[Example] Iterator tool for image classification

intel · Jan 28, 2019 · dc31ec2 · dc31ec2
1 parent 382e0cd
commit dc31ec2
Show file tree

Hide file tree

Showing 2 changed files with 90 additions and 43 deletions.
diff --git a/examples/deeplab/utils.js b/examples/deeplab/utils.js
@@ -45,49 +45,6 @@ class Utils {
     this.initialized = true;
   }
 
-  async iterateLayers(configs) {
-    if (!this.initialized) return;
-
-    let iterators = [];
-    for (let config of configs) {
-      let model = await new TFliteModelImporter({
-        rawModel: this.tfModel,
-        backend: config.backend,
-        prefer: config.prefer || null,
-      });
-      iterators.push(model.layerIterator([this.inputTensor]));
-    }
-
-    while (true) {
-
-      let layerOutputs = [];
-      for (let it of iterators) {
-        layerOutputs.push(await it.next());
-      }
-
-      let baselineOutput = layerOutputs[0];
-      if (baselineOutput.done) {
-        break;
-      }
-
-      console.debug(`\n\n\nLayer ${baselineOutput.value.outputName}`);
-
-      for (let i = 0; i < configs.length; ++i) {
-        console.debug(`\n${configs[i].backend}:`);
-        console.debug(`\n${layerOutputs[i].value.tensor}`);
-
-        if (i > 0) {
-          let sum = 0;
-          for (let j = 0; j < baselineOutput.value.tensor.length; j++) {
-            sum += Math.pow(layerOutputs[i].value.tensor[j] - baselineOutput.value.tensor[j], 2);
-          }
-          let variance = sum / baselineOutput.value.tensor.length;
-          console.debug(`var with ${configs[0].backend}: ${variance}`);
-        }
-      }
-    }
-  }
-
   async predict() {
     if (!this.initialized) return;
     let start = performance.now();
@@ -199,4 +156,48 @@ class Utils {
     this.outputTensor = new Float32Array(newModel.outputSize.reduce((x,y) => x*y));
     this.tfModel = null;
   }
+
+  // for debugging
+  async iterateLayers(configs) {
+    if (!this.initialized) return;
+
+    let iterators = [];
+    for (let config of configs) {
+      let model = await new TFliteModelImporter({
+        rawModel: this.tfModel,
+        backend: config.backend,
+        prefer: config.prefer || null,
+      });
+      iterators.push(model.layerIterator([this.inputTensor]));
+    }
+
+    while (true) {
+
+      let layerOutputs = [];
+      for (let it of iterators) {
+        layerOutputs.push(await it.next());
+      }
+
+      let baselineOutput = layerOutputs[0];
+      if (baselineOutput.done) {
+        break;
+      }
+
+      console.debug(`\n\n\nLayer ${baselineOutput.value.outputName}`);
+
+      for (let i = 0; i < configs.length; ++i) {
+        console.debug(`\n${configs[i].backend}:`);
+        console.debug(`\n${layerOutputs[i].value.tensor}`);
+
+        if (i > 0) {
+          let sum = 0;
+          for (let j = 0; j < baselineOutput.value.tensor.length; j++) {
+            sum += Math.pow(layerOutputs[i].value.tensor[j] - baselineOutput.value.tensor[j], 2);
+          }
+          let variance = sum / baselineOutput.value.tensor.length;
+          console.debug(`var with ${configs[0].backend}: ${variance}`);
+        }
+      }
+    }
+  }
 }
diff --git a/examples/image_classification/utils.js b/examples/image_classification/utils.js
@@ -218,4 +218,50 @@ class Utils {
       this.model._compilation._preparedModel._deleteAll();
     }
   }
+
+
+  // for debugging
+  async iterateLayers(configs) {
+    if (!this.initialized) return;
+
+    let iterators = [];
+    for (let config of configs) {
+      let importer = this.modelFile.split('.').pop() === 'tflite' ? TFliteModelImporter : OnnxModelImporter;
+      let model = await new importer({
+        rawModel: this.rawModel,
+        backend: config.backend,
+        prefer: config.prefer || null,
+      });
+      iterators.push(model.layerIterator([this.inputTensor]));
+    }
+
+    while (true) {
+
+      let layerOutputs = [];
+      for (let it of iterators) {
+        layerOutputs.push(await it.next());
+      }
+
+      let baselineOutput = layerOutputs[0];
+      if (baselineOutput.done) {
+        break;
+      }
+
+      console.debug(`\n\n\nLayer ${baselineOutput.value.outputName}`);
+
+      for (let i = 0; i < configs.length; ++i) {
+        console.debug(`\n${configs[i].backend}:`);
+        console.debug(`\n${layerOutputs[i].value.tensor}`);
+
+        if (i > 0) {
+          let sum = 0;
+          for (let j = 0; j < baselineOutput.value.tensor.length; j++) {
+            sum += Math.pow(layerOutputs[i].value.tensor[j] - baselineOutput.value.tensor[j], 2);
+          }
+          let variance = sum / baselineOutput.value.tensor.length;
+          console.debug(`var with ${configs[0].backend}: ${variance}`);
+        }
+      }
+    }
+  }
 }