model-name: GoogleNet
backbone-name: GoogleNet
module-type: cv-classification
fine-tunable: True
input-shape: [224, 224, 3]
model-version: 1.0
train-dataset: cifar10
accuracy: 0.934
author: MindSpore team
update-time: 2020-09-22
repo-link: https://gitee.com/mindspore/models/tree/master/official/cv/googlenet
user-id: MindSpore
used-for: inference
train-backend: ascend
infer-backend: ascend
mindspore-version: 0.7
asset:
license: Apache2.0
summary: GoogleNet used to classify the 10 classes of cifar10.
This MindSpore Hub model uses the implementation of GoogleNet from the MindSpore model zoo on Gitee at model_zoo/official/cv/googlenet.
This model has been trained on Cifar10 using the code published on Gitee.
All Parameters in the module are trainable.
import mindspore_hub as mshub
import mindspore
from mindspore import context, Tensor, nn
from mindspore.train.model import Model
from mindspore.common import dtype as mstype
from mindspore.dataset.transforms import py_transforms
context.set_context(mode=context.GRAPH_MODE,
device_target="Ascend",
device_id=0)
model = "mindspore/ascend/0.7/googlenet_v1_cifar10"
# initialize the number of classes based on the pre-trained model
network = mshub.load(model, num_classes=10)
network.set_train(False)
# Use as the same as MindSpore Model to inference.
# ...
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。