You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "YaoJiawei329 (via GitHub)" <gi...@apache.org> on 2023/04/20 12:47:05 UTC
[GitHub] [tvm] YaoJiawei329 opened a new issue, #14681: [Bug] tvmc tune did not work.
YaoJiawei329 opened a new issue, #14681:
URL: https://github.com/apache/tvm/issues/14681
I use this command to tune yolov7.onnx
tvmc tune --target "llvm" --output yolov7.json yolov7.onnx
but it just show for so long:
[Task 1/47] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/21) | 0.00 s
and cpu usage is 0%, memory usage is 30MB.
I want to know how to fix it. Or what's wrong with my conda env, or some other suggestions. Thanks!
### Environment
Operating System: Windows 11 laptop
TVM version: 0.13
### Triage
Please refer to the list of label tags [here](https://github.com/apache/tvm/wiki/Issue-Triage-Labels) to find the relevant tags and add them below in a bullet format (example below).
* needs-triage
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] YaoJiawei329 commented on issue #14681: [Bug] tvmc tune did not work.
Posted by "YaoJiawei329 (via GitHub)" <gi...@apache.org>.
YaoJiawei329 commented on issue #14681:
URL: https://github.com/apache/tvm/issues/14681#issuecomment-1516371881
And I try to use the following code to tune the same model, but it also did not work, just hangon.
`
from tvm.driver import tvmc
from tvm import autotvm, relay
def tvmc_tune(model_path, shape_dict, target, log_file):
model = tvmc.load(model_path, shape_dict=shape_dict) # 第 1 步: 加载 + shape_dict
tvmc.tune(model, target=target, tuning_records=log_file) # 第 1.5 步：可选 Tune
package = tvmc.compile(model, target=target, tuning_records=log_file) # 第 2 步：编译
mod, params = relay.frontend.from_onnx(model_path, shape_dict)
with autotvm.apply_history_best(log_file):
with tvm.transform.PassContext(opt_level=4, config={}):
lib = relay.build(mod, target=target, params=params)
lib.export_library(model_path.replace("onnx", "so"))
if __name__ == "__main__":
model_path = "./yolov7.onnx"
shape_dict = {'images':[1,3,640,640]}
target = "llvm"
log_file = 'tune.json'
tvmc_tune(model_path, shape_dict, target, log_file)
`
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] YaoJiawei329 commented on issue #14681: [Bug] tvmc tune did not work.
Posted by "YaoJiawei329 (via GitHub)" <gi...@apache.org>.
YaoJiawei329 commented on issue #14681:
URL: https://github.com/apache/tvm/issues/14681#issuecomment-1518666804
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] YaoJiawei329 commented on issue #14681: [Bug] tvmc tune did not work.
Posted by "YaoJiawei329 (via GitHub)" <gi...@apache.org>.
YaoJiawei329 commented on issue #14681:
URL: https://github.com/apache/tvm/issues/14681#issuecomment-1518976286
Today I try to tune model by auto_scheduler, also did not work.
| ID | Task Description | Latency (ms) | Speed (GFLOPS) | Trials |
-----------------------------------------------------------------------------------------------------------------
| 0 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_17 | - | - | 0 |
| 1 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_1 | - | - | 0 |
| 2 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_25 | - | - | 0 |
| 3 | vm_mod_fused_nn_max_pool2d_6 | - | - | 0 |
| 4 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_33 | - | - | 0 |
| 5 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_5 | - | - | 0 |
| 6 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_41 | - | - | 0 |
| 7 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_3 | - | - | 0 |
| 8 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_13 | - | - | 0 |
| 9 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_21 | - | - | 0 |
| 10 | vm_mod_fused_nn_max_pool2d_2 | - | - | 0 |
| 11 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_1 | - | - | 0 |
| 12 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_28 | - | - | 0 |
| 13 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_2 | - | - | 0 |
| 14 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_36 | - | - | 0 |
| 15 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply | - | - | 0 |
| 16 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_16 | - | - | 0 |
| 17 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_24 | - | - | 0 |
| 18 | vm_mod_fused_nn_max_pool2d_3,vm_mod_fused_nn_max_pool2d_4,vm_mod_fused_nn_max_pool2d_5 | - | - | 0 |
| 19 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_32 | - | - | 0 |
| 20 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_40 | - | - | 0 |
| 21 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add | - | - | 0 |
| 22 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_12 | - | - | 0 |
| 23 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_39 | - | - | 0 |
| 24 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_20 | - | - | 0 |
| 25 | vm_mod_fused_nn_max_pool2d_1 | - | - | 0 |
| 26 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_19 | - | - | 0 |
| 27 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_8 | - | - | 0 |
| 28 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_27 | - | - | 0 |
| 29 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_35 | - | - | 0 |
| 30 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_6 | - | - | 0 |
| 31 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_43 | - | - | 0 |
| 32 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_15 | - | - | 0 |
| 33 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_23 | - | - | 0 |
| 34 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_4 | - | - | 0 |
| 35 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_31 | - | - | 0 |
| 36 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_2 | - | - | 0 |
| 37 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_11 | - | - | 0 |
| 38 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_38 | - | - | 0 |
| 39 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_18 | - | - | 0 |
| 40 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_26 | - | - | 0 |
| 41 | vm_mod_fused_nn_max_pool2d_7 | - | - | 0 |
| 42 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_34 | - | - | 0 |
| 43 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_42 | - | - | 0 |
| 44 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_14 | - | - | 0 |
| 45 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_22 | - | - | 0 |
| 46 | vm_mod_fused_nn_max_pool2d | - | - | 0 |
| 47 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_30 | - | - | 0 |
| 48 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_10 | - | - | 0 |
| 49 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_29 | - | - | 0 |
| 50 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_37 | - | - | 0 |
| 51 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_9 | - | - | 0 |
| 52 | vm_mod_fused_nn_contrib_conv2d_NCHWc_add_sigmoid_multiply_7 | - | - | 0 |
-----------------------------------------------------------------------------------------------------------------
Estimated total latency: - ms Trials: 0 Used time : 0 s Next ID: 0
----------------------------------------------------------------------
------------------------------ [ Search ]
----------------------------------------------------------------------
Generate Sketches #s: 3
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [I] [Bug] tvmc tune did not work. [tvm]
Posted by "ajiansoft (via GitHub)" <gi...@apache.org>.
ajiansoft commented on issue #14681:
URL: https://github.com/apache/tvm/issues/14681#issuecomment-1955758056
hey friend,do you fix it?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org