python - 加载模型时出现意外错误 : problem in predictor - ModuleNotFoundError: No module named 'torchvision'

Question

我一直在尝试通过我的 vm 实例上的控制台将我的模型部署到 AI 平台进行预测，但我收到错误“(gcloud.beta.ai-platform.versions.create)创建版本失败。模型错误检测到错误:“加载模型失败:加载模型时出现意外错误:预测器中的问题 - ModuleNotFoundError:没有名为‘torchvision’的模块(错误代码:0)”

我需要同时包含 torch和 torchvision .我按照这个问题中的步骤 Cannot deploy trained model to Google Cloud Ai-Platform with custom prediction routine: Model requires more memory than allowed ，但我无法获取用户 gogasca 指向的文件。我试过下载this来自 Pytorch 网站的 .whl 文件并将其上传到我的云存储，但得到相同的错误，即没有模块 torchvision ，即使这个版本应该包括torch 和torchvision。还尝试使用与 Cloud AI 兼容的软件包 here ，但不包括 torchvision .

我尝试为 torch 指向两个单独的 .whl 文件。和 torchvision在 --package-uris参数，那些指向我的云存储中的文件，但后来我得到了超出内存容量的错误。这很奇怪，因为它们的总大小约为 130Mb。我的命令示例导致缺少 torchvision看起来像这样:

gcloud beta ai-platform versions create version_1 \
  --model online_pred_1 \
  --runtime-version 1.15 \
  --python-version 3.7 \
  --origin gs://BUCKET/model-dir \
  --package-uris gs://BUCKET/staging-dir/my_package-0.1.tar.gz,gs://BUCKET/torchvision-dir/torch-1.4.0+cpu-cp37-cp37m-linux_x86_64.whl \
  --prediction-class predictor.MyPredictor

我尝试指向我从不同来源获得的 .whl 文件的不同组合，但出现无模块错误或内存不足。我不明白在这种情况下模块如何交互以及为什么编译器认为没有这样的模块。我该如何解决这个问题？或者，我如何自己编译一个包含 torch 的包和 torchvision .您能否给出详细的答案，因为我对包管理和 bash 脚本不是很熟悉。

这是我使用的代码， torch_model.py :

from torch import nn


class EthnicityClassifier44(nn.Module):
    def __init__(self, num_classes=2):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 32, kernel_size=7, stride=1, padding=3)
        self.maxpool1 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv22 = nn.Conv2d(32, 32, kernel_size=3, stride=1, padding=1)
        self.maxpool2 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv3 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)
        self.maxpool3 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv4 = nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1)
        self.maxpool4 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.relu = nn.ReLU(inplace=False)
        self.fc1 = nn.Linear(8*8*128, 128)
        self.fc2 = nn.Linear(128, 128)
        self.fc4 = nn.Linear(128, num_classes)


    def forward(self, x):
        x = self.relu(self.conv1(x))
        x = self.maxpool1(x)
        x = self.relu(self.conv22(x))
        x = self.maxpool2(x)
        x = self.maxpool3(self.relu(self.conv3(x)))
        x = self.maxpool4(self.relu(self.conv4(x)))
        x = self.relu(self.fc1(x.view(x.shape[0], -1)))
        x = self.relu(self.fc2(x))
        x = self.fc4(x)
        return x

这是 predictor_py :

from facenet_pytorch import MTCNN, InceptionResnetV1, extract_face
import torch
import torchvision
from torchvision import transforms
from torch.nn import functional as F
from PIL import Image
from sklearn.externals import joblib
import numpy as np
import os
import torch_model


class MyPredictor(object):

    import torch
    import torchvision

    def __init__(self, model, preprocessor, device):
        """Stores artifacts for prediction. Only initialized via `from_path`.
        """
        self._resnet = model
        self._mtcnn_mult = preprocessor
        self._device = device
        self.get_std_tensor = transforms.Compose([
            np.float32,
            np.uint8,
            transforms.ToTensor(),
        ])
        self.tensor2pil = transforms.ToPILImage(mode='RGB')
        self.trans_resnet = transforms.Compose([
            transforms.Resize((100, 100)),
            np.float32,
            transforms.ToTensor()
        ])

    def predict(self, instances, **kwargs):

        pil_transform = transforms.Resize((512, 512))

        imarr = np.asarray(instances)
        pil_im = Image.fromarray(imarr)
        image = pil_im.convert('RGB')
        pil_im_512 = pil_transform(image)

        boxes, _ = self._mtcnn_mult(pil_im_512)
        box = boxes[0]

        face_tensor = extract_face(pil_im_512, box, margin=40)
        std_tensor = self.get_std_tensor(face_tensor.permute(1, 2, 0))
        cropped_pil_im = self.tensor2pil(std_tensor)

        face_tensor = self.trans_resnet(cropped_pil_im)
        face_tensor4d = face_tensor.unsqueeze(0)
        face_tensor4d = face_tensor4d.to(self._device)

        prediction = self._resnet(face_tensor4d)
        preds = F.softmax(prediction, dim=1).detach().numpy().reshape(-1)
        print('probability of (class1, class2) = ({:.4f}, {:.4f})'.format(preds[0], preds[1]))

        return preds.tolist()

    @classmethod
    def from_path(cls, model_dir):
        import torch
        import torchvision
        import torch_model

        model_path = os.path.join(model_dir, 'class44_M40RefinedExtra_bin_no_norm_7860.joblib')
        classifier = joblib.load(model_path)

        mtcnn_path = os.path.join(model_dir, 'mtcnn_mult.joblib')
        mtcnn_mult = joblib.load(mtcnn_path)

        device_path = os.path.join(model_dir, 'device_cpu.joblib')
        device = joblib.load(device_path)

        return cls(classifier, mtcnn_mult, device)

和 setup.py :

from setuptools import setup

REQUIRED_PACKAGES = ['opencv-python-headless', 'facenet-pytorch']

setup(
 name="my_package",
 version="0.1",
 include_package_data=True,
 scripts=["predictor.py", "torch_model.py"],
 install_requires=REQUIRED_PACKAGES
)

Answer 1

解决方案是将以下软件包放入 setup.py自定义预测代码文件:

REQUIRED_PACKAGES = ['torchvision==0.5.0', 'torch @ https://download.pytorch.org/whl/cpu/torch-1.4.0%2Bcpu-cp37-cp37m-linux_x86_64.whl', 'opencv-python', 'facenet-pytorch']

然后我在自定义类实例化方面遇到了不同的问题，但是 this文章解释得很好。因此，我能够成功地将我的模型部署到 AI 平台进行预测。