Nicholas Dronen ndronen

ndronen / gist:12bc4c4eeb357eea247e0a571f6827b4

Last active September 10, 2024 11:19

Debugging ResNet - l

	Here's the output of activate_excess_capacity with my debug statements in it.

	The whole log file that follows contains the entire output of the run.

	This is after pruning the first task and before training the second task.

	Notice that excess capacity goes to 0% even for some layers with only a small %age of pruning.

	Notice that after activating excess capacity, the backward grad hook "ERROR" messages start to appear
	in the whole log file.

ndronen / PyTorch issue 35643

Created April 25, 2020 09:06

Straw man proposal for PyTorch issue

	"""
	This is a straw man proposal to begin discussion of how to change the
	PyTorch hooks API to support capture/inspection/modification of
	keyword arguments.

	https://github.com/pytorch/pytorch/issues/35643
	"""

	import unittest

ndronen / resnet56_cifar_filter_rank.log

Created August 20, 2018 16:49

	/home/ubuntu/conda/miniconda3/envs/distiller-python-3.5/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
	return f(args, *kwds)
	/home/ubuntu/conda/miniconda3/envs/distiller-python-3.5/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
	return f(args, *kwds)
	/home/ubuntu/conda/miniconda3/envs/distiller-python-3.5/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
	return f(args, *kwds)
	/home/ubuntu/conda/miniconda3/envs/distiller-python-3.5/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
	return f(args, *kwds)
	Log file for this run: /home/ubuntu/proj/distiller-python-3.5/examples/pruning_filters_for_efficient_convnets/logs/2018.08.20-10

ndronen / model.py

Last active April 28, 2018 19:50

Semantic segmentation with ENet in PyTorch

	#!/usr/bin/env python
	"""
	A quick, partial implementation of ENet (https://arxiv.org/abs/1606.02147) using PyTorch.
	The original Torch ENet implementation can process a 480x360 image in ~12 ms (on a P2 AWS
	instance). TensorFlow takes ~35 ms. The PyTorch implementation takes ~25 ms, an improvement
	over TensorFlow, but worse than the original Torch.
	"""

	from __future__ import absolute_import

ndronen / gist:f6ce80b7343a73c18072

Created July 9, 2015 21:20

Minimal working example of something that doesn't work with nn.Concat.

	#!/usr/bin/env th

	require 'nn';

	local cmd = torch.CmdLine()
	cmd:text()
	cmd:text("What's wrong with this use of nn.Concat?")
	cmd:text('Options:')
	cmd:option('-noConcat', false, 'do not include concat layer')

ndronen / gist:a8e13e5799b8118f7cc0

Last active August 29, 2015 14:22

	#!/usr/bin/env th

	local cmd = torch.CmdLine()
	cmd:text('Demonstration of incompatibility between nn and fbcunn temporal convolutions.')
	cmd:text()
	cmd:text('Running with -fbconv causes a tensor dimension mismatch error in TemporalConvolutionFB_updateOutput.')
	cmd:text()
	cmd:text('I think the bug is somewhere in ConvolutionBias.cu.')
	cmd:text()
	cmd:text('Options:')