resnet-50-tf
is a TensorFlow* implementation of ResNet-50 - an image classification model pretrained on the ImageNet dataset. Originally redistributed in Saved model format, converted to frozen graph using tf.graph_util
module. For details see paper, repository.
Metric | Value |
---|---|
Type | Classification |
GFLOPs | 8.2164 |
MParams | 25.53 |
Source framework | TensorFlow* |
Metric | Original model | Converted model |
---|---|---|
Top 1 | 76.45% | 76.17% |
Top 5 | 93.05% | 92.98% |
Image, name: map/TensorArrayStack/TensorArrayGatherV3
, shape: 1,224,224,3
, format is B,H,W,C
where:
B
- batch sizeH
- heightW
- widthC
- channelChannel order is RGB
. Mean values: [123.68,116.78,103.94].
Image, name: map/TensorArrayStack/TensorArrayGatherV3
, shape: 1,224,224,3
, format is B,H,W,C
where:
B
- batch sizeH
- heightW
- widthC
- channelChannel order is BGR
.
Object classifier according to ImageNet classes, name: softmax_tensor
, shape: 1,1001
, output data format is B,C
where:
B
- batch sizeC
- predicted probabilities for each class in [0, 1] rangeObject classifier according to ImageNet classes, name: softmax_tensor
, shape: 1,1001
, output data format is B,C
where:
B
- batch sizeC
- predicted probabilities for each class in [0, 1] rangeYou can download models and if necessary convert them into Inference Engine format using the Model Downloader and other automation tools as shown in the examples below.
An example of using the Model Downloader:
An example of using the Model Converter:
The original model is distributed under the Apache License, Version 2.0. A copy of the license is provided in APACHE-2.0-TensorFlow.txt.