解
该问题要求训练一个基于Swin Transformer模型的二分类器用以识别图像中是否包含绿幕。解决方案涉及数据预处理、模型设计、训练和评估等多个环节。
首先在数据预处理阶段图像需要被调整大小并进行归一化以满足Swin Transformer的输入需求。此外数据集中的标签是二值化的分别代表有无绿幕0表示无绿幕1表示有绿幕确保数据集类能够准确处理这些标签是至关重要的。在模型设计上使用了预训练的Swin Transformer模型并针对二分类任务进行了微调。输出层被替换为一个具有两个节点的全连接层分别对应两个类别。通过这种方式模型能够有效地适应二分类任务。训练过程采用了标准的训练循环设置了损失函数和优化器并使用学习率调度器动态调整学习率。此外为了防止过拟合模型在训练过程中还应用了正则化技术如dropout。在模型评估阶段除了准确率还使用了精确率、召回率和F1分数等指标以全面评估模型在二分类任务中的表现。同时为了更直观地展示模型效果选择了一些样本图像进行可视化显示它们的预测结果与实际标签的对比。
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, Dataset
from torchvision import transforms
from swin_transformer_pytorch import SwinTransformer
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
from PIL import Image
import matplotlib.pyplot as plt
import numpy as np# 数据集类定义
class GreenScreenDataset(Dataset):def __init__(self, image_paths, labels, transformNone):self.image_paths image_pathsself.labels labelsself.transform transformdef __len__(self):return len(self.image_paths)def __getitem__(self, idx):image Image.open(self.image_paths[idx]).convert(RGB)label self.labels[idx]if self.transform:image self.transform(image)return image, torch.tensor(label, dtypetorch.long)# 数据预处理
transform transforms.Compose([transforms.Resize((224, 224)),transforms.ToTensor(),transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])train_dataset GreenScreenDataset(train_image_paths, train_labels, transformtransform)
train_loader DataLoader(train_dataset, batch_size32, shuffleTrue)val_dataset GreenScreenDataset(val_image_paths, val_labels, transformtransform)
val_loader DataLoader(val_dataset, batch_size32, shuffleFalse)model SwinTransformer(hidden_dim96,layers(2, 2, 6, 2),num_heads(3, 6, 12, 24),num_classes2,window_size7,input_resolution224
)
model model.to(torch.device(cuda if torch.cuda.is_available() else cpu))criterion nn.CrossEntropyLoss()
optimizer optim.AdamW(model.parameters(), lr1e-4, weight_decay0.01)
scheduler torch.optim.lr_scheduler.StepLR(optimizer, step_size5, gamma0.1)# 训练
def train(model, train_loader, criterion, optimizer, scheduler, num_epochs10):model.train()for epoch in range(num_epochs):running_loss 0.0for images, labels in train_loader:images, labels images.to(device), labels.to(device)optimizer.zero_grad()outputs model(images)loss criterion(outputs, labels)loss.backward()optimizer.step()running_loss loss.item()scheduler.step()print(fEpoch [{epoch1}/{num_epochs}], Loss: {running_loss/len(train_loader):.4f})# 模型评估
def evaluate(model, val_loader):model.eval()all_preds []all_labels []with torch.no_grad():for images, labels in val_loader:images, labels images.to(device), labels.to(device)outputs model(images)_, preds torch.max(outputs, 1)all_preds.extend(preds.cpu().numpy())all_labels.extend(labels.cpu().numpy())accuracy accuracy_score(all_labels, all_preds)precision precision_score(all_labels, all_preds)recall recall_score(all_labels, all_preds)f1 f1_score(all_labels, all_preds)print(fAccuracy: {accuracy:.4f}, Precision: {precision:.4f}, Recall: {recall:.4f}, F1-score: {f1:.4f})return all_preds, all_labels# 可视化
def visualize_predictions(val_loader, model):model.eval()images, labels next(iter(val_loader))images, labels images.to(device), labels.to(device)outputs model(images)_, preds torch.max(outputs, 1)images images.cpu().numpy()preds preds.cpu().numpy()labels labels.cpu().numpy()# 可视化前6个样本plt.figure(figsize(12, 8))for i in range(6):plt.subplot(2, 3, i 1)image np.transpose(images[i], (1, 2, 0))image image * np.array([0.229, 0.224, 0.225]) np.array([0.485, 0.456, 0.406]) # 反归一化image np.clip(image, 0, 1)plt.imshow(image)plt.title(fPred: {preds[i]}, Actual: {labels[i]})plt.axis(off)plt.show()device torch.device(cuda if torch.cuda.is_available() else cpu)
train(model, train_loader, criterion, optimizer, scheduler, num_epochs10)
all_preds, all_labels evaluate(model, val_loader)
visualize_predictions(val_loader, model)
