cppflow
cppflow copied to clipboard
serizba
Run TensorFlow models in C++ without installation and without Bazel
Hi, I have a string tensor that looks like this: (tensor: shape=[1], data= ["0007 HMS\342\226\221\342\226\221\342\226\221"]) How can I decode and extract the string? or just extract the string and decode...
How to specify GPU index? For example, I have multiple GPU devices
It seems tensorflow.dll has to be in the system32 folder for my application to run correctly. Is there a way to configure cppflow to search from the .dll in the...
I don't know whether I'm wrong or not, it seems that the cppflow::fill and cppflow::tensor can only support one dimension tensor in the example. If I'm wrong, could you please...
Wondering if it's possible to get the computed values of an intermediate layer.
Hey follwing example: I have a tensor that looks like this: `(tensor: shape=[1 200 304], dtype=TF_FLOAT, data=...` Now how can iterate through the tensor? With` .get_data()` I only get the...
Hello, I run the `load_model` example, but encounter `CUDA_ERROR_OUT_OF_MEMORY` problem ```shell ./example 2021-09-15 16:52:00.362882: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use...
Hey! I am using: ``` cppflow::model model("C:\\Users\\Caike\\source\\repos\\StarCon\\x64\\Debug\\Models\\Objects\\"); auto input = cppflow::decode_jpeg(cppflow::read_file(std::string("C:\\Users\\Caike\\source\\repos\\StarCon\\x64\\Debug\\output2.jpg"))); input = cppflow::cast(input, TF_UINT8, TF_FLOAT); input = input / 255.f; input = cppflow::expand_dims(input, 0); auto output = model(input); std::cout...
