cppflow
cppflow copied to clipboard
serizba
Run TensorFlow models in C++ without installation and without Bazel
Hello, I'm loading a model of a frozen graph and run it. I then check for the device of the resulting output-tensors and they all return to me `/job:localhost/replica:0/task:0/device:CPU:0` implying...
I think it should work since they are releasing tensorflow libraries aswell but i wanted to make sure.  
Hi , I try to compile my C++ code that load tensorflow modle with functions from cppflow library. This code perefectly loaded model and make prediction. But later , when...
Hi, I am creating a cpp tensor in two different ways. The first method is by using cppflow::decode_jpeg() to create a tensor on GPU memory, the second method is by...
How can one compute gradients of a model's output with respect to its inputs?
Hi Thanks for the library, I build this successfully in ubuntu, but now I want to use it in windows. Is it support windows? if yes, how to build?
``` 2022-11-09 11:29:11.466957: I tensorflow/cc/saved_model/reader.cc:45] Reading SavedModel from: ./resources/models/dummy_model 2022-11-09 11:29:11.470546: I tensorflow/cc/saved_model/reader.cc:89] Reading meta graph with tags { serve } 2022-11-09 11:29:11.470586: I tensorflow/cc/saved_model/reader.cc:130] Reading SavedModel debug info (if...
Hi, I'm trying to use your library to load model in h5 format, but it's maybe ill formed or just not possible. I've created model using such python code: ```python...
Hi, I have networks consisting of LSTM, Convolutional and Dense layers, and some BatchNormalization and Concatenate layers. There is also a lambda layer which performs a very simple function -...
Default MaxPoolingOp only supports NHWC on device type CPU but I don't have MaxPooling in this model
Hello, I want to make prediction from this: ```shape = std::vector{1, 32, 3, 1}; auto input = cppflow::tensor(points_teeth, shape); for (auto s: model_points.get_operations()){ std::cout
