-
-
After model.fit for 1 epoch via Colab TPU I saved my model by model.save.
But when I open the h5 file by import hdf5 I just saw 'model_weights' without 'optimizer_weights' at the same time.
Maybe s…
-
### Describe the problem
Built in support for Google's Universal Sentence Encoder (USE) which can useful for greater-than-word length text, such as sentences, phrases or short paragraphs.
[USE Pap…
-
### MediaPipe Solution (you are using)
Model Maker
### Programming language
_No response_
### Are you willing to contribute it
No
### Describe the feature and the current behaviour/state
[Mobil…
-
When I tested the model, raised an error:
File "/home/sy/nerf/code/jaxnerf/eval.py", line 73, in main
lpips_model = tf_hub.load(LPIPS_TFHUB_PATH)
I can not solve this problem. I hope you ca…
-
I wonder if somebody use a word2vec model with ofxTensorflow2?
I found a model and tried to use it, but without success: https://tfhub.dev/google/Wiki-words-250-with-normalization/2
For now I use of…
-
Sorry for my English. Refer in https://tfhub.dev/tensorflow/lite-model/deeplabv3/1/metadata/2,the origin image process should be sub 127.5 then div 127.5.The code in line 2 of setcion 6 should like th…
-
@kevinkilgour
I tried to convert the model provided at https://tfhub.dev/google/speech_embedding/1 to TFLite but unfortunately failed.
### Setup:
- tensorflow 2.2.0rc2
- tensorflow-hub 0.8.0
…
-
I'm getting 0.1% as Top 1 accuracy for the validation of Resnet50 and Resnet101 models using the TF-TRT.
Validation script: https://github.com/tensorflow/tensorrt/blob/master/tftrt/examples/image-cla…
-
As the title says the multilingual model is available in https://tfhub.dev/google/bert_multi_cased_L-12_H-768_A-12/1 but there's no TF2 version.
Everything else seems to have been converted so this …