Try my own trained model

[FereshtehFeiz]

Hello,
I want to use my own trained model for emotion detection (.h5 model), but I get the below error, could you let me know what is the problem?

2022-10-04 17:31:37.690958: 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.
Found 28709 images belonging to 7 classes.
Found 7178 images belonging to 7 classes.
2022-10-04 17:31:50.018247: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'nvcuda.dll'; dlerror: nvcuda.dll not found
2022-10-04 17:31:50.018462: W tensorflow/stream_executor/cuda/cuda_driver.cc:263] failed call to cuInit: UNKNOWN ERROR (303)
2022-10-04 17:31:50.024974: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: DESKTOP-41NG8QC
2022-10-04 17:31:50.025176: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: DESKTOP-41NG8QC
2022-10-04 17:31:50.025657: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.```

[terminatormlp]

The error message you are seeing indicates that TensorFlow is not able to find the nvcuda.dll library, which is required for running on a NVIDIA GPU. However, it looks like you are running TensorFlow on a CPU, as indicated by the message: "This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2".

While running TensorFlow on a CPU is perfectly fine, it is possible that your model was trained on a GPU and therefore expects to be run on a GPU. If that is the case, you may encounter performance issues when running the model on a CPU.

To fix the error message, you can try installing the NVIDIA CUDA toolkit and cuDNN library, which are required for running TensorFlow on a GPU. Alternatively, you can try running TensorFlow on a cloud-based service that provides access to GPUs, such as Google Colab or AWS.

If you don't have access to a GPU or don't want to use one, you can also try disabling GPU acceleration in TensorFlow by setting the CUDA_VISIBLE_DEVICES environment variable to -1. Here's an example of how to do this:
import os os.environ["CUDA_VISIBLE_DEVICES"] = "-1"