Repository navigation
Pre-trained models #6
Description
Activity
+1
You can find one pre-trained network as part of the Android example, at https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/android/assets/tensorflow_inception_graph.pb
This implements a version of the Inception architecture for Imagenet classification.Reacted by Moustafa Alzantot and Sahal Sajjad👍
Reopening to de-dupe future requests for this
I converted the VGG-16 caffemodel to TensorFlow https://github.com/ry/tensorflow-vgg16 which might be helpful for a generalized script
Reacted by Jordan Burgess, Jesse Vander Does, willwywang, John Allen, alfiya400, kumarshirish, Silvan Heller, Jiang. Qing-Yuan, junpeiz, Louis M. and 3 moreThe link to pretrained model of inception for imagenet seems broken
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/android/assets/tensorflow_inception_graph.pbReacted by Dmytro Lituiev, Marcella Astrid and pinguo-cuizhengwenThis is working as expected. We've moved the model out of the source repo, but it's available for separate download. See the android example README for the latest instructions:
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/android/README.md
Currently the link is https://storage.googleapis.com/download.tensorflow.org/models/inception5h.zip but the README will hold the most up-to-date location going forward.The inception model checkpoint is downloadable (and we have examples using it for classification and deepdream), and more models are being added to https://github.com/tensorflow/models. Closing this.
I found that the file size of https://storage.googleapis.com/download.tensorflow.org/models/inception5h.zip is very small, ~50MB. The Inception v3 model in tensorflow/tensorflow/examples/label_image/data/inception_dec_2015.zip is rather larger ~100MB but still portable on mobile devices. However when I tried to convert VGG-16 models into .pb file, it cost ~500MB. Is that the architecture of Inception is more superior than VGG in term of portability?
51 remaining items
- added 7 commits that reference this issue
on Apr 9, 2025 - added 5 commits that reference this issue
on Jul 28, 2025 - added a commit that references this issue
on Nov 26, 2025
Is there any plan to include caffe-like pre-trained models to use for predictions?