I was running the code from the tutorial, but I get the following error:
------------------------------ [ Task Scheduler ]
----------------------------------------------------------------------
| ID | Task Description | Latency (ms) | Speed (GFLOPS) | Trials |
-----------------------------------------------------------------------------------------------------------------
| 0 | vm_mod_fused_nn_conv2d_add_nn_relu_5 | 0.211 | 487.76 | 6 |
| 1 | vm_mod_fused_nn_conv2d_add | 0.524 | 197.74 | 6 |
| 2 | vm_mod_fused_nn_conv2d | 0.215 | 477.76 | 6 |
| 3 | vm_mod_fused_nn_conv2d_add_nn_relu_1 | 0.173 | 150.45 | 6 |
| 4 | vm_mod_fused_nn_dense_add | 0.371 | 11.03 | 6 |
| 5 | vm_mod_fused_nn_conv2d_add_add_nn_relu | 0.305 | 344.76 | 6 |
| 6 | vm_mod_fused_nn_global_avg_pool2d | 0.006 | -0.00 | 6 |
| 7 | vm_mod_fused_nn_conv2d_add_nn_relu_8 | 0.158 | 325.82 | 6 |
| 8 | vm_mod_fused_nn_conv2d_3 | 0.587 | 349.87 | 6 |
| 9 | vm_mod_fused_nn_conv2d_add_3 | 0.297 | 346.35 | 6 |
| 10 | vm_mod_fused_nn_conv2d_add_nn_relu_4 | 0.150 | 344.53 | 6 |
| 11 | vm_mod_fused_nn_conv2d_add_add_nn_relu_1 | 0.185 | 562.96 | 6 |
| 12 | vm_mod_fused_nn_conv2d_1 | 0.751 | 273.75 | 6 |
| 13 | vm_mod_fused_nn_softmax | 0.008 | 0.50 | 6 |
| 14 | vm_mod_fused_nn_conv2d_add_2 | 0.210 | 489.87 | 6 |
| 15 | vm_mod_fused_nn_conv2d_add_nn_relu | - | - | 0 |
| 16 | vm_mod_fused_nn_max_pool2d_add_nn_relu | - | - | 0 |
| 17 | vm_mod_fused_nn_conv2d_add_nn_relu_10 | - | - | 0 |
| 18 | vm_mod_fused_nn_conv2d_add_nn_relu_7 | - | - | 0 |
| 19 | vm_mod_fused_nn_contrib_conv2d_winograd_without_weight_transform_add_nn_relu_1 | - | - | 0 |
| 20 | vm_mod_fused_nn_conv2d_add_nn_relu_3 | - | - | 0 |
| 21 | vm_mod_fused_nn_conv2d_add_multiply_add_nn_relu | - | - | 0 |
| 22 | vm_mod_fused_nn_conv2d_add_1 | - | - | 0 |
| 23 | vm_mod_fused_nn_conv2d_2 | - | - | 0 |
| 24 | vm_mod_fused_nn_conv2d_add_nn_relu_6 | - | - | 0 |
| 25 | vm_mod_fused_nn_conv2d_add_add_nn_relu_2 | - | - | 0 |
| 26 | vm_mod_fused_nn_conv2d_add_nn_relu_2 | - | - | 0 |
| 27 | vm_mod_fused_nn_contrib_conv2d_winograd_without_weight_transform_add_nn_relu | - | - | 0 |
| 28 | vm_mod_fused_nn_conv2d_add_nn_relu_9 | - | - | 0 |
-----------------------------------------------------------------------------------------------------------------
Estimated total latency: - ms Trials: 90 Used time : 179 s Next ID: 15
----------------------------------------------------------------------
------------------------------ [ Search ]
----------------------------------------------------------------------
Generate Sketches #s: 3
/usr/include/c++/11/bits/stl_vector.h:1063: std::vector<_Tp, _Alloc>::const_reference std::vector<_Tp, _Alloc>::operator[](std::vector<_Tp, _Alloc>::size_type) const [with _Tp = float; _Alloc = std::allocator<float>; std::vector<_Tp, _Alloc>::const_reference = const float&; std::vector<_Tp, _Alloc>::size_type = long unsigned int]: Assertion '__n < this->size()' failed.
[1] 1230981 IOT instruction (core dumped) python tune_network_x86.py
I am on the latest master branch of TVM. Don’t know what’s going on and I’d appreciate some help from the community.