ModuleNotFoundError: No module named 'tensorflow.python.saved_model.model_utils'

本文解决了一个在升级到TensorFlow2.0后遇到的ModuleNotFoundError问题,详细介绍了如何通过卸载并重新安装tensorflow_estimator来修复此错误。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

ModuleNotFoundError: No module named 'tensorflow.python.saved_model.model_utils'

出现原因:升级了tensorflow2.0,退回1.13出现该问题。

解决方法:删除tensorflow_estimator重新安装

pip uninstall tensorflow_estimator
pip install tensorflow_estimator
import os import torch import torch.nn as nn import torch.optim as optim from torch.utils.data import DataLoader from config import * from utils import YOLODataset, get_data_loader, YOLOLoss # 假设已有相关函数 from models.yolov5 import YOLOv5 # 加载数据 train_loader = get_data_loader(TRAIN_IMAGES, TRAIN_LABELS, img_size=IMG_SIZE, batch_size=BATCH_SIZE, shuffle=True) val_loader = get_data_loader(VAL_IMAGES, VAL_LABELS, img_size=IMG_SIZE, batch_size=BATCH_SIZE, shuffle=False) # 初始化模型 model = YOLOv5(num_classes=80).to(DEVICE) criterion = YOLOLoss(num_classes=80, img_size=IMG_SIZE) optimizer = optim.AdamW(model.parameters(), lr=LEARNING_RATE, weight_decay=WEIGHT_DECAY) # 模型保存路径 MODEL_SAVE_PATH = "D:\\commodity_sorting_system\\final_model.pth" # 训练 for epoch in range(EPOCHS): model.train() total_loss = 0 for batch_idx, (images, labels) in enumerate(train_loader): images = images.to(DEVICE) labels = labels.to(DEVICE) optimizer.zero_grad() outputs = model(images) loss = criterion(outputs, labels) loss.backward() optimizer.step() total_loss += loss.item() print(f"Epoch [{epoch+1}/{EPOCHS}], Batch [{batch_idx+1}/{len(train_loader)}], Loss: {loss.item():.4f}") # 训练完成后保存模型 torch.save(model.state_dict(), MODEL_SAVE_PATH) print(f"Training complete. Final model saved to {MODEL_SAVE_PATH}") 运行后显示C:\Users\23228\PyCharmMiscProject\.venv\Scripts\python.exe D:\commodity_sorting_system\code\main.py Traceback (most recent call last): File "D:\commodity_sorting_system\code\main.py", line 8, in <module> from models.yolov5 import YOLOv5 ModuleNotFoundError: No module named 'models.yolov5' 进程已结束,退出代码为 1 怎么解决
06-05
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值