vatsal-sodha’s gists

vatsal-sodha / image_resizer.proto

Created July 30, 2018 00:52

	syntax = "proto2";

	package object_detection.protos;

	// Configuration proto for image resizing operations.
	// See builders/image_resizer_builder.py for details.
	message ImageResizer {
	oneof image_resizer_oneof {
	KeepAspectRatioResizer keep_aspect_ratio_resizer = 1;
	FixedShapeResizer fixed_shape_resizer = 2;

vatsal-sodha / model.proto

Created July 29, 2018 23:40

	syntax = "proto2";

	package object_detection.protos;

	import "object_detection/protos/faster_rcnn.proto";
	import "object_detection/protos/ssd.proto";

	// Top level configuration for DetectionModels.
	message DetectionModel {
	oneof model {

vatsal-sodha / grid_anchor_generator.proto

Created July 28, 2018 08:10

grid_anchor_generator.proto

	syntax = "proto2";

	package object_detection.protos;

	// Configuration proto for GridAnchorGenerator. See
	// anchor_generators/grid_anchor_generator.py for details.
	message GridAnchorGenerator {
	// Anchor height in pixels.
	optional int32 height = 1 [default = 256];

vatsal-sodha / faster_rcnn_resnet50_pets.config

Created July 1, 2018 13:35

Faster R-CNN with Resnet-50 config file

	# Faster R-CNN with Resnet-50 (v1), configured for Oxford-IIIT Pets Dataset.
	# Users should configure the fine_tune_checkpoint field in the train config as
	# well as the label_map_path and input_path fields in the train_input_reader and
	# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
	# should be configured.

	model {
	faster_rcnn {
	num_classes: 37
	image_resizer {

vatsal-sodha / object-detection.pbtxt

Created March 26, 2018 11:15

vatsal-sodha / generate_tfRecord.py

Created March 26, 2018 10:40

Generating tfRecords for TensoFlow Object Detection API

	"""
	Usage:
	# From tensorflow/models/
	# Create train data:
	python generate_tfrecord.py --csv_input=data/train_labels.csv --output_path=train.record

	# Create test data:
	python generate_tfrecord.py --csv_input=data/test_labels.csv --output_path=test.record
	"""
	from __future__ import division

vatsal-sodha / nodules.csv

Created March 26, 2018 10:17

For TensorFlow object detection API tutorial

vatsal-sodha / HammingCode.py

Created October 16, 2016 20:12

Python function for generating hamming code and detecting single bit error for any size of data length

	#function to check no of parity bits in genration of hamming code
	#return no of parity bits required to append in given size of data word
	def noOfParityBits(noOfBits):
	i=0
	while 2.**i <= noOfBits+i: # (power of 2 + parity bits laready counted) that is for 4 bit of dataword requires 3 bit of parity bits
	i+=1
	return i
	#function to genrate no of parity bits in while correction of hamming codes returns no of parity bits in given size of code word
	def noOfParityBitsInCode(noOfBits):
	i=0

vatsal-sodha / gist:e29451d82815aa82aec2ec5c822a561c

Created October 16, 2016 20:10

Python Function for generating hamming code and detecting single bit error for any size of data

	#function to check no of parity bits in genration of hamming code
	#return no of parity bits required to append in given size of data word
	def noOfParityBits(noOfBits):
	i=0
	while 2.**i <= noOfBits+i: # (power of 2 + parity bits laready counted) that is for 4 bit of dataword requires 3 bit of parity bits
	i+=1
	return i
	#function to genrate no of parity bits in while correction of hamming codes returns no of parity bits in given size of code word
	def noOfParityBitsInCode(noOfBits):
	i=0

Vatsal Sodha vatsal-sodha