Hao qfgaohao

qfgaohao / ssd_priors.py

Last active November 27, 2019 08:06

Generate SSD Prior Boxes.

	import collections
	import numpy as np
	import itertools

	SSDBoxSizes = collections.namedtuple('SSDBoxSizes', ['min', 'max'])

	Spec = collections.namedtuple('Spec', ['feature_map_size', 'shrinkage', 'box_sizes', 'aspect_ratios'])

	# the SSD orignal specs
	specs = [

qfgaohao / draw_tensorflow_graph_in_notebook.py

Created January 31, 2018 21:41

	def strip_consts(graph_def, max_const_size=32):
	"""Strip large constant values from graph_def."""
	strip_def = tf.GraphDef()
	for n0 in graph_def.node:
	n = strip_def.node.add()
	n.MergeFrom(n0)
	if n.op == 'Const':
	tensor = n.attr['value'].tensor
	size = len(tensor.tensor_content)
	if size > max_const_size:

qfgaohao / pb_utils.cc

Last active April 6, 2023 11:05

Demonstrate how to save and read a protobuf message AddressBook to/from pb or pbtxt files.

	#include <iostream>
	#include <fstream>
	#include <string>
	#include <sstream>


	#include <google/protobuf/text_format.h>

	// for read_from_pbtxt_nocopy
	#include <fcntl.h>

qfgaohao / caffe2_workflow.py

Last active December 18, 2018 06:02

demonstrates how to train a model, init weights from another source (transfer learning), save models to pb and pbtxt files.

	import numpy as np

	from caffe2.python import (
	brew,
	model_helper,
	optimizer,
	workspace,
	utils,
	)
	from caffe2.proto import caffe2_pb2

qfgaohao / parse_pytorch_graph.py

Last active November 24, 2019 14:09

demonstrate how to trace/parse a pytorch graph

	import torch
	from torchvision import models

	def parse(net, inputs = torch.randn(1, 3, 224, 224)):
	with torch.onnx.set_training(net, False):
	trace = torch.onnx.utils._trace(net, inputs)

	graph = trace.graph()
	for n in graph.nodes():
	print(n.scopeName(), n.kind())

qfgaohao / create_hellotensor.py

Created April 30, 2019 04:40 — forked from omimo/create_hellotensor.py

A simple example for saving a tensorflow model and preparing it for using on Android

	# Create a simple TF Graph
	# By Omid Alemi - Jan 2017
	# Works with TF <r1.0

	import tensorflow as tf

	I = tf.placeholder(tf.float32, shape=[None,3], name='I') # input
	W = tf.Variable(tf.zeros_initializer(shape=[3,2]), dtype=tf.float32, name='W') # weights
	b = tf.Variable(tf.zeros_initializer(shape=[2]), dtype=tf.float32, name='b') # biases
	O = tf.nn.relu(tf.matmul(I, W) + b, name='O') # activation / output