I’m trying to convert my TensorFlow SavedModel into a TensorFlow.js format using tensorflowjs_converter. tensorflowjs_converter --input_format=tf_saved_model --output_format=tfjs_graph_model --saved_model_tags=serve --strip_debug_ops SavedModel TFJS 2025-09-18 16:19:28.918331: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found 2025-09-18 16:19:28.918535: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. Traceback (most recent call last): ... I ran the following command in my conda environment: tensorflowjs_converter --input_format=tf_saved_model --output_format=tfjs_graph_model --saved_model_tags=serve --strip_debug_ops SavedModel TFJS What I expected: I expected it to generate two files in the TFJS folder: model.json group1-shard1of1.bin so that I could load the model in TensorFlow.js for inference in the browser. What actually happened: Instead of successful conversion, I got the following warning and traceback: Could not load dynamic library 'cudart64_110.dll' Traceback (most recent call last): ... Continue reading...
