hub
hub copied to clipboard
A library for transfer learning by reusing parts of TensorFlow models.
### What happened? Using below URL for pretrained MobileNet model, it throws me an error : OSError: SavedModel file does not exist at: /var/folders/9y/yyk41v6n0fn2plkwb8wc5tdw0000gn/T/tfhub_modules/145bb06ec3b59b08fb564ab752bd5aa222bfb50a/{saved_model.pbtxt|saved_model.pb} URL = "https://tfhub.dev/google/tf2-preview/mobilenet_v2/feature_vector/4 I've now downgraded...
I had a few changes in the markdown edited; just a few typo errors.
### What happened? Hi there, I'm trying to retrain the pre-trained BERT model from TF Hub. I'm using the following preprocessor: https://tfhub.dev/tensorflow/bert_multi_cased_preprocess/3 along with the multilingual encoder https://tfhub.dev/tensorflow/bert_multi_cased_L-12_H-768_A-12/4' I'm running...
TFHub "Updated" field for any model is always set to a current date This makes it impossible to see which models are recently added or updated I addition, I suggest...
Hello! I've found a performance issue in /examples/image_retraining/retrain.py: `eval_sess = tf.Session(graph=eval_graph)`[(here)](https://github.com/tensorflow/hub/blob/e2dbee5c0a503185f41c84eb5e3b0b195be9cbc4/examples/image_retraining/retrain.py#L883) is defined in the function `build_eval_session`[(here)](https://github.com/tensorflow/hub/blob/e2dbee5c0a503185f41c84eb5e3b0b195be9cbc4/examples/image_retraining/retrain.py#L868) which is called in the function `save_graph_to_file`[(here)](https://github.com/tensorflow/hub/blob/e2dbee5c0a503185f41c84eb5e3b0b195be9cbc4/examples/image_retraining/retrain.py#L904) which is repeatedly called in the...
Hello! I'm running into some issues with determinism at inference time for the MobileBERT tfhub-hosted models. Even after setting `trainable`/`training` kwargs to `False`, I'm finding that the model output can...
I am attempting to migrate an existing Efficientnet model from keras.applications to the respective hub. However, I see vastly different behaviors in training and final performance, and thus I am...
Hi, I am using the MoveNet Thunder model for pose-estimation and used the model on google colab for calculating the keypoints of the estimated markers. I, then used the markers...
When loading a `SavedModel` into a `hub.KerasLayer` with `trainable=False` and requesting a specific signature via the `signature=...` argument, the layer can't be called for inferencing. Instead, the following error appears:...
There seems to be a caching issue for the BERT models (including the preprocessors and the encoders). I am referring to the BERT models mentioned in this blog post: https://blog.tensorflow.org/2020/12/making-bert-easier-with-preprocessing-models-from-tensorflow-hub.html....