Bing Zha
Hi Sir or Madam, I install the windows 10 in my macbook air. So it seems that I can't enter bios to set Hyper-V. Could you please tell me how...
Hi, I saw the loss weight setup in your code. But I am a little confused that how do you determine that weight. The total weight of 11 class is...
When I run `demo_skeleton.py`, I got visualization like this: KeyError: 'PoseLocalVisualizer is not in the visualizer registry. Please check whether the value of `PoseLocalVisualizer` is correct or it was registered...
Hi, Thanks for your great work. Do you have any plan to develop onnx export tool so that the onnx model can be used in the practical project? Thank you!
Hi @royshil I think there is a bug in your code BundleAdjuster.cpp. I give you a snapshot in following. I think Pmats[i] isn't the representation of camera matrix. For example...
I hava compile it successfully on vs2010. But when I run it I have a error. The error information is followed. Assertion failed: (reinterpret_cast(array) & 0xf) == 0 && "this...
Hi, Thank you for sharing your code and dataset. I was wondering if you possibly can explain more how you generate those training dataset?
allocated 474 MiB for model parameters train_gpt2fp32cu: train_gpt2_fp32.cu:1815: void tokenizer_init(Tokenizer*, const char*): Assertion `header[1] == 1' failed. [1] 2229854 abort (core dumped) ./train_gpt2fp32cu
tinygrad.device.CompileError: compile failed: (17): error: more than one user-defined conversion from "nv_bfloat16" to "half" applies: function "__half::__half(float)" (declared at line 214 of /usr/local/cuda/include/cuda_fp16.hpp) function "__half::__half(short)" (declared at line 227 of...
Hi @jytime Great work. I am wondering if you ever tried long sequence video input as in visual odometry. Also if the number of input frames is limited by resources,...