Yochanan Scharf
Yochanan Scharf
@fiverriddle, if you would like to initialize a tensor with all elements having the same value, use the following: `float val = 1.0;` `cppflow::tensor tnsr = cppflow::fill({ 1000, 5 },...
If you come up against errors in the `model.h` file, do the following changes. for (int i=0; igraph.get(), op_name.c_str()); inp_ops[i].index = op_idx; if (!inp_ops[i].oper) throw std::runtime_error("No operation named \"" +...
After writing the above: Saw the below: [issue 108](https://github.com/serizba/cppflow/pull/108 )
Try following [this answer on StackOverflow](https://stackoverflow.com/a/71998020/3957794)
Would like to try and contribute on this useful feature @serizba .
@oishi89 Did you try the following: creat a directory called `DATA` and placing the `.npz` and .txt files inside. Then in the `retrain_yolo.py` script change lines 29 and 35 to...
Have you tried using the `cppflow::slice` operator?
Save the model in the `saved_model` format. This can be done by doing `model.save("model_name")`. Tensorflow will save the model in the `saved_model` format if you don't put `.h5` in "model_name".