diff --git a/CHANGELOG.md b/CHANGELOG.md
index 917d0021..5aeb3953 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,6 +11,7 @@
   
 ### **HEAD -> main** 2021/09/12 mandic00@live.com
 
+- minor typos
 - release candidate
 - parametrize face config
 - mark all config items as optional
diff --git a/src/env.ts b/src/env.ts
index d7b1ee78..d1bfa2f4 100644
--- a/src/env.ts
+++ b/src/env.ts
@@ -121,7 +121,7 @@ export async function get() {
   if (env.webgpu.supported) env.webgpu.adapter = (await navigator['gpu'].requestAdapter())?.name;
 
   // enumerate kernels
-  env.kernels = tf.getKernelsForBackend(tf.getBackend()).map((kernel) => kernel.kernelName);
+  env.kernels = tf.getKernelsForBackend(tf.getBackend()).map((kernel) => kernel.kernelName.toLowerCase());
 
   // get cpu info
   // cpuinfo();
diff --git a/src/handpose/handpipeline.ts b/src/handpose/handpipeline.ts
index 2b6d941b..4db952b4 100644
--- a/src/handpose/handpipeline.ts
+++ b/src/handpose/handpipeline.ts
@@ -3,6 +3,7 @@ import * as box from './box';
 import * as util from './util';
 import * as detector from './handdetector';
 import { Tensor, GraphModel } from '../tfjs/types';
+import { env } from '../env';
 
 const palmBoxEnlargeFactor = 5; // default 3
 const handBoxEnlargeFactor = 1.65; // default 1.65
@@ -109,7 +110,7 @@ export class HandPipeline {
         const angle = config.hand.rotation ? util.computeRotation(currentBox.palmLandmarks[palmLandmarksPalmBase], currentBox.palmLandmarks[palmLandmarksMiddleFingerBase]) : 0;
         const palmCenter = box.getBoxCenter(currentBox);
         const palmCenterNormalized = [palmCenter[0] / image.shape[2], palmCenter[1] / image.shape[1]];
-        const rotatedImage = config.hand.rotation && tf.ENV.flags.IS_BROWSER ? tf.image.rotateWithOffset(image, angle, 0, palmCenterNormalized) : image.clone();
+        const rotatedImage = config.hand.rotation && env.kernels.includes('rotatewithoffset') ? tf.image.rotateWithOffset(image, angle, 0, palmCenterNormalized) : image.clone();
         const rotationMatrix = util.buildRotationMatrix(-angle, palmCenter);
         const newBox = useFreshBox ? this.getBoxForPalmLandmarks(currentBox.palmLandmarks, rotationMatrix) : currentBox;
         const croppedInput = box.cutBoxFromImageAndResize(newBox, rotatedImage, [this.inputSize, this.inputSize]);
diff --git a/src/human.ts b/src/human.ts
index a3cfb441..c0765b92 100644
--- a/src/human.ts
+++ b/src/human.ts
@@ -226,7 +226,7 @@ export class Human {
   #sanity = (input: Input): null | string => {
     if (!this.#checkSanity) return null;
     if (!input) return 'input is not defined';
-    if (this.tf.ENV.flags.IS_NODE && !(input instanceof tf.Tensor)) return 'input must be a tensor';
+    if (this.env.node && !(input instanceof tf.Tensor)) return 'input must be a tensor';
     try {
       this.tf.getBackend();
     } catch {
@@ -293,10 +293,10 @@ export class Human {
     if (this.#firstRun) { // print version info on first run and check for correct backend setup
       if (this.config.debug) log(`version: ${this.version}`);
       if (this.config.debug) log(`tfjs version: ${this.tf.version_core}`);
-      if (this.config.debug) log('environment:', env.env);
+      // if (this.config.debug) log('environment:', this.env);
 
       await this.#checkBackend();
-      if (this.tf.ENV.flags.IS_BROWSER) {
+      if (this.env.browser) {
         if (this.config.debug) log('configuration:', this.config);
         if (this.config.debug) log('tf flags:', this.tf.ENV.flags);
       }
@@ -322,7 +322,7 @@ export class Human {
   // check if backend needs initialization if it changed
   /** @hidden */
   #checkBackend = async () => {
-    if (this.#firstRun || (this.config.backend && (this.config.backend.length > 0) || (this.tf.getBackend() !== this.config.backend))) {
+    if (this.#firstRun || (this.config.backend && (this.config.backend.length > 0) && (this.tf.getBackend() !== this.config.backend))) {
       const timeStamp = now();
       this.state = 'backend';
       /* force backend reload
@@ -343,17 +343,17 @@ export class Human {
         }
 
         // force browser vs node backend
-        if (this.tf.ENV.flags.IS_BROWSER && this.config.backend === 'tensorflow') {
+        if (this.env.browser && this.config.backend === 'tensorflow') {
           log('override: backend set to tensorflow while running in browser');
           this.config.backend = 'humangl';
         }
-        if (this.tf.ENV.flags.IS_NODE && (this.config.backend === 'webgl' || this.config.backend === 'humangl')) {
+        if (this.env.node && (this.config.backend === 'webgl' || this.config.backend === 'humangl')) {
           log(`override: backend set to ${this.config.backend} while running in nodejs`);
           this.config.backend = 'tensorflow';
         }
 
         // handle webgpu
-        if (this.tf.ENV.flags.IS_BROWSER && this.config.backend === 'webgpu') {
+        if (this.env.browser && this.config.backend === 'webgpu') {
           if (typeof navigator === 'undefined' || typeof navigator['gpu'] === 'undefined') {
             log('override: backend set to webgpu but browser does not support webgpu');
             this.config.backend = 'humangl';
@@ -370,8 +370,8 @@ export class Human {
 
         if (!available.includes(this.config.backend)) {
           log(`error: backend ${this.config.backend} not found in registry`);
-          this.config.backend = this.tf.ENV.flags.IS_NODE ? 'tensorflow' : 'humangl';
-          log(`override: using backend ${this.config.backend} instead`);
+          this.config.backend = this.env.node ? 'tensorflow' : 'humangl';
+          log(`override: setting backend ${this.config.backend}`);
         }
 
         if (this.config.debug) log('setting backend:', this.config.backend);
@@ -415,6 +415,7 @@ export class Human {
       this.tf.enableProdMode();
       await this.tf.ready();
       this.performance.backend = Math.trunc(now() - timeStamp);
+      this.config.backend = this.tf.getBackend();
 
       env.get(); // update env on backend init
       this.env = env.env;
diff --git a/src/image/image.ts b/src/image/image.ts
index 5df88412..ff428f86 100644
--- a/src/image/image.ts
+++ b/src/image/image.ts
@@ -6,6 +6,7 @@ import * as tf from '../../dist/tfjs.esm.js';
 import * as fxImage from './imagefx';
 import { Tensor } from '../tfjs/types';
 import { Config } from '../config';
+import { env } from '../env';
 
 type Input = Tensor | typeof Image | ImageData | ImageBitmap | HTMLImageElement | HTMLMediaElement | HTMLVideoElement | HTMLCanvasElement | OffscreenCanvas;
 
@@ -90,7 +91,7 @@ export function process(input: Input, config: Config): { tensor: Tensor | null,
         if (outCanvas?.width !== inCanvas?.width) outCanvas.width = inCanvas?.width;
         if (outCanvas?.height !== inCanvas?.height) outCanvas.height = inCanvas?.height;
         // log('created FX filter');
-        fx = tf.ENV.flags.IS_BROWSER ? new fxImage.GLImageFilter({ canvas: outCanvas }) : null; // && (typeof document !== 'undefined')
+        fx = env.browser ? new fxImage.GLImageFilter({ canvas: outCanvas }) : null; // && (typeof document !== 'undefined')
       }
       if (!fx) return { tensor: null, canvas: inCanvas };
       fx.reset();
diff --git a/src/object/centernet.ts b/src/object/centernet.ts
index 78b44785..d86dd7cd 100644
--- a/src/object/centernet.ts
+++ b/src/object/centernet.ts
@@ -8,6 +8,7 @@ import { labels } from './labels';
 import { ObjectResult } from '../result';
 import { GraphModel, Tensor } from '../tfjs/types';
 import { Config } from '../config';
+import { env } from '../env';
 
 let model;
 let last: ObjectResult[] = [];
@@ -76,6 +77,7 @@ export async function predict(input: Tensor, config: Config): Promise<ObjectResu
     return last;
   }
   skipped = 0;
+  if (!env.kernels.includes('mod') || !env.kernels.includes('sparsetodense')) return last;
   return new Promise(async (resolve) => {
     const outputSize = [input.shape[2], input.shape[1]];
     const resize = tf.image.resizeBilinear(input, [model.inputSize, model.inputSize]);
diff --git a/src/object/nanodet.ts b/src/object/nanodet.ts
index 8bdabf17..8e50f46c 100644
--- a/src/object/nanodet.ts
+++ b/src/object/nanodet.ts
@@ -8,6 +8,7 @@ import { labels } from './labels';
 import { ObjectResult } from '../result';
 import { GraphModel, Tensor } from '../tfjs/types';
 import { Config } from '../config';
+import { env } from '../env';
 
 let model;
 let last: Array<ObjectResult> = [];
@@ -108,6 +109,7 @@ export async function predict(image: Tensor, config: Config): Promise<ObjectResu
     return last;
   }
   skipped = 0;
+  if (!env.kernels.includes('mod') || !env.kernels.includes('sparsetodense')) return last;
   return new Promise(async (resolve) => {
     const outputSize = [image.shape[2], image.shape[1]];
     const resize = tf.image.resizeBilinear(image, [model.inputSize, model.inputSize], false);
diff --git a/wiki b/wiki
index ee12bda3..0e902fcb 160000
--- a/wiki
+++ b/wiki
@@ -1 +1 @@
-Subproject commit ee12bda3113d3d893c898a9827f9c174d4058fb8
+Subproject commit 0e902fcb57bdf9b65ed5e7ef281a699e95db6d99