Forrest Iandola

Results 23 comments of Forrest Iandola

I’m sorry about that! Glad you were able to figure it out. Good detective work. :)

The final layer of SqueezeNet outputs a 1 dimensional vector with length equal to the number of categories. For example, if you are classifying an images and you have 1000...

@ujsyehao That's interesting. How much did the accuracy improve with your new setting of lr_mult?

Sorry for the slow reply. I would be interested to learn more about this. I don't have your contact info, so could you send me an email at [email protected]?

Interesting question! There is quite a lot of open-source code that applies deep learning to face detection (specifically: getting the face location). The following page has some examples of these...

Thank you! Do you also have an acc_norm number for your experiments?

I was having the same problem. Here's how I got it to work: `MUJOCO_GL=glx python examples/libero/main.py`

#16 is relevant

@alistair23 Thanks for the reply! I wish I had the source code for Torque. But, here is what I know: Torque is able to take a CSV file for car-specific...

I do have one guess of what might be wrong. It could be that when I do `OBDCommand(..., ecu=ECU.UNKNOWN, ...)`, I should actually use a different value for `ecu`. For...