From 93a2bcc760124ab251b86038e45e285ed0aa7736 Mon Sep 17 00:00:00 2001
From: Glenn Jocher <glenn.jocher@ultralytics.com>
Date: Sun, 14 Nov 2021 22:33:34 +0100
Subject: [PATCH] Created using Colaboratory

---
 tutorial.ipynb | 189 ++++++++++++++++++++++++-------------------------
 1 file changed, 94 insertions(+), 95 deletions(-)

diff --git a/tutorial.ipynb b/tutorial.ipynb
index 828e434f..4e7049d8 100644
--- a/tutorial.ipynb
+++ b/tutorial.ipynb
@@ -368,7 +368,7 @@
         "colab_type": "text"
       },
       "source": [
-        "<a href=\"https://colab.research.google.com/github/ultralytics/yolov3/blob/update%2Fyolov5_v6.0_release/tutorial.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+        "<a href=\"https://colab.research.google.com/github/ultralytics/yolov3/blob/master/tutorial.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
@@ -402,10 +402,10 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "2e5d0950-2978-4304-856f-3b39f0d6627c"
+        "outputId": "b15def02-a331-4580-9878-8d06900e296d"
       },
       "source": [
-        "!git clone https://github.com/ultralytics/yolov3 -b update/yolov5_v6.0_release  # clone\n",
+        "!git clone https://github.com/ultralytics/yolov3  # clone\n",
         "%cd yolov3\n",
         "%pip install -qr requirements.txt  # install\n",
         "\n",
@@ -413,13 +413,13 @@
         "from yolov3 import utils\n",
         "display = utils.notebook_init()  # checks"
       ],
-      "execution_count": 1,
+      "execution_count": 11,
       "outputs": [
         {
           "output_type": "stream",
           "name": "stderr",
           "text": [
-            "YOLOv3 🚀 v9.5.0-20-g9d10fe5 torch 1.10.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB)\n"
+            "YOLOv3 🚀 v9.6.0-0-g7eb23e3 torch 1.10.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB)\n"
           ]
         },
         {
@@ -459,26 +459,26 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "499c53a7-95f7-4fc1-dab8-7a660b813546"
+        "outputId": "5754dd6d-b5b0-41aa-ce81-7cc7a4c30553"
       },
       "source": [
         "!python detect.py --weights yolov3.pt --img 640 --conf 0.25 --source data/images\n",
         "display.Image(filename='runs/detect/exp/zidane.jpg', width=600)"
       ],
-      "execution_count": 3,
+      "execution_count": 15,
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
             "\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov3.pt'], source=data/images, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False\n",
-            "YOLOv3 🚀 v9.5.0-20-g9d10fe5 torch 1.10.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB)\n",
+            "YOLOv3 🚀 v9.6.0-0-g7eb23e3 torch 1.10.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB)\n",
             "\n",
             "Fusing layers... \n",
             "Model Summary: 261 layers, 61922845 parameters, 0 gradients\n",
             "image 1/2 /content/yolov3/data/images/bus.jpg: 640x480 4 persons, 1 bus, 1 tie, Done. (0.020s)\n",
             "image 2/2 /content/yolov3/data/images/zidane.jpg: 384x640 2 persons, 3 ties, Done. (0.020s)\n",
-            "Speed: 0.5ms pre-process, 19.8ms inference, 1.2ms NMS per image at shape (1, 3, 640, 640)\n",
+            "Speed: 0.6ms pre-process, 20.0ms inference, 1.2ms NMS per image at shape (1, 3, 640, 640)\n",
             "Results saved to \u001b[1mruns/detect/exp\u001b[0m\n"
           ]
         }
@@ -567,43 +567,42 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "0f4cfe4e-364e-4d79-e0af-8884d89eaacd"
+        "outputId": "fe3159ef-a2e4-49e3-ec0b-2ef434e9a28e"
       },
       "source": [
         "# Run YOLOv3 on COCO val\n",
         "!python val.py --weights yolov3.pt --data coco.yaml --img 640 --iou 0.65 --half"
       ],
-      "execution_count": 5,
+      "execution_count": 13,
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
             "\u001b[34m\u001b[1mval: \u001b[0mdata=/content/yolov3/data/coco.yaml, weights=['yolov3.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True, dnn=False\n",
-            "YOLOv3 🚀 v9.5.0-20-g9d10fe5 torch 1.10.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB)\n",
+            "YOLOv3 🚀 v9.6.0-0-g7eb23e3 torch 1.10.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB)\n",
             "\n",
             "Fusing layers... \n",
             "Model Summary: 261 layers, 61922845 parameters, 0 gradients\n",
-            "\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:00<00:00, 12689.82it/s]\n",
-            "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: ../datasets/coco/val2017.cache\n",
-            "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 157/157 [00:42<00:00,  3.70it/s]\n",
+            "\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco/val2017.cache' images and labels... 4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:00<?, ?it/s]\n",
+            "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 157/157 [00:42<00:00,  3.68it/s]\n",
             "                 all       5000      36335      0.655      0.599      0.623       0.42\n",
             "Speed: 0.1ms pre-process, 2.1ms inference, 1.2ms NMS per image at shape (32, 3, 640, 640)\n",
             "\n",
             "Evaluating pycocotools mAP... saving runs/val/exp/yolov3_predictions.json...\n",
             "loading annotations into memory...\n",
-            "Done (t=0.45s)\n",
+            "Done (t=0.44s)\n",
             "creating index...\n",
             "index created!\n",
             "Loading and preparing results...\n",
-            "DONE (t=5.04s)\n",
+            "DONE (t=4.95s)\n",
             "creating index...\n",
             "index created!\n",
             "Running per image evaluation...\n",
             "Evaluate annotation type *bbox*\n",
-            "DONE (t=82.40s).\n",
+            "DONE (t=86.74s).\n",
             "Accumulating evaluation results...\n",
-            "DONE (t=12.41s).\n",
+            "DONE (t=12.46s).\n",
             " Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.433\n",
             " Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.630\n",
             " Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.470\n",
@@ -712,13 +711,13 @@
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "outputId": "28039ba4-b23b-4e59-ea0e-e1f8f7df0cdb"
+        "outputId": "ed857ac6-f674-425b-8163-c7ae0c107311"
       },
       "source": [
         "# Train YOLOv3 on COCO128 for 3 epochs\n",
         "!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov3.pt --cache"
       ],
-      "execution_count": 8,
+      "execution_count": 14,
       "outputs": [
         {
           "output_type": "stream",
@@ -726,7 +725,7 @@
           "text": [
             "\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov3.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, adam=False, sync_bn=False, workers=8, project=runs/train, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, patience=100, freeze=0, save_period=-1, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest\n",
             "\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov3 ✅\n",
-            "YOLOv3 🚀 v9.5.0-20-g9d10fe5 torch 1.10.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB)\n",
+            "YOLOv3 🚀 v9.6.0-0-g7eb23e3 torch 1.10.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB)\n",
             "\n",
             "\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.1, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0\n",
             "\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv3 🚀 runs (RECOMMENDED)\n",
@@ -769,9 +768,9 @@
             "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 72 weight, 75 weight (no decay), 75 bias\n",
             "\u001b[34m\u001b[1malbumentations: \u001b[0mversion 1.0.3 required by YOLOv3, but version 0.1.12 is currently installed\n",
             "\u001b[34m\u001b[1mtrain: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<?, ?it/s]\n",
-            "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 1376.44it/s]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 1510.60it/s]\n",
             "\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<?, ?it/s]\n",
-            "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 414.73it/s]\n",
+            "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 400.72it/s]\n",
             "Plotting labels to runs/train/exp/labels.jpg... \n",
             "\n",
             "\u001b[34m\u001b[1mAutoAnchor: \u001b[0m4.27 anchors/target, 0.994 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅\n",
@@ -781,19 +780,19 @@
             "Starting training for 3 epochs...\n",
             "\n",
             "     Epoch   gpu_mem       box       obj       cls    labels  img_size\n",
-            "       0/2     12.2G   0.06494   0.08502   0.01907       186       640: 100% 8/8 [00:04<00:00,  1.89it/s]\n",
+            "       0/2     12.2G   0.06494   0.08502   0.01907       186       640: 100% 8/8 [00:04<00:00,  1.94it/s]\n",
             "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00,  5.14it/s]\n",
-            "                 all        128        929        0.5      0.342      0.394      0.175\n",
+            "                 all        128        929        0.5      0.343      0.394      0.175\n",
             "\n",
             "     Epoch   gpu_mem       box       obj       cls    labels  img_size\n",
-            "       1/2     16.3G   0.06255   0.08206   0.01831       164       640: 100% 8/8 [00:01<00:00,  4.86it/s]\n",
-            "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00,  5.12it/s]\n",
+            "       1/2     16.3G   0.06255   0.08206   0.01831       164       640: 100% 8/8 [00:01<00:00,  4.80it/s]\n",
+            "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00,  5.11it/s]\n",
             "                 all        128        929      0.487      0.437      0.475      0.205\n",
             "\n",
             "     Epoch   gpu_mem       box       obj       cls    labels  img_size\n",
-            "       2/2     16.3G   0.06032   0.07332   0.01861       192       640: 100% 8/8 [00:01<00:00,  4.74it/s]\n",
-            "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00,  5.24it/s]\n",
-            "                 all        128        929      0.564      0.455      0.528       0.23\n",
+            "       2/2     16.3G   0.06032   0.07331   0.01861       192       640: 100% 8/8 [00:01<00:00,  4.81it/s]\n",
+            "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00,  5.17it/s]\n",
+            "                 all        128        929      0.565      0.455      0.528      0.231\n",
             "\n",
             "3 epochs completed in 0.006 hours.\n",
             "Optimizer stripped from runs/train/exp/weights/last.pt, 124.4MB\n",
@@ -802,79 +801,79 @@
             "Validating runs/train/exp/weights/best.pt...\n",
             "Fusing layers... \n",
             "Model Summary: 261 layers, 61922845 parameters, 0 gradients, 156.1 GFLOPs\n",
-            "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00,  1.21it/s]\n",
-            "                 all        128        929      0.561      0.456      0.528      0.231\n",
-            "              person        128        254      0.573      0.567      0.593      0.246\n",
-            "             bicycle        128          6      0.183      0.167      0.273      0.124\n",
-            "                 car        128         46      0.557       0.13      0.218     0.0538\n",
-            "          motorcycle        128          5      0.682        0.8      0.818      0.272\n",
-            "            airplane        128          6      0.769      0.563      0.809      0.322\n",
-            "                 bus        128          7      0.717      0.714      0.752      0.541\n",
-            "               train        128          3       0.67      0.667      0.863      0.221\n",
-            "               truck        128         12      0.686      0.333      0.469      0.186\n",
-            "                boat        128          6       0.67      0.333      0.473       0.19\n",
-            "       traffic light        128         14       0.18     0.0257     0.0721     0.0435\n",
-            "           stop sign        128          2      0.369        0.5      0.497      0.137\n",
-            "               bench        128          9      0.479      0.333      0.387      0.125\n",
-            "                bird        128         16      0.519      0.472       0.59      0.224\n",
-            "                 cat        128          4      0.661      0.978      0.828      0.555\n",
-            "                 dog        128          9      0.532      0.333      0.523      0.265\n",
-            "               horse        128          2      0.698          1      0.995      0.596\n",
-            "            elephant        128         17      0.677      0.647      0.755      0.277\n",
-            "                bear        128          1      0.683          1      0.995      0.398\n",
-            "               zebra        128          4      0.753          1      0.945        0.4\n",
-            "             giraffe        128          9      0.274      0.889      0.767      0.328\n",
-            "            backpack        128          6      0.608      0.167      0.463      0.183\n",
-            "            umbrella        128         18       0.68      0.708      0.749       0.25\n",
-            "             handbag        128         19      0.661      0.158      0.305      0.157\n",
-            "                 tie        128          7      0.813      0.626      0.753       0.29\n",
-            "            suitcase        128          4      0.518        0.5      0.781       0.34\n",
-            "             frisbee        128          5      0.556      0.512      0.454      0.289\n",
+            "               Class     Images     Labels          P          R     mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00,  1.22it/s]\n",
+            "                 all        128        929      0.565      0.454      0.528      0.231\n",
+            "              person        128        254      0.576      0.567      0.593      0.245\n",
+            "             bicycle        128          6      0.184      0.167      0.273      0.124\n",
+            "                 car        128         46      0.568       0.13      0.217     0.0537\n",
+            "          motorcycle        128          5      0.683        0.8      0.818      0.272\n",
+            "            airplane        128          6      0.766      0.555      0.809      0.342\n",
+            "                 bus        128          7      0.718      0.714      0.752      0.541\n",
+            "               train        128          3      0.676      0.667      0.863      0.221\n",
+            "               truck        128         12      0.699      0.333      0.469      0.186\n",
+            "                boat        128          6      0.675      0.333      0.472       0.19\n",
+            "       traffic light        128         14      0.176     0.0252     0.0721     0.0435\n",
+            "           stop sign        128          2       0.37        0.5      0.497      0.137\n",
+            "               bench        128          9       0.48      0.333      0.393      0.126\n",
+            "                bird        128         16      0.518      0.471       0.59      0.224\n",
+            "                 cat        128          4      0.656       0.96      0.828      0.555\n",
+            "                 dog        128          9      0.534      0.333      0.523      0.265\n",
+            "               horse        128          2        0.7          1      0.995      0.596\n",
+            "            elephant        128         17      0.677      0.647      0.754      0.286\n",
+            "                bear        128          1      0.684          1      0.995      0.398\n",
+            "               zebra        128          4      0.755          1      0.945        0.4\n",
+            "             giraffe        128          9      0.275      0.889      0.767      0.328\n",
+            "            backpack        128          6      0.611      0.167      0.463      0.183\n",
+            "            umbrella        128         18      0.679      0.706      0.749       0.25\n",
+            "             handbag        128         19      0.663      0.158      0.305      0.157\n",
+            "                 tie        128          7      0.811      0.618      0.753       0.29\n",
+            "            suitcase        128          4      0.522        0.5      0.781       0.34\n",
+            "             frisbee        128          5      0.552      0.503      0.454      0.289\n",
             "                skis        128          1          0          0      0.124     0.0124\n",
-            "           snowboard        128          7      0.747      0.571      0.695      0.305\n",
-            "         sports ball        128          6      0.601      0.167      0.177     0.0865\n",
-            "                kite        128         10      0.222        0.2      0.153     0.0284\n",
-            "        baseball bat        128          4      0.948       0.25      0.461      0.212\n",
-            "      baseball glove        128          7      0.792      0.143      0.248      0.159\n",
-            "          skateboard        128          5       0.61        0.2      0.371       0.16\n",
-            "       tennis racket        128          7      0.424      0.286      0.342      0.134\n",
-            "              bottle        128         18       0.43      0.278      0.425      0.167\n",
-            "          wine glass        128         16      0.607      0.438      0.532       0.24\n",
-            "                 cup        128         36      0.418      0.278      0.409      0.121\n",
-            "                fork        128          6       0.43      0.333      0.441      0.121\n",
-            "               knife        128         16      0.746      0.368      0.434      0.162\n",
-            "               spoon        128         22      0.485      0.273      0.342      0.113\n",
-            "                bowl        128         28      0.583        0.5      0.615      0.382\n",
-            "              banana        128          1      0.773          1      0.995      0.298\n",
+            "           snowboard        128          7      0.749      0.571      0.695      0.305\n",
+            "         sports ball        128          6      0.609      0.167      0.177     0.0865\n",
+            "                kite        128         10      0.225        0.2      0.154      0.026\n",
+            "        baseball bat        128          4      0.956       0.25      0.461      0.212\n",
+            "      baseball glove        128          7      0.905      0.143      0.248      0.159\n",
+            "          skateboard        128          5      0.611        0.2      0.371       0.16\n",
+            "       tennis racket        128          7      0.427      0.286      0.343      0.135\n",
+            "              bottle        128         18      0.432      0.278      0.425      0.167\n",
+            "          wine glass        128         16      0.614      0.438      0.531      0.239\n",
+            "                 cup        128         36      0.421      0.278      0.411      0.121\n",
+            "                fork        128          6      0.439      0.333      0.441      0.123\n",
+            "               knife        128         16      0.744      0.365      0.419      0.161\n",
+            "               spoon        128         22      0.487      0.273      0.342      0.112\n",
+            "                bowl        128         28      0.582      0.496      0.615      0.382\n",
+            "              banana        128          1      0.776          1      0.995      0.298\n",
             "            sandwich        128          2          1          0      0.663      0.498\n",
-            "              orange        128          4      0.464       0.66      0.472      0.235\n",
-            "            broccoli        128         11      0.132      0.182      0.123     0.0912\n",
-            "              carrot        128         24      0.223       0.25      0.266      0.112\n",
-            "             hot dog        128          2      0.645          1      0.995      0.275\n",
+            "              orange        128          4      0.463      0.658      0.472      0.235\n",
+            "            broccoli        128         11      0.133      0.182      0.123     0.0912\n",
+            "              carrot        128         24      0.225       0.25      0.266      0.112\n",
+            "             hot dog        128          2      0.647          1      0.995      0.275\n",
             "               pizza        128          5      0.398        0.8      0.639      0.322\n",
             "               donut        128         14      0.662          1       0.82      0.436\n",
-            "                cake        128          4      0.776      0.879      0.945      0.449\n",
+            "                cake        128          4      0.775      0.877      0.945      0.449\n",
             "               chair        128         35      0.323        0.4      0.328      0.113\n",
-            "               couch        128          6      0.401      0.333      0.399      0.251\n",
-            "        potted plant        128         14      0.803      0.643      0.679      0.281\n",
-            "                 bed        128          3      0.663      0.333       0.83      0.416\n",
-            "        dining table        128         13      0.314      0.615      0.291      0.135\n",
-            "              toilet        128          2       0.79          1      0.995      0.298\n",
-            "                  tv        128          2      0.627          1      0.828      0.414\n",
-            "              laptop        128          3          1          0      0.194       0.18\n",
+            "               couch        128          6      0.428      0.333      0.399      0.251\n",
+            "        potted plant        128         14      0.806      0.643      0.678       0.28\n",
+            "                 bed        128          3      0.667      0.333       0.83      0.416\n",
+            "        dining table        128         13      0.337      0.615      0.291      0.128\n",
+            "              toilet        128          2      0.791          1      0.995      0.298\n",
+            "                  tv        128          2      0.629          1      0.828      0.414\n",
+            "              laptop        128          3          1          0      0.194      0.179\n",
             "               mouse        128          2          1          0      0.129     0.0258\n",
             "              remote        128          8      0.217      0.125      0.204     0.0994\n",
             "          cell phone        128          8      0.557      0.168       0.42      0.076\n",
-            "           microwave        128          3       0.65      0.667      0.747      0.292\n",
+            "           microwave        128          3      0.652      0.667      0.747      0.292\n",
             "                oven        128          5      0.422        0.4      0.486      0.195\n",
-            "                sink        128          6      0.273      0.333       0.24      0.118\n",
-            "        refrigerator        128          5      0.565        0.6      0.699      0.371\n",
-            "                book        128         29      0.408      0.138      0.263     0.0898\n",
-            "               clock        128          9      0.508      0.333      0.572      0.291\n",
-            "                vase        128          2      0.264      0.546      0.695      0.367\n",
+            "                sink        128          6      0.275      0.333       0.24      0.118\n",
+            "        refrigerator        128          5      0.568        0.6      0.699      0.371\n",
+            "                book        128         29      0.411      0.138      0.263     0.0897\n",
+            "               clock        128          9      0.509      0.333      0.572      0.291\n",
+            "                vase        128          2      0.257      0.523      0.695      0.367\n",
             "            scissors        128          1          1          0     0.0113    0.00226\n",
-            "          teddy bear        128         21      0.506      0.333      0.403      0.146\n",
-            "          toothbrush        128          5      0.277        0.2      0.263     0.0837\n",
+            "          teddy bear        128         21      0.508      0.333      0.403      0.146\n",
+            "          toothbrush        128          5      0.279        0.2      0.263     0.0837\n",
             "Results saved to \u001b[1mruns/train/exp\u001b[0m\n"
           ]
         }
@@ -1081,4 +1080,4 @@
       "outputs": []
     }
   ]
-}
+}
\ No newline at end of file