Merge pull request #444 from Mjrovai/366-labs-raspi-support

Upload the Object Detection Lab

contents/labs/raspi/image_classification/image_classification.qmd

@@ -131,11 +131,10 @@ tflite_11_05_08/mobilenet_v2_1.0_224_quant.tgz
 tar xzf mobilenet_v2_1.0_224_quant.tgz
 ```
 
-Get its labels:
+Get its [labels](https://github.com/Mjrovai/EdgeML-with-Raspberry-Pi/blob/main/IMG_CLASS/models/labels.txt):
 
 ```bash
-wget https://raw.githubusercontent.com/tensorflow/tensorflow/master/tensorflow/
-lite/java/demo/app/src/main/assets/labels_mobilenet_quant_v1_224.txt -O labels.txt
+wget https://github.com/Mjrovai/EdgeML-with-Raspberry-Pi/blob/main/IMG_CLASS/models/labels.txt
 ```
 
 In the end, you should have the models in its directory: 
@@ -292,7 +291,7 @@ So, let's reshape the image, add the batch dimension, and see the result:
 
 ```python
 img = img.resize((input_details[0]['shape'][1], input_details[0]['shape'][2]))
-input_data = np.expand_dims(img, axis=0
+input_data = np.expand_dims(img, axis=0)
 input_data.shape
 ```
 
@@ -422,30 +421,30 @@ def image_classification(img_path, model_path, labels, top_k_results=5):
     # Get input and output tensors
     input_details = interpreter.get_input_details()
     output_details = interpreter.get_output_details()
-
+    
     # Preprocess
     img = img.resize((input_details[0]['shape'][1], 
                       input_details[0]['shape'][2]))
     input_data = np.expand_dims(img, axis=0)
-
+    
     # Inference on Raspi-Zero
     interpreter.set_tensor(input_details[0]['index'], input_data)
     interpreter.invoke()
 
     # Obtain results and map them to the classes
     predictions = interpreter.get_tensor(output_details[0]['index'])[0]
-
+    
     # Get indices of the top k results
     top_k_indices = np.argsort(predictions)[::-1][:top_k_results]
-
+    
     # Get quantization parameters
     scale, zero_point = output_details[0]['quantization']
-
+    
     # Dequantize the output and apply softmax
     dequantized_output = (predictions.astype(np.float32) - zero_point) * scale
     exp_output = np.exp(dequantized_output - np.max(dequantized_output))
     probabilities = exp_output / np.sum(exp_output)
-
+    
     print("\n\t[PREDICTION]        [Prob]\n")
     for i in range(top_k_results):
         print("\t{:20}: {}%".format(
@@ -483,7 +482,7 @@ On the notebook [Cifar 10 - Image Classification on a Raspi with TFLite](https:/
 
     ```bash
     source ~/tflite/bin/activate
-    ```
+```
 
 2. Now, let's create a .pth file in your virtual environment to add the system site-packages path:
 
@@ -578,6 +577,7 @@ Once we have defined our Machine Learning project goal, the next and most crucia
 2. Let's create a new Python script combining image capture with a web server.  We'll call it `get_img_data.py`:
 
 <div class="scroll-code-block">
+
 ```python
 from flask import Flask, Response, render_template_string, request, redirect, url_for
 from picamera2 import Picamera2
@@ -766,7 +766,7 @@ if __name__ == '__main__':
 
     ```bash
     python3 get_img_data.py
-    ```
+```
 
 3. Access the web interface:
 
@@ -1147,11 +1147,11 @@ def image_classification(img_path, model_path, labels, top_k_results=3,
     # Load the TFLite model
     interpreter = tflite.Interpreter(model_path=model_path)
     interpreter.allocate_tensors()
-
+    
     # Get input and output tensors
     input_details = interpreter.get_input_details()
     output_details = interpreter.get_output_details()
-
+    
     # Preprocess
     img = img.resize((input_details[0]['shape'][1], 
                       input_details[0]['shape'][2]))
@@ -1167,20 +1167,20 @@ def image_classification(img_path, model_path, labels, top_k_results=3,
         input_data = np.expand_dims(img_array, axis=0)
     else:  # float32
         input_data = np.expand_dims(np.array(img, dtype=np.float32), axis=0) / 255.0
-
+    
     # Inference on Raspi-Zero
     start_time = time.time()
     interpreter.set_tensor(input_details[0]['index'], input_data)
     interpreter.invoke()
     end_time = time.time()
     inference_time = (end_time - start_time) * 1000  # Convert to milliseconds
-
+    
     # Obtain results
     predictions = interpreter.get_tensor(output_details[0]['index'])[0]
-
+    
     # Get indices of the top k results
     top_k_indices = np.argsort(predictions)[::-1][:top_k_results]
-
+    
     # Handle output based on type
     output_dtype = output_details[0]['dtype']
     if output_dtype in [np.int8, np.uint8]:
@@ -1194,7 +1194,7 @@ def image_classification(img_path, model_path, labels, top_k_results=3,
         probabilities = exp_preds / np.sum(exp_preds)
     else:
         probabilities = predictions
-
+    
     print("\n\t[PREDICTION]        [Prob]\n")
     for i in range(top_k_results):
         print("\t{:20}: {:.1f}%".format(