Questions


About the Questions category (2)
Did not support ConstantOfShape Operator in ONNX? (2)
Problems when import BERT model from ONNX relay (2)
[solved][ONNX] Error when deploying on Raspberry pi 4 (4)
Is NonMaxSupression support in the Tensorflow frontend? (1)
[Autotuning]"Cannot find config for target" occuring at compilation with autotuning log file (4)
Is module Relay only in version 0.6? (4)
Reproducibility of CI environment (2)
【error】Expected type relay.Expr but get relay.Module (2)
MVM not being decomposed properly when targeting VTA (7)
Error in tune_relay_arm.py (14)
Tvm support int8 quantize on android device? (3)
[ONNX] Failed to execute certain ONNX model on CUDA `CUDA_ERROR_INVALID_PTX` (7)
Documentation for non_max_suppression (5)
Can't Tune GPU on tx2 remotely (5)
[VTA] Supporting other models apart from resnet18 in VTA (4)
Cross Compiling for CUDA without CUDA device (1)
CUDA model compiled can not be invoked for inference on Jetson (2)
Can we resume an autotuning session? (5)
[ERROR]/tvm/build/CMakeFiles/CMakeTmp/CheckSymbolExists.c:2:10: fatal error: OpenCL_INCLUDE_DIR-NOTFOUND/CL/cl.h: No such file or directory (1)
[Ubuntu 16.04] TVM building error : FOUNDATION_LIB are used in this project, but they are set to NOTFOUND (6)
Throwing error reading JSON file (2)
How can I get the Intermediate results using debug_get_output(All the Intermediate results are wrong except the final result) (1)
[Tensorflow] support tf saved_model and more operators (3)
How to reassign functions in an existing module to other device(s)? (1)
TVM/VTA questions & use computer as SoC? (3)
[torch_tvm] How do we tune our models? (2)
How to add floormod in relay and topi (3)
AttributeError: Module has no function 'get_num_outputs' ,when deploy cross compile model (1)
Supporting Faster RCNN and Mask RCNN models (12)