Nothing can be predicted after changing the code about tensorrtx HOT 8 CLOSED

You can try to debug it by getting the output of middle layers.

from tensorrtx.

You can try to debug it by getting the output of middle layers.

Sorry, I'm a newbie, I don't quite understand what you mean, could you be more detailed, thank you.

from tensorrtx.

For example, you have added 10 layers, from layer1 to layer10, now you only check the output tensor of layer10, and the result is wrong.

For debug purpose, you can first get the output of layer1, to see if the result is correct. If yes, then check layer2.
Check the layer output one by one, until you found which layer has issue.

from tensorrtx.

For example, you have added 10 layers, from layer1 to layer10, now you only check the output tensor of layer10, and the result is wrong.

For debug purpose, you can first get the output of layer1, to see if the result is correct. If yes, then check layer2. Check the layer output one by one, until you found which layer has issue.

Hello, the modified model is the same as the original model. The Dimensions, DynamicRangeMin, DynamicRangeMax, and AllowedFormats of each layer's tensors are the same. What output should I check? If all the outputs are the same, what should I do?

from tensorrtx.

Have you check the values of the output tensor for each layer?

from tensorrtx.

Dimensions、DynamicRangeMin、DynamicRangeMax和AllowedFormats

Yes, I have checked every layer, including tensor Dimensions, DynamicRangeMin, DynamicRangeMax and AllowedFormats. They are all the same. Is it because I checked the tensor output type incorrectly? Let me reiterate my question: engine inference built after modifying the model. Is empty.

from tensorrtx.

Have you check the values of the output tensor for each layer?

I don’t think we should check the Dimensions output by each layer’s tensor. If it is different from the source model, the engine model will not be generated, but I really don’t know what to check. Do you have any ideas? Specifically, we should check which outputs are wrong and lead to inferential reasoning.

from tensorrtx.

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

from tensorrtx.