TensorFlow issue

#39
by kgrabko - opened

When I loaded it in DJL with TensorFlow engine then I got error

Model name: tf_model.h5
Model exists: true
Loading fine-tuned T5 model with TensorFlow...
2025-10-22 01:07:03.568511: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0.
2025-10-22 01:07:03.630302: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: SSE SSE2 SSE3 SSE4.1 SSE4.2 AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
Failed to run the chatbot: No TensorFlow model found in: C:\Users\kgrab\flan-t5-base_1_onnx\tf_model.h5
java.io.FileNotFoundException: No TensorFlow model found in: C:\Users\kgrab\flan-t5-base_1_onnx\tf_model.h5
at ai.djl.tensorflow.engine.TfModel.load(TfModel.java:71)
at ai.djl.repository.zoo.BaseModelLoader.loadModel(BaseModelLoader.java:176)
at ai.djl.repository.zoo.Criteria.loadModel(Criteria.java:151)
at jirackml.ChatBotTf.main(ChatBotTf.java:62)

It is Keros model . It is not TensorFlow

Please fix it to use TensorFlow from DJL

Sign up or log in to comment