Update utils/predict.py

utils/predict.py

@@ -61,19 +61,19 @@ def predict_batch(image_path):
     predictions_df = pd.DataFrame()
     num =  random.randint(0,50)
     for images, labels in slice:
-      for i in range(6):
-            ax = plt.subplot(3, 3, i + 1)
+      for i, j in zip(range(num,num+6), range(6)):
+            ax = plt.subplot(3, 3, j + 1)
             plt.imshow(images[i].numpy().astype("uint8"))
             output = np.argmax(slice_pred[i])
 
             prob_list = slice_pred[i].numpy().flatten().tolist()
             sorted_prob = np.argsort(slice_pred[i])[::-1].flatten()
-            prob_scores = {"image": "image "+ str(i), "first": f"predicted {class_vocab[sorted_prob[0]]} with {round(prob_list[sorted_prob[0]] * 100,2)}% confidence", 
+            prob_scores = {"image": "image "+ str(j), "first": f"predicted {class_vocab[sorted_prob[0]]} with {round(prob_list[sorted_prob[0]] * 100,2)}% confidence", 
             "second": f"predicted {class_vocab[sorted_prob[1]]} is {round(prob_list[sorted_prob[1]] * 100,2)}% confidence", 
             "third": f"predicted {class_vocab[sorted_prob[2]]} is {round(prob_list[sorted_prob[2]] * 100,2)}% confidence"}
             predictions_df = predictions_df.append(prob_scores,ignore_index=True)
             
-            plt.title(f"image {i} : {class_vocab[output]}")
+            plt.title(f"image {j} : {class_vocab[output]}")
             plt.axis("off")
             plt.savefig(saved_plot,bbox_inches='tight')