返回模型

说明文档

import trace_layer2 as models
import torch

x=torch.randn(1, 3, 224, 224)

state_dict = torch.load('swav_imagenet_layer2.pt', map_location='cpu')

model = models.resnet50w2()
model.load_state_dict(state_dict)
model.eval()
feature = model(x)

traced_model = torch.jit.load('traced_swav_imagenet_layer2.pt', map_location='cpu')
traced_model.eval()
feature = traced_model(x)

lixiangchun/imagenet-swav-resnet50w2

作者 lixiangchun

tf-keras

↓ 0 ♥ 0

创建时间: 2022-10-20 04:06:01+00:00

更新时间: 2022-10-28 04:13:37+00:00

在 Hugging Face 上查看

文件 (19)

.gitattributes

README.md

convert_onnx_2_tf.sh

featureExtractor.py

md5.txt

swav_imagenet_layer2.pt

swav_imagenet_layer2_sim.onnx ONNX

tf_saved_model/saved_model.pb

tf_saved_model/variables/variables.data-00000-of-00001

tf_saved_model/variables/variables.index

tfjs_saved_model/group1-shard1of6.bin

tfjs_saved_model/group1-shard2of6.bin

tfjs_saved_model/group1-shard3of6.bin

tfjs_saved_model/group1-shard4of6.bin

tfjs_saved_model/group1-shard5of6.bin

tfjs_saved_model/group1-shard6of6.bin

tfjs_saved_model/model.json

trace_layer2.py

traced_swav_imagenet_layer2.pt