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] rangeThe original model is distributed under the Apache License, Version 2.0. A copy of the license is provided in APACHE-2.0-TensorFlow.txt.