creation of the space

README.md

@@ -5,9 +5,45 @@ colorFrom: blue
 colorTo: yellow
 sdk: streamlit
 sdk_version: 1.27.2
-app_file: app.py
+app_file: app06.py
 pinned: false
 license: mit
 ---
 
+
+# 🛠️ PCB Defect Detection App 
+
+This app allows users to upload PCB images and detect defects using state-of-the-art machine learning models.
+
+## 🌟 Features 
+
+- **Image Upload**: Easily upload your PCB images and get instant defect predictions.
+- **Visualization**: Visualize the detected defects on the PCB image.
+- **Defect Types**: The app can identify multiple types of defects and highlight them uniquely for easy identification.
+
+## 🚀 Usage 
+
+### 1️⃣ Uploading an Image:
+- Click on the "Browse files" button.
+- Select a PCB image from your device.
+- Sit back and relax! Let the model churn through the image and present its findings.
+
+### 2️⃣ Interpreting Results:
+- It will display the original image alongside the predicted defect mask.
+- Different defect types will be highlighted using unique grayscale values.
+
+## Model Details
+
+The app utilzes the Segformer model trained on a custom PCB dataset. The model has been fine-tuned to detect:
+- **Incorrect Installation**
+- **Short Circuit**
+- **Dry Joints**  
+
+... commonly found defects in PCBs.
+
+
+## 📜 Requirements
+
+The app is built using `Streamlit` and leverages the `Hugging Face Transformers` library for model inference. For a full list of requirements, refer to the `requirements.txt` file.
+
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app06.py

@@ -0,0 +1,38 @@
+
+import streamlit as st
+from transformers import SegformerForSemanticSegmentation, SegformerImageProcessor
+from PIL import Image
+import numpy as np
+import torch
+
+# Load the model and processor
+model_dir = "C://Users//nazli//OneDrive//Desktop//PCB-Defect-Detection-Segmentation//model11//model//"
+model = SegformerForSemanticSegmentation.from_pretrained(model_dir)
+processor = SegformerImageProcessor.from_pretrained(model_dir)
+model.eval()
+
+st.title("PCB Defect Detection")
+
+# Upload image in Streamlit
+uploaded_file = st.file_uploader("Upload a PCB image", type=["jpg", "png"])
+
+if uploaded_file:
+    # Preprocess the image
+    test_image = Image.open(uploaded_file).convert("RGB")
+    inputs = processor(images=test_image, return_tensors="pt")
+
+    # Model inference
+    with torch.no_grad():
+        outputs = model(**inputs)
+
+    # Post-process
+    semantic_map = processor.post_process_semantic_segmentation(outputs, target_sizes=[test_image.size[::-1]])[0]
+    semantic_map = np.uint8(semantic_map)
+    semantic_map[semantic_map==1] = 255
+    semantic_map[semantic_map==2] = 195
+    semantic_map[semantic_map==3] = 135
+    semantic_map[semantic_map==4] = 75
+
+    # Display the results
+    st.image(test_image, caption="Uploaded Image", use_column_width=True)
+    st.image(semantic_map, caption="Predicted Defects", use_column_width=True, channels="GRAY")

model/config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "segformer-b0-finetuned-pcb-outputs/checkpoint-16500",
+  "architectures": [
+    "SegformerForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 256,
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    32,
+    64,
+    160,
+    256
+  ],
+  "id2label": {
+    "0": "background",
+    "1": "Short_circuit",
+    "2": "Dry_joint",
+    "3": "Incorrect_installation"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Dry_joint": 2,
+    "Incorrect_installation": 3,
+    "Short_circuit": 1,
+    "background": 0
+  },
+  "layer_norm_eps": 1e-06,
+  "mlp_ratios": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "model_type": "segformer",
+  "num_attention_heads": [
+    1,
+    2,
+    5,
+    8
+  ],
+  "num_channels": 3,
+  "num_encoder_blocks": 4,
+  "patch_sizes": [
+    7,
+    3,
+    3,
+    3
+  ],
+  "reshape_last_stage": true,
+  "semantic_loss_ignore_index": 255,
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0"
+}

model/preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_normalize": true,
+  "do_reduce_labels": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "SegformerImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 512,
+    "width": 512
+  }
+}

model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa39910006f4344fe9f3ee950bfcfb8de2b2090a3fcd59354832e9c4b0aee36
+size 14930957

requirements.txt

@@ -0,0 +1,6 @@
+numpy==1.26.0
+Pillow==9.5.0
+Pillow==10.0.1
+streamlit==1.24.1
+torch==2.0.1
+transformers==4.30.2

training/train/WIN_20221017_18_46_59_Pro_jpg.rf.78cb5715edb922dd6140afc84d64d8c5.xml

@@ -0,0 +1,14 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_46_59_Pro_jpg.rf.78cb5715edb922dd6140afc84d64d8c5.jpg</filename>
+	<path>WIN_20221017_18_46_59_Pro_jpg.rf.78cb5715edb922dd6140afc84d64d8c5.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+</annotation>

training/train/WIN_20221017_18_46_59_Pro_jpg.rf.7f17d30a83c990fa68a33e983c814709.xml

@@ -0,0 +1,14 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_46_59_Pro_jpg.rf.7f17d30a83c990fa68a33e983c814709.jpg</filename>
+	<path>WIN_20221017_18_46_59_Pro_jpg.rf.7f17d30a83c990fa68a33e983c814709.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+</annotation>

training/train/WIN_20221017_18_46_59_Pro_jpg.rf.97f5d550dde3b43965a5400369167e52.xml

@@ -0,0 +1,14 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_46_59_Pro_jpg.rf.97f5d550dde3b43965a5400369167e52.jpg</filename>
+	<path>WIN_20221017_18_46_59_Pro_jpg.rf.97f5d550dde3b43965a5400369167e52.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+</annotation>

training/train/WIN_20221017_18_48_04_Pro_jpg.rf.fbf91369966a68271571a4e676c89f9d.xml

@@ -0,0 +1,14 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_48_04_Pro_jpg.rf.fbf91369966a68271571a4e676c89f9d.jpg</filename>
+	<path>WIN_20221017_18_48_04_Pro_jpg.rf.fbf91369966a68271571a4e676c89f9d.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+</annotation>

training/train/WIN_20221017_18_48_04_Pro_jpg.rf.fff6f5430ca351843aeb9277506c1fe9.xml

@@ -0,0 +1,14 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_48_04_Pro_jpg.rf.fff6f5430ca351843aeb9277506c1fe9.jpg</filename>
+	<path>WIN_20221017_18_48_04_Pro_jpg.rf.fff6f5430ca351843aeb9277506c1fe9.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+</annotation>

training/train/WIN_20221017_18_48_12_Pro_jpg.rf.a0952389431e2d9456613cafc60cbabb.xml

@@ -0,0 +1,81 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_48_12_Pro_jpg.rf.a0952389431e2d9456613cafc60cbabb.jpg</filename>
+	<path>WIN_20221017_18_48_12_Pro_jpg.rf.a0952389431e2d9456613cafc60cbabb.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Incorrect_installation</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>208</xmin>
+			<xmax>322</xmax>
+			<ymin>225</ymin>
+			<ymax>351</ymax>
+		</bndbox>
+		<polygon>
+			<x1>214</x1>
+			<y1>258.8</y1>
+			<x2>220</x2>
+			<y2>259.4</y2>
+			<x3>206.5</x3>
+			<y3>298.09</y3>
+			<x4>250.66</x4>
+			<y4>313.64</y4>
+			<x5>248.1</x5>
+			<y5>326.1</y5>
+			<x6>244</x6>
+			<y6>326.8</y6>
+			<x7>241.9</x7>
+			<y7>347.9</y7>
+			<x8>273.2</x8>
+			<y8>350.1</y8>
+			<x9>275.5</x9>
+			<y9>322.6</y9>
+			<x10>307.6</x10>
+			<y10>333.09</y10>
+			<x11>321.21</x11>
+			<y11>291.14</y11>
+			<x12>314.27</x12>
+			<y12>283.37</y12>
+			<x13>320.66</x13>
+			<y13>264.2</y13>
+			<x14>318.2</x14>
+			<y14>259</y14>
+			<x15>318.99</x15>
+			<y15>233.37</y15>
+			<x16>287.3</x16>
+			<y16>231.1</y16>
+			<x17>282.88</x17>
+			<y17>263.37</y17>
+			<x18>303.99</x18>
+			<y18>265.59</y18>
+			<x19>301.21</x19>
+			<y19>277.26</y19>
+			<x20>295.1</x20>
+			<y20>279.48</y20>
+			<x21>248.16</x21>
+			<y21>262.54</y21>
+			<x22>255.1</x22>
+			<y22>241.98</y22>
+			<x23>248.16</x23>
+			<y23>236.98</y23>
+			<x24>249</x24>
+			<y24>227.3</y24>
+			<x25>214.6</x25>
+			<y25>223.8</y25>
+			<x26>214</x26>
+			<y26>258.8</y26>
+		</polygon>
+	</object>
+</annotation>

training/train/WIN_20221017_18_48_12_Pro_jpg.rf.aea23e817b46f38ede677defa9534b06.xml

@@ -0,0 +1,81 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_48_12_Pro_jpg.rf.aea23e817b46f38ede677defa9534b06.jpg</filename>
+	<path>WIN_20221017_18_48_12_Pro_jpg.rf.aea23e817b46f38ede677defa9534b06.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Incorrect_installation</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>320</xmin>
+			<xmax>435</xmax>
+			<ymin>131</ymin>
+			<ymax>257</ymax>
+		</bndbox>
+		<polygon>
+			<x1>426</x1>
+			<y1>221.2</y1>
+			<x2>420</x2>
+			<y2>220.6</y2>
+			<x3>433.5</x3>
+			<y3>181.91</y3>
+			<x4>389.34</x4>
+			<y4>166.36</y4>
+			<x5>391.9</x5>
+			<y5>153.9</y5>
+			<x6>396</x6>
+			<y6>153.2</y6>
+			<x7>398.1</x7>
+			<y7>132.1</y7>
+			<x8>366.8</x8>
+			<y8>129.9</y8>
+			<x9>364.5</x9>
+			<y9>157.4</y9>
+			<x10>332.4</x10>
+			<y10>146.91</y10>
+			<x11>318.79</x11>
+			<y11>188.86</y11>
+			<x12>325.73</x12>
+			<y12>196.63</y12>
+			<x13>319.34</x13>
+			<y13>215.8</y13>
+			<x14>321.8</x14>
+			<y14>221</y14>
+			<x15>321.01</x15>
+			<y15>246.63</y15>
+			<x16>352.7</x16>
+			<y16>248.9</y16>
+			<x17>357.12</x17>
+			<y17>216.63</y17>
+			<x18>336.01</x18>
+			<y18>214.41</y18>
+			<x19>338.79</x19>
+			<y19>202.74</y19>
+			<x20>344.9</x20>
+			<y20>200.52</y20>
+			<x21>391.84</x21>
+			<y21>217.46</y21>
+			<x22>384.9</x22>
+			<y22>238.02</y22>
+			<x23>391.84</x23>
+			<y23>243.02</y23>
+			<x24>391</x24>
+			<y24>252.7</y24>
+			<x25>425.4</x25>
+			<y25>256.2</y25>
+			<x26>426</x26>
+			<y26>221.2</y26>
+		</polygon>
+	</object>
+</annotation>

training/train/WIN_20221017_18_50_25_Pro_jpg.rf.7453d114331880fb6a9bc898fd3f9b22.xml

@@ -0,0 +1,117 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_50_25_Pro_jpg.rf.7453d114331880fb6a9bc898fd3f9b22.jpg</filename>
+	<path>WIN_20221017_18_50_25_Pro_jpg.rf.7453d114331880fb6a9bc898fd3f9b22.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Short_circuit</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>198</xmin>
+			<xmax>394</xmax>
+			<ymin>186</ymin>
+			<ymax>347</ymax>
+		</bndbox>
+		<polygon>
+			<x1>373.8</x1>
+			<y1>193.44</y1>
+			<x2>378.78</x2>
+			<y2>186.66</y2>
+			<x3>352.54</x3>
+			<y3>184.85</y3>
+			<x4>344.39</x4>
+			<y4>189.37</y4>
+			<x5>337.16</x5>
+			<y5>193.89</y5>
+			<x6>323.13</x6>
+			<y6>202.04</y6>
+			<x7>313.63</x7>
+			<y7>213.8</y7>
+			<x8>309.56</x8>
+			<y8>224.21</y8>
+			<x9>319.06</x9>
+			<y9>232.35</y9>
+			<x10>307.3</x10>
+			<y10>244.56</y10>
+			<x11>288.75</x11>
+			<y11>263.11</y11>
+			<x12>288.75</x12>
+			<y12>273.52</y12>
+			<x13>280.6</x13>
+			<y13>280.3</y13>
+			<x14>223.15</x14>
+			<y14>313.33</y14>
+			<x15>210.03</x15>
+			<y15>318.76</y15>
+			<x16>196.91</x16>
+			<y16>336.85</y16>
+			<x17>197.81</x17>
+			<y17>345.9</y17>
+			<x18>199.62</x18>
+			<y18>345.9</y18>
+			<x19>219.53</x19>
+			<y19>337.76</y19>
+			<x20>239.89</x20>
+			<y20>321.93</y20>
+			<x21>263.41</x21>
+			<y21>308.35</y21>
+			<x22>288.3</x22>
+			<y22>297.95</y22>
+			<x23>304.58</x23>
+			<y23>299.76</y23>
+			<x24>316.8</x24>
+			<y24>299.76</y24>
+			<x25>333.08</x25>
+			<y25>293.88</y25>
+			<x26>350.28</x26>
+			<y26>285.73</y26>
+			<x27>357.97</x27>
+			<y27>278.95</y27>
+			<x28>363.39</x28>
+			<y28>273.97</y28>
+			<x29>369.28</x29>
+			<y29>269.45</y29>
+			<x30>382.85</x30>
+			<y30>264.92</y30>
+			<x31>387.37</x31>
+			<y31>261.76</y31>
+			<x32>392.35</x32>
+			<y32>252.71</y32>
+			<x33>392.8</x33>
+			<y33>242.75</y33>
+			<x34>393.25</x34>
+			<y34>235.52</y34>
+			<x35>392.35</x35>
+			<y35>231.9</y35>
+			<x36>390.99</x36>
+			<y36>227.37</y36>
+			<x37>389.63</x37>
+			<y37>220.59</y37>
+			<x38>386.92</x38>
+			<y38>217.87</y38>
+			<x39>383.3</x39>
+			<y39>216.97</y39>
+			<x40>381.94</x40>
+			<y40>214.25</y40>
+			<x41>378.78</x41>
+			<y41>209.73</y41>
+			<x42>376.6</x42>
+			<y42>205.8</y42>
+			<x43>371.99</x43>
+			<y43>205.66</y43>
+			<x44>373.8</x44>
+			<y44>193.44</y44>
+		</polygon>
+	</object>
+</annotation>

training/train/WIN_20221017_18_50_25_Pro_jpg.rf.74b08bfb0e81909af021c5e33a1074c5.xml

@@ -0,0 +1,117 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_50_25_Pro_jpg.rf.74b08bfb0e81909af021c5e33a1074c5.jpg</filename>
+	<path>WIN_20221017_18_50_25_Pro_jpg.rf.74b08bfb0e81909af021c5e33a1074c5.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Short_circuit</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>248</xmin>
+			<xmax>444</xmax>
+			<ymin>135</ymin>
+			<ymax>296</ymax>
+		</bndbox>
+		<polygon>
+			<x1>266.2</x1>
+			<y1>286.56</y1>
+			<x2>261.22</x2>
+			<y2>293.34</y2>
+			<x3>287.46</x3>
+			<y3>295.15</y3>
+			<x4>295.61</x4>
+			<y4>290.63</y4>
+			<x5>302.84</x5>
+			<y5>286.11</y5>
+			<x6>316.87</x6>
+			<y6>277.96</y6>
+			<x7>326.37</x7>
+			<y7>266.2</y7>
+			<x8>330.44</x8>
+			<y8>255.79</y8>
+			<x9>320.94</x9>
+			<y9>247.65</y9>
+			<x10>332.7</x10>
+			<y10>235.44</y10>
+			<x11>351.25</x11>
+			<y11>216.89</y11>
+			<x12>351.25</x12>
+			<y12>206.48</y12>
+			<x13>359.4</x13>
+			<y13>199.7</y13>
+			<x14>416.85</x14>
+			<y14>166.67</y14>
+			<x15>429.97</x15>
+			<y15>161.24</y15>
+			<x16>443.09</x16>
+			<y16>143.15</y16>
+			<x17>442.19</x17>
+			<y17>134.1</y17>
+			<x18>440.38</x18>
+			<y18>134.1</y18>
+			<x19>420.47</x19>
+			<y19>142.24</y19>
+			<x20>400.11</x20>
+			<y20>158.07</y20>
+			<x21>376.59</x21>
+			<y21>171.65</y21>
+			<x22>351.7</x22>
+			<y22>182.05</y22>
+			<x23>335.42</x23>
+			<y23>180.24</y23>
+			<x24>323.2</x24>
+			<y24>180.24</y24>
+			<x25>306.92</x25>
+			<y25>186.12</y25>
+			<x26>289.72</x26>
+			<y26>194.27</y26>
+			<x27>282.03</x27>
+			<y27>201.05</y27>
+			<x28>276.61</x28>
+			<y28>206.03</y28>
+			<x29>270.72</x29>
+			<y29>210.55</y29>
+			<x30>257.15</x30>
+			<y30>215.08</y30>
+			<x31>252.63</x31>
+			<y31>218.24</y31>
+			<x32>247.65</x32>
+			<y32>227.29</y32>
+			<x33>247.2</x33>
+			<y33>237.25</y33>
+			<x34>246.75</x34>
+			<y34>244.48</y34>
+			<x35>247.65</x35>
+			<y35>248.1</y35>
+			<x36>249.01</x36>
+			<y36>252.63</y36>
+			<x37>250.37</x37>
+			<y37>259.41</y37>
+			<x38>253.08</x38>
+			<y38>262.13</y38>
+			<x39>256.7</x39>
+			<y39>263.03</y39>
+			<x40>258.06</x40>
+			<y40>265.75</y40>
+			<x41>261.22</x41>
+			<y41>270.27</y41>
+			<x42>263.4</x42>
+			<y42>274.2</y42>
+			<x43>268.01</x43>
+			<y43>274.34</y43>
+			<x44>266.2</x44>
+			<y44>286.56</y44>
+		</polygon>
+	</object>
+</annotation>

training/train/WIN_20221017_18_51_03_Pro_jpg.rf.778a411efb67a46622fb530a8d63f2a3.xml

@@ -0,0 +1,14 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_51_03_Pro_jpg.rf.778a411efb67a46622fb530a8d63f2a3.jpg</filename>
+	<path>WIN_20221017_18_51_03_Pro_jpg.rf.778a411efb67a46622fb530a8d63f2a3.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+</annotation>

training/train/WIN_20221017_18_51_03_Pro_jpg.rf.7be31d8b1cb485eeb5896d4dea17fe86.xml

@@ -0,0 +1,14 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_51_03_Pro_jpg.rf.7be31d8b1cb485eeb5896d4dea17fe86.jpg</filename>
+	<path>WIN_20221017_18_51_03_Pro_jpg.rf.7be31d8b1cb485eeb5896d4dea17fe86.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+</annotation>

training/train/WIN_20221017_18_53_01_Pro_jpg.rf.414cbf44c5148bb91fa5ab9fc1eaf418.xml

@@ -0,0 +1,47 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_53_01_Pro_jpg.rf.414cbf44c5148bb91fa5ab9fc1eaf418.jpg</filename>
+	<path>WIN_20221017_18_53_01_Pro_jpg.rf.414cbf44c5148bb91fa5ab9fc1eaf418.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Incorrect_installation</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>212</xmin>
+			<xmax>272</xmax>
+			<ymin>1</ymin>
+			<ymax>80</ymax>
+		</bndbox>
+		<polygon>
+			<x1>211.01</x1>
+			<y1>0</y1>
+			<x2>216.55</x2>
+			<y2>66.77</y2>
+			<x3>234.88</x3>
+			<y3>64.83</y3>
+			<x4>236</x4>
+			<y4>78.72</y4>
+			<x5>270.71</x5>
+			<y5>74</y5>
+			<x6>267.38</x6>
+			<y6>45.94</y6>
+			<x7>261.27</x7>
+			<y7>46.5</y7>
+			<x8>256.59</x8>
+			<y8>0</y8>
+			<x9>211.01</x9>
+			<y9>0</y9>
+		</polygon>
+	</object>
+</annotation>

training/train/WIN_20221017_18_53_01_Pro_jpg.rf.bdc4c3e8d5735c97bcf05d503cccae96.xml

@@ -0,0 +1,47 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_53_01_Pro_jpg.rf.bdc4c3e8d5735c97bcf05d503cccae96.jpg</filename>
+	<path>WIN_20221017_18_53_01_Pro_jpg.rf.bdc4c3e8d5735c97bcf05d503cccae96.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Incorrect_installation</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>81</xmin>
+			<xmax>160</xmax>
+			<ymin>290</ymin>
+			<ymax>350</ymax>
+		</bndbox>
+		<polygon>
+			<x1>126.5</x1>
+			<y1>298.73</y1>
+			<x2>80</x2>
+			<y2>303.41</y2>
+			<x3>80</x3>
+			<y3>348.99</y3>
+			<x4>146.77</x4>
+			<y4>343.45</y4>
+			<x5>144.83</x5>
+			<y5>325.12</y5>
+			<x6>158.72</x6>
+			<y6>324</y6>
+			<x7>154</x7>
+			<y7>289.29</y7>
+			<x8>125.94</x8>
+			<y8>292.62</y8>
+			<x9>126.5</x9>
+			<y9>298.73</y9>
+		</polygon>
+	</object>
+</annotation>

training/train/WIN_20221017_18_54_24_Pro_jpg.rf.602b991b286b5ac8a79d048efcaa77b5.xml

@@ -0,0 +1,51 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_54_24_Pro_jpg.rf.602b991b286b5ac8a79d048efcaa77b5.jpg</filename>
+	<path>WIN_20221017_18_54_24_Pro_jpg.rf.602b991b286b5ac8a79d048efcaa77b5.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Incorrect_installation</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>542</xmin>
+			<xmax>641</xmax>
+			<ymin>129</ymin>
+			<ymax>266</ymax>
+		</bndbox>
+		<polygon>
+			<x1>640</x1>
+			<y1>140.14</y1>
+			<x2>631.33</x2>
+			<y2>128.13</y2>
+			<x3>540.54</x3>
+			<y3>201.72</y3>
+			<x4>574.93</x4>
+			<y4>245.32</y4>
+			<x5>582.93</x5>
+			<y5>242.52</y5>
+			<x6>601.33</x6>
+			<y6>265.32</y6>
+			<x7>640</x7>
+			<y7>233.75</y7>
+			<x8>640</x8>
+			<y8>232.64</y8>
+			<x9>624.13</x9>
+			<y9>212.12</y9>
+			<x10>640</x10>
+			<y10>197.69</y10>
+			<x11>640</x11>
+			<y11>140.14</y11>
+		</polygon>
+	</object>
+</annotation>

training/train/WIN_20221017_18_54_24_Pro_jpg.rf.d2a6837579ced3fe3499ee7031dfb6cf.xml

@@ -0,0 +1,14 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_54_24_Pro_jpg.rf.d2a6837579ced3fe3499ee7031dfb6cf.jpg</filename>
+	<path>WIN_20221017_18_54_24_Pro_jpg.rf.d2a6837579ced3fe3499ee7031dfb6cf.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+</annotation>

training/train/WIN_20221017_18_56_15_Pro_jpg.rf.5561859c2847247027b6612ba5c94c27.xml

@@ -0,0 +1,107 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_56_15_Pro_jpg.rf.5561859c2847247027b6612ba5c94c27.jpg</filename>
+	<path>WIN_20221017_18_56_15_Pro_jpg.rf.5561859c2847247027b6612ba5c94c27.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Dry_joint</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>381</xmin>
+			<xmax>454</xmax>
+			<ymin>158</ymin>
+			<ymax>232</ymax>
+		</bndbox>
+		<polygon>
+			<x1>401.3</x1>
+			<y1>160.5</y1>
+			<x2>391.9</x2>
+			<y2>166.5</y2>
+			<x3>384.4</x3>
+			<y3>175</y3>
+			<x4>380.2</x4>
+			<y4>187.3</y4>
+			<x5>379.8</x5>
+			<y5>194.9</y5>
+			<x6>380.3</x6>
+			<y6>201</y6>
+			<x7>380.6</x7>
+			<y7>203.5</y7>
+			<x8>380.2</x8>
+			<y8>205.4</y8>
+			<x9>379.9</x9>
+			<y9>209</y9>
+			<x10>380.5</x10>
+			<y10>211</y10>
+			<x11>382.4</x11>
+			<y11>214.5</y11>
+			<x12>384.2</x12>
+			<y12>215.4</y12>
+			<x13>386.7</x13>
+			<y13>214.4</y13>
+			<x14>390.5</x14>
+			<y14>218.8</y14>
+			<x15>394.8</x15>
+			<y15>222.3</y15>
+			<x16>400.6</x16>
+			<y16>226.3</y16>
+			<x17>407.9</x17>
+			<y17>228.7</y17>
+			<x18>415.8</x18>
+			<y18>230.5</y18>
+			<x19>424</x19>
+			<y19>230.1</y19>
+			<x20>430.6</x20>
+			<y20>228</y20>
+			<x21>435.3</x21>
+			<y21>225.7</y21>
+			<x22>440.7</x22>
+			<y22>221.3</y22>
+			<x23>445.6</x23>
+			<y23>217.4</y23>
+			<x24>450.1</x24>
+			<y24>209</y24>
+			<x25>451.8</x25>
+			<y25>202.4</y25>
+			<x26>452.5</x26>
+			<y26>198.5</y26>
+			<x27>452.5</x27>
+			<y27>192.4</y27>
+			<x28>452.2</x28>
+			<y28>188.2</y28>
+			<x29>451.5</x29>
+			<y29>183.9</y29>
+			<x30>449.7</x30>
+			<y30>178.7</y30>
+			<x31>447.4</x31>
+			<y31>174.8</y31>
+			<x32>444.4</x32>
+			<y32>170</y32>
+			<x33>438.7</x33>
+			<y33>165.9</y33>
+			<x34>435.1</x34>
+			<y34>163.1</y34>
+			<x35>431.9</x35>
+			<y35>161.6</y35>
+			<x36>426.9</x36>
+			<y36>158.9</y36>
+			<x37>420.5</x37>
+			<y37>156.9</y37>
+			<x38>411.8</x38>
+			<y38>157.5</y38>
+			<x39>401.3</x39>
+			<y39>160.5</y39>
+		</polygon>
+	</object>
+</annotation>

training/train/WIN_20221017_18_56_15_Pro_jpg.rf.a928b7c33ce8e03eb54e66c4e8a4de67.xml

@@ -0,0 +1,107 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_56_15_Pro_jpg.rf.a928b7c33ce8e03eb54e66c4e8a4de67.jpg</filename>
+	<path>WIN_20221017_18_56_15_Pro_jpg.rf.a928b7c33ce8e03eb54e66c4e8a4de67.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Dry_joint</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>331</xmin>
+			<xmax>404</xmax>
+			<ymin>301</ymin>
+			<ymax>374</ymax>
+		</bndbox>
+		<polygon>
+			<x1>399.5</x1>
+			<y1>321.3</y1>
+			<x2>393.5</x2>
+			<y2>311.9</y2>
+			<x3>385</x3>
+			<y3>304.4</y3>
+			<x4>372.7</x4>
+			<y4>300.2</y4>
+			<x5>365.1</x5>
+			<y5>299.8</y5>
+			<x6>359</x6>
+			<y6>300.3</y6>
+			<x7>356.5</x7>
+			<y7>300.6</y7>
+			<x8>354.6</x8>
+			<y8>300.2</y8>
+			<x9>351</x9>
+			<y9>299.9</y9>
+			<x10>349</x10>
+			<y10>300.5</y10>
+			<x11>345.5</x11>
+			<y11>302.4</y11>
+			<x12>344.6</x12>
+			<y12>304.2</y12>
+			<x13>345.6</x13>
+			<y13>306.7</y13>
+			<x14>341.2</x14>
+			<y14>310.5</y14>
+			<x15>337.7</x15>
+			<y15>314.8</y15>
+			<x16>333.7</x16>
+			<y16>320.6</y16>
+			<x17>331.3</x17>
+			<y17>327.9</y17>
+			<x18>329.5</x18>
+			<y18>335.8</y18>
+			<x19>329.9</x19>
+			<y19>344</y19>
+			<x20>332</x20>
+			<y20>350.6</y20>
+			<x21>334.3</x21>
+			<y21>355.3</y21>
+			<x22>338.7</x22>
+			<y22>360.7</y22>
+			<x23>342.6</x23>
+			<y23>365.6</y23>
+			<x24>351</x24>
+			<y24>370.1</y24>
+			<x25>357.6</x25>
+			<y25>371.8</y25>
+			<x26>361.5</x26>
+			<y26>372.5</y26>
+			<x27>367.6</x27>
+			<y27>372.5</y27>
+			<x28>371.8</x28>
+			<y28>372.2</y28>
+			<x29>376.1</x29>
+			<y29>371.5</y29>
+			<x30>381.3</x30>
+			<y30>369.7</y30>
+			<x31>385.2</x31>
+			<y31>367.4</y31>
+			<x32>390</x32>
+			<y32>364.4</y32>
+			<x33>394.1</x33>
+			<y33>358.7</y33>
+			<x34>396.9</x34>
+			<y34>355.1</y34>
+			<x35>398.4</x35>
+			<y35>351.9</y35>
+			<x36>401.1</x36>
+			<y36>346.9</y36>
+			<x37>403.1</x37>
+			<y37>340.5</y37>
+			<x38>402.5</x38>
+			<y38>331.8</y38>
+			<x39>399.5</x39>
+			<y39>321.3</y39>
+		</polygon>
+	</object>
+</annotation>

training/train/WIN_20221017_18_57_55_Pro_jpg.rf.3f5b19bce389e97321f23c59e8d416d9.xml

@@ -0,0 +1,119 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_57_55_Pro_jpg.rf.3f5b19bce389e97321f23c59e8d416d9.jpg</filename>
+	<path>WIN_20221017_18_57_55_Pro_jpg.rf.3f5b19bce389e97321f23c59e8d416d9.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Short_circuit</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>252</xmin>
+			<xmax>335</xmax>
+			<ymin>143</ymin>
+			<ymax>223</ymax>
+		</bndbox>
+		<polygon>
+			<x1>295.9</x1>
+			<y1>141.6</y1>
+			<x2>289.7</x2>
+			<y2>144</y2>
+			<x3>284.5</x3>
+			<y3>150.3</y3>
+			<x4>288.5</x4>
+			<y4>156.5</y4>
+			<x5>296.6</x5>
+			<y5>166.4</y5>
+			<x6>296.6</x6>
+			<y6>170.3</y6>
+			<x7>292.4</x7>
+			<y7>176</y7>
+			<x8>288.3</x8>
+			<y8>179.7</y8>
+			<x9>282.2</x9>
+			<y9>179.7</y9>
+			<x10>276.1</x10>
+			<y10>177.3</y10>
+			<x11>263.3</x11>
+			<y11>174.4</y11>
+			<x12>259.8</x12>
+			<y12>174.4</y12>
+			<x13>255.9</x13>
+			<y13>177.3</y13>
+			<x14>254.6</x14>
+			<y14>178.1</y14>
+			<x15>250.9</x15>
+			<y15>181.6</y15>
+			<x16>250.5</x16>
+			<y16>184.4</y16>
+			<x17>251.6</x17>
+			<y17>186.4</y17>
+			<x18>251.6</x18>
+			<y18>191</y18>
+			<x19>252.2</x19>
+			<y19>196.8</y19>
+			<x20>255.3</x20>
+			<y20>200.1</y20>
+			<x21>259.2</x21>
+			<y21>201.4</y21>
+			<x22>264.4</x22>
+			<y22>201.4</y22>
+			<x23>267</x23>
+			<y23>203.6</y23>
+			<x24>270.7</x24>
+			<y24>206.6</y24>
+			<x25>279.3</x25>
+			<y25>211.8</y25>
+			<x26>288.9</x26>
+			<y26>222.1</y26>
+			<x27>299.8</x27>
+			<y27>211.8</y27>
+			<x28>297.9</x28>
+			<y28>209.5</y28>
+			<x29>291.4</x29>
+			<y29>201.7</y29>
+			<x30>285.3</x30>
+			<y30>195.3</y30>
+			<x31>285.3</x31>
+			<y31>193.3</y31>
+			<x32>286.2</x32>
+			<y32>193.1</y32>
+			<x33>288.8</x33>
+			<y33>192.2</y33>
+			<x34>294.8</x34>
+			<y34>190.7</y34>
+			<x35>298.8</x35>
+			<y35>186.6</y35>
+			<x36>302.4</x36>
+			<y36>185.3</y36>
+			<x37>304.9</x37>
+			<y37>184.8</y37>
+			<x38>307.3</x38>
+			<y38>183</y38>
+			<x39>308.9</x39>
+			<y39>179.8</y39>
+			<x40>310.7</x40>
+			<y40>179.5</y40>
+			<x41>314</x41>
+			<y41>181.1</y41>
+			<x42>316.6</x42>
+			<y42>184</y42>
+			<x43>323</x43>
+			<y43>190.7</y43>
+			<x44>333.9</x44>
+			<y44>180</y44>
+			<x45>295.9</x45>
+			<y45>141.6</y45>
+		</polygon>
+	</object>
+</annotation>

training/train/WIN_20221017_18_57_55_Pro_jpg.rf.cb158107d8ae6d05bd1b6276b42aec2e.xml

@@ -0,0 +1,119 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_57_55_Pro_jpg.rf.cb158107d8ae6d05bd1b6276b42aec2e.jpg</filename>
+	<path>WIN_20221017_18_57_55_Pro_jpg.rf.cb158107d8ae6d05bd1b6276b42aec2e.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Short_circuit</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>307</xmin>
+			<xmax>391</xmax>
+			<ymin>259</ymin>
+			<ymax>339</ymax>
+		</bndbox>
+		<polygon>
+			<x1>344.1</x1>
+			<y1>338.4</y1>
+			<x2>350.3</x2>
+			<y2>336</y2>
+			<x3>355.5</x3>
+			<y3>329.7</y3>
+			<x4>351.5</x4>
+			<y4>323.5</y4>
+			<x5>343.4</x5>
+			<y5>313.6</y5>
+			<x6>343.4</x6>
+			<y6>309.7</y6>
+			<x7>347.6</x7>
+			<y7>304</y7>
+			<x8>351.7</x8>
+			<y8>300.3</y8>
+			<x9>357.8</x9>
+			<y9>300.3</y9>
+			<x10>363.9</x10>
+			<y10>302.7</y10>
+			<x11>376.7</x11>
+			<y11>305.6</y11>
+			<x12>380.2</x12>
+			<y12>305.6</y12>
+			<x13>384.1</x13>
+			<y13>302.7</y13>
+			<x14>385.4</x14>
+			<y14>301.9</y14>
+			<x15>389.1</x15>
+			<y15>298.4</y15>
+			<x16>389.5</x16>
+			<y16>295.6</y16>
+			<x17>388.4</x17>
+			<y17>293.6</y17>
+			<x18>388.4</x18>
+			<y18>289</y18>
+			<x19>387.8</x19>
+			<y19>283.2</y19>
+			<x20>384.7</x20>
+			<y20>279.9</y20>
+			<x21>380.8</x21>
+			<y21>278.6</y21>
+			<x22>375.6</x22>
+			<y22>278.6</y22>
+			<x23>373</x23>
+			<y23>276.4</y23>
+			<x24>369.3</x24>
+			<y24>273.4</y24>
+			<x25>360.7</x25>
+			<y25>268.2</y25>
+			<x26>351.1</x26>
+			<y26>257.9</y26>
+			<x27>340.2</x27>
+			<y27>268.2</y27>
+			<x28>342.1</x28>
+			<y28>270.5</y28>
+			<x29>348.6</x29>
+			<y29>278.3</y29>
+			<x30>354.7</x30>
+			<y30>284.7</y30>
+			<x31>354.7</x31>
+			<y31>286.7</y31>
+			<x32>353.8</x32>
+			<y32>286.9</y32>
+			<x33>351.2</x33>
+			<y33>287.8</y33>
+			<x34>345.2</x34>
+			<y34>289.3</y34>
+			<x35>341.2</x35>
+			<y35>293.4</y35>
+			<x36>337.6</x36>
+			<y36>294.7</y36>
+			<x37>335.1</x37>
+			<y37>295.2</y37>
+			<x38>332.7</x38>
+			<y38>297</y38>
+			<x39>331.1</x39>
+			<y39>300.2</y39>
+			<x40>329.3</x40>
+			<y40>300.5</y40>
+			<x41>326</x41>
+			<y41>298.9</y41>
+			<x42>323.4</x42>
+			<y42>296</y42>
+			<x43>317</x43>
+			<y43>289.3</y43>
+			<x44>306.1</x44>
+			<y44>300</y44>
+			<x45>344.1</x45>
+			<y45>338.4</y45>
+		</polygon>
+	</object>
+</annotation>

training/train/WIN_20221017_18_57_55_Pro_jpg.rf.f93b9c99a8e2d1540f0dfb9f555c70d0.xml

@@ -0,0 +1,119 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_57_55_Pro_jpg.rf.f93b9c99a8e2d1540f0dfb9f555c70d0.jpg</filename>
+	<path>WIN_20221017_18_57_55_Pro_jpg.rf.f93b9c99a8e2d1540f0dfb9f555c70d0.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Short_circuit</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>223</xmin>
+			<xmax>303</xmax>
+			<ymin>227</ymin>
+			<ymax>311</ymax>
+		</bndbox>
+		<polygon>
+			<x1>221.6</x1>
+			<y1>264.1</y1>
+			<x2>224</x2>
+			<y2>270.3</y2>
+			<x3>230.3</x3>
+			<y3>275.5</y3>
+			<x4>236.5</x4>
+			<y4>271.5</y4>
+			<x5>246.4</x5>
+			<y5>263.4</y5>
+			<x6>250.3</x6>
+			<y6>263.4</y6>
+			<x7>256</x7>
+			<y7>267.6</y7>
+			<x8>259.7</x8>
+			<y8>271.7</y8>
+			<x9>259.7</x9>
+			<y9>277.8</y9>
+			<x10>257.3</x10>
+			<y10>283.9</y10>
+			<x11>254.4</x11>
+			<y11>296.7</y11>
+			<x12>254.4</x12>
+			<y12>300.2</y12>
+			<x13>257.3</x13>
+			<y13>304.1</y13>
+			<x14>258.1</x14>
+			<y14>305.4</y14>
+			<x15>261.6</x15>
+			<y15>309.1</y15>
+			<x16>264.4</x16>
+			<y16>309.5</y16>
+			<x17>266.4</x17>
+			<y17>308.4</y17>
+			<x18>271</x18>
+			<y18>308.4</y18>
+			<x19>276.8</x19>
+			<y19>307.8</y19>
+			<x20>280.1</x20>
+			<y20>304.7</y20>
+			<x21>281.4</x21>
+			<y21>300.8</y21>
+			<x22>281.4</x22>
+			<y22>295.6</y22>
+			<x23>283.6</x23>
+			<y23>293</y23>
+			<x24>286.6</x24>
+			<y24>289.3</y24>
+			<x25>291.8</x25>
+			<y25>280.7</y25>
+			<x26>302.1</x26>
+			<y26>271.1</y26>
+			<x27>291.8</x27>
+			<y27>260.2</y27>
+			<x28>289.5</x28>
+			<y28>262.1</y28>
+			<x29>281.7</x29>
+			<y29>268.6</y29>
+			<x30>275.3</x30>
+			<y30>274.7</y30>
+			<x31>273.3</x31>
+			<y31>274.7</y31>
+			<x32>273.1</x32>
+			<y32>273.8</y32>
+			<x33>272.2</x33>
+			<y33>271.2</y33>
+			<x34>270.7</x34>
+			<y34>265.2</y34>
+			<x35>266.6</x35>
+			<y35>261.2</y35>
+			<x36>265.3</x36>
+			<y36>257.6</y36>
+			<x37>264.8</x37>
+			<y37>255.1</y37>
+			<x38>263</x38>
+			<y38>252.7</y38>
+			<x39>259.8</x39>
+			<y39>251.1</y39>
+			<x40>259.5</x40>
+			<y40>249.3</y40>
+			<x41>261.1</x41>
+			<y41>246</y41>
+			<x42>264</x42>
+			<y42>243.4</y42>
+			<x43>270.7</x43>
+			<y43>237</y43>
+			<x44>260</x44>
+			<y44>226.1</y44>
+			<x45>221.6</x45>
+			<y45>264.1</y45>
+		</polygon>
+	</object>
+</annotation>

training/train/WIN_20221017_18_58_20_Pro_jpg.rf.0f432a0916e318aa3a6b08da08887641.xml

@@ -0,0 +1,316 @@
+<annotation>
+	<folder></folder>
+	<filename>WIN_20221017_18_58_20_Pro_jpg.rf.0f432a0916e318aa3a6b08da08887641.jpg</filename>
+	<path>WIN_20221017_18_58_20_Pro_jpg.rf.0f432a0916e318aa3a6b08da08887641.jpg</path>
+	<source>
+		<database>roboflow.ai</database>
+	</source>
+	<size>
+		<width>640</width>
+		<height>480</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Short_circuit</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>252</xmin>
+			<xmax>347</xmax>
+			<ymin>385</ymin>
+			<ymax>481</ymax>
+		</bndbox>
+		<polygon>
+			<x1>321.845046</x1>
+			<y1>480</y1>
+			<x2>324.32</x2>
+			<y2>478.94</y2>
+			<x3>327.6</x3>
+			<y3>474.21</y3>
+			<x4>329.41</x4>
+			<y4>472.21</y4>
+			<x5>326.5</x5>
+			<y5>467.85</y5>
+			<x6>326.5</x6>
+			<y6>460.94</y6>
+			<x7>326.32</x7>
+			<y7>453.85</y7>
+			<x8>325.23</x8>
+			<y8>450.76</y8>
+			<x9>325.05</x9>
+			<y9>446.03</y9>
+			<x10>326.14</x10>
+			<y10>440.58</y10>
+			<x11>330.32</x11>
+			<y11>442.4</y11>
+			<x12>335.41</x12>
+			<y12>442.58</y12>
+			<x13>340.87</x13>
+			<y13>441.49</y13>
+			<x14>342.5</x14>
+			<y14>434.76</y14>
+			<x15>346.14</x15>
+			<y15>429.12</y15>
+			<x16>346.14</x16>
+			<y16>425.67</y16>
+			<x17>345.78</x17>
+			<y17>423.49</y17>
+			<x18>340.69</x18>
+			<y18>419.49</y18>
+			<x19>336.5</x19>
+			<y19>416.76</y19>
+			<x20>333.05</x20>
+			<y20>414.94</y20>
+			<x21>329.78</x21>
+			<y21>414.21</y21>
+			<x22>324.87</x22>
+			<y22>413.49</y22>
+			<x23>320.87</x23>
+			<y23>411.67</y23>
+			<x24>319.41</x24>
+			<y24>408.21</y24>
+			<x25>317.05</x25>
+			<y25>404.58</y25>
+			<x26>312.32</x26>
+			<y26>400.76</y26>
+			<x27>307.96</x27>
+			<y27>396.76</y27>
+			<x28>303.41</x28>
+			<y28>392.58</y28>
+			<x29>298.87</x29>
+			<y29>386.4</y29>
+			<x30>293.41</x30>
+			<y30>384.22</y30>
+			<x31>283.41</x31>
+			<y31>393.31</y31>
+			<x32>290.69</x32>
+			<y32>400.03</y32>
+			<x33>292.51</x33>
+			<y33>401.67</y33>
+			<x34>294.69</x34>
+			<y34>406.58</y34>
+			<x35>296.14</x35>
+			<y35>411.12</y35>
+			<x36>297.96</x36>
+			<y36>412.94</y36>
+			<x37>297.6</x37>
+			<y37>417.85</y37>
+			<x38>298.32</x38>
+			<y38>422.21</y38>
+			<x39>298.87</x39>
+			<y39>424.21</y39>
+			<x40>292.69</x40>
+			<y40>428.94</y40>
+			<x41>288.69</x41>
+			<y41>428.76</y41>
+			<x42>285.6</x42>
+			<y42>435.85</y42>
+			<x43>283.6</x43>
+			<y43>438.58</y43>
+			<x44>278.51</x44>
+			<y44>435.3</y44>
+			<x45>274.32</x45>
+			<y45>430.4</y45>
+			<x46>260.87</x46>
+			<y46>417.49</y46>
+			<x47>251.05</x47>
+			<y47>426.58</y47>
+			<x48>255.96</x48>
+			<y48>432.21</y48>
+			<x49>259.42</x49>
+			<y49>436.21</y49>
+			<x50>259.96</x50>
+			<y50>439.3</y50>
+			<x51>267.05</x51>
+			<y51>446.76</y51>
+			<x52>271.78</x52>
+			<y52>450.03</y52>
+			<x53>272.69</x53>
+			<y53>453.12</y53>
+			<x54>275.78</x54>
+			<y54>456.76</y54>
+			<x55>279.05</x55>
+			<y55>457.67</y55>
+			<x56>280.69</x56>
+			<y56>458.03</y56>
+			<x57>280.69</x57>
+			<y57>460.94</y57>
+			<x58>278.51</x58>
+			<y58>463.67</y58>
+			<x59>275.96</x59>
+			<y59>463.49</y59>
+			<x60>286.87</x60>
+			<y60>475.85</y60>
+			<x61>292.87</x61>
+			<y61>478.03</y61>
+			<x62>296.51</x62>
+			<y62>478.76</y62>
+			<x63>299.05</x63>
+			<y63>478.76</y63>
+			<x64>303.6</x64>
+			<y64>477.3</y64>
+			<x65>305.41</x65>
+			<y65>475.67</y65>
+			<x66>310.14</x66>
+			<y66>477.85</y66>
+			<x67>316.116606</x67>
+			<y67>480</y67>
+			<x68>321.845046</x68>
+			<y68>480</y68>
+		</polygon>
+	</object>
+	<object>
+		<name>Short_circuit</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<occluded>0</occluded>
+		<bndbox>
+			<xmin>456</xmin>
+			<xmax>554</xmax>
+			<ymin>193</ymin>
+			<ymax>287</ymax>
+		</bndbox>
+		<polygon>
+			<x1>464.6</x1>
+			<y1>247.1</y1>
+			<x2>469.9</x2>
+			<y2>250.8</y2>
+			<x3>472.4</x3>
+			<y3>253.8</y3>
+			<x4>478.8</x4>
+			<y4>261.7</y4>
+			<x5>480.9</x5>
+			<y5>265</y5>
+			<x6>479.7</x6>
+			<y6>268.8</y6>
+			<x7>484.5</x7>
+			<y7>273.3</y7>
+			<x8>490.7</x8>
+			<y8>273.8</y8>
+			<x9>493.5</x9>
+			<y9>276.8</y9>
+			<x10>490.2</x10>
+			<y10>279</y10>
+			<x11>488.5</x11>
+			<y11>280.6</y11>
+			<x12>494</x12>
+			<y12>285.8</y12>
+			<x13>502.3</x13>
+			<y13>284.9</y13>
+			<x14>505.9</x14>
+			<y14>280.4</y14>
+			<x15>508.7</x15>
+			<y15>280.9</y15>
+			<x16>513.7</x16>
+			<y16>278</y16>
+			<x17>516</x17>
+			<y17>271.9</y17>
+			<x18>517.5</x18>
+			<y18>269.7</y18>
+			<x19>518.6</x19>
+			<y19>265</y19>
+			<x20>518.7</x20>
+			<y20>260.7</y20>
+			<x21>517.5</x21>
+			<y21>258.5</y21>
+			<x22>516.1</x22>
+			<y22>256.7</y22>
+			<x23>514.9</x23>
+			<y23>255.2</y23>
+			<x24>514.4</x24>
+			<y24>252.2</y24>
+			<x25>519.6</x25>
+			<y25>249.5</y25>
+			<x26>527.4</x26>
+			<y26>249.7</y26>
+			<x27>530.6</x27>
+			<y27>250.5</y27>
+			<x28>540.1</x28>
+			<y28>250.5</y28>
+			<x29>550</x29>
+			<y29>245.5</y29>
+			<x30>553.3</x30>
+			<y30>236.8</y30>
+			<x31>548.5</x31>
+			<y31>231.1</y31>
+			<x32>544.6</x32>
+			<y32>225.6</y32>
+			<x33>539.3</x33>
+			<y33>220.1</y33>
+			<x34>534.1</x34>
+			<y34>214.9</y34>
+			<x35>526.9</x35>
+			<y35>213.2</y35>
+			<x36>519.9</x36>
+			<y36>212.7</y36>
+			<x37>515.7</x37>
+			<y37>210.4</y37>
+			<x38>514.4</x38>
+			<y38>206.5</y38>
+			<x39>512.5</x39>
+			<y39>201.2</y39>
+			<x40>507</x40>
+			<y40>200.2</y40>
+			<x41>503</x41>
+			<y41>197.7</y41>
+			<x42>500</x42>
+			<y42>193.5</y42>
+			<x43>498.5</x43>
+			<y43>191.5</y43>
+			<x44>489.1</x44>
+			<y44>200.3</y44>
+			<x45>496.3</x45>
+			<y45>209</y45>
+			<x46>501.1</x46>
+			<y46>216.8</y46>
+			<x47>502.5</x47>
+			<y47>218.6</y47>
+			<x48>504.3</x48>
+			<y48>222.5</y48>
+			<x49>501.3</x49>
+			<y49>227.3</y49>
+			<x50>497.6</x50>
+			<y50>227.3</y50>
+			<x51>494.2</x51>
+			<y51>230.3</y51>
+			<x52>490.6</x52>
+			<y52>232.1</y52>
+			<x53>488.3</x53>
+			<y53>234</y53>
+			<x54>485.8</x54>
+			<y54>237.5</y54>
+			<x55>484</x55>
+			<y55>238.8</y55>
+			<x56>481.1</x56>
+			<y56>240.4</y56>
+			<x57>479</x57>
+			<y57>235.7</y57>
+			<x58>477.5</x58>
+			<y58>233</y58>
+			<x59>477.5</x59>
+			<y59>230</y59>
+			<x60>475.1</x60>
+			<y60>227.4</y60>
+			<x61>473.2</x61>
+			<y61>228.9</y61>
+			<x62>470.7</x62>
+			<y62>227.6</y62>
+			<x63>468.8</x63>
+			<y63>227.2</y63>
+			<x64>466.6</x64>
+			<y64>226.5</y64>
+			<x65>464.5</x65>
+			<y65>224.9</y65>
+			<x66>455</x66>
+			<y66>232.8</y66>
+			<x67>464.2</x67>
+			<y67>242.9</y67>
+			<x68>464.6</x68>
+			<y68>247.1</y68>
+		</polygon>
+	</object>
+</annotation>