Skip to content

2
2023-029
Commit 2053bb22 authored by janithGamage's avatar janithGamage
Browse files
Options

fix: update 

Desc: update project
parent 26f2107c
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 9693 additions and 4557 deletions
Project/Backend/ML_Models/Learning_Model/.gitignore 0 → 100644
View file @ 2053bb22
models/*
!models/
DataSet/Sn_sign_language_dataset/
Project/Backend/ML_Models/Learning_Model/.ipynb_checkpoints/API_Calculate_Similarity_Score-1-checkpoint.ipynb 0 → 100644
View file @ 2053bb22
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "f47e929b",
"metadata": {},
"outputs": [],
"source": [
"import nest_asyncio\n",
"import asyncio\n",
"import torch.nn.functional as F\n",
"import torch.nn as nn\n",
"import torchvision.transforms as transforms\n",
"import numpy as np\n",
"import io\n",
"import uvicorn\n",
"from fastapi import FastAPI, UploadFile\n",
"from PIL import Image\n",
"import torch"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "13b1d58b",
"metadata": {},
"outputs": [],
"source": [
"nest_asyncio.apply()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "35f4adc0",
"metadata": {},
"outputs": [],
"source": [
"app = FastAPI()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "a5aba4be",
"metadata": {},
"outputs": [],
"source": [
"transform = transforms.Compose([\n",
" transforms.Resize((300, 300)),\n",
" transforms.Grayscale(num_output_channels=1),\n",
" transforms.ToTensor(),\n",
" transforms.Normalize(mean=(0.5), std=(0.5))\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "11ec2fae",
"metadata": {},
"outputs": [],
"source": [
"class theCNN(nn.Module):\n",
" def __init__(self):\n",
" super(theCNN, self).__init__()\n",
" \n",
" self.conv01 = nn.Conv2d(\n",
" in_channels=1,\n",
" out_channels=10,\n",
" kernel_size=5,\n",
" stride=1,\n",
" padding=1\n",
" )\n",
" \n",
" self.conv02 = nn.Conv2d(\n",
" in_channels=10,\n",
" out_channels=20,\n",
" kernel_size=5,\n",
" stride=1,\n",
" padding=1\n",
" )\n",
" \n",
" expectedSize = int(np.floor((73 + 2 * 0 - 1) / 1) + 1)\n",
" expectedSize = 20 * int(expectedSize ** 2)\n",
" \n",
" self.fc01 = nn.Linear(expectedSize, 50)\n",
" self.output = nn.Linear(50, 16)\n",
"\n",
" def forward(self, x):\n",
" x = F.relu(F.max_pool2d(self.conv01(x), 2))\n",
" x = F.relu(F.max_pool2d(self.conv02(x), 2))\n",
" nUnits = x.shape.numel() / x.shape[0]\n",
" x = x.view(-1, int(nUnits))\n",
" x = F.relu(self.fc01(x))\n",
" return torch.softmax(self.output(x), axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "353a4725",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"theCNN(\n",
" (conv01): Conv2d(1, 10, kernel_size=(5, 5), stride=(1, 1), padding=(1, 1))\n",
" (conv02): Conv2d(10, 20, kernel_size=(5, 5), stride=(1, 1), padding=(1, 1))\n",
" (fc01): Linear(in_features=106580, out_features=50, bias=True)\n",
" (output): Linear(in_features=50, out_features=16, bias=True)\n",
")"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model = theCNN()\n",
"model.load_state_dict(torch.load(\"model.pth\"))\n",
"model.eval()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "bb87b7f0",
"metadata": {},
"outputs": [],
"source": [
"@app.post(\"/score\")\n",
"async def calculate_score(image_file: UploadFile):\n",
" image = Image.open(io.BytesIO(await image_file.read())).convert(\"L\")\n",
" image = transform(image).unsqueeze(0)\n",
"\n",
" with torch.no_grad():\n",
" output = model(image)\n",
"\n",
" probabilities = torch.softmax(output, dim=1)[0]\n",
" predicted_class = torch.argmax(probabilities).item()\n",
"\n",
" # Get the actual number corresponding to the hand sign\n",
" actual_number = get_actual_number_from_image(image)\n",
" \n",
" print(actual_number)\n",
"\n",
" # Compare predicted class with actual number and calculate correctness percentage\n",
" correct = int(predicted_class + 1 == actual_number)\n",
" print(correct)\n",
" correctness_percentage = correct / 1.0 * 100.0\n",
"\n",
" return {\"predicted_class\": predicted_class, \"correctness_percentage\": correctness_percentage}"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "05646e93",
"metadata": {},
"outputs": [],
"source": [
"import cv2\n",
"import numpy as np\n",
"\n",
"def get_actual_number_from_image(image):\n",
" # Convert the image to numpy array\n",
" image_array = np.array(image)\n",
"\n",
" # Apply image processing techniques to detect and recognize digits\n",
" # Example steps: thresholding, contour detection, character segmentation, digit recognition\n",
"\n",
" # Apply thresholding\n",
" _, binary_image = cv2.threshold(image_array, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)\n",
"\n",
" # Find contours\n",
" contours, _ = cv2.findContours(binary_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n",
"\n",
" # Sort contours based on their x-coordinate\n",
" contours = sorted(contours, key=lambda cnt: cv2.boundingRect(cnt)[0])\n",
"\n",
" # Initialize the recognized digit sequence\n",
" digit_sequence = \"\"\n",
"\n",
" # Iterate over the contours and recognize digits\n",
" for contour in contours:\n",
" # Get the bounding box of the contour\n",
" x, y, w, h = cv2.boundingRect(contour)\n",
"\n",
" # Crop the digit region from the image\n",
" digit_image = binary_image[y:y + h, x:x + w]\n",
"\n",
" # Resize the digit image to a fixed size (e.g., 28x28)\n",
" resized_digit_image = cv2.resize(digit_image, (28, 28))\n",
"\n",
" # Preprocess the resized digit image (e.g., normalize pixel values)\n",
" preprocessed_digit_image = resized_digit_image / 255.0\n",
"\n",
" # Flatten the preprocessed digit image\n",
" flattened_digit_image = preprocessed_digit_image.flatten()\n",
"\n",
" # Pass the flattened digit image to your digit recognition model\n",
" # to get the predicted digit (e.g., using a separate model or the same model you used for training)\n",
"\n",
" # Here, let's assume you have a function `predict_digit` that takes the flattened digit image\n",
" # and returns the predicted digit as an integer\n",
" predicted_digit = predict_digit(flattened_digit_image)\n",
"\n",
" # Add the predicted digit to the digit sequence\n",
" digit_sequence += str(predicted_digit)\n",
"\n",
" # Convert the digit sequence to an integer\n",
" actual_number = int(digit_sequence)\n",
"\n",
" return actual_number\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ee993fc1",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO: Started server process [36312]\n",
"INFO: Waiting for application startup.\n",
"INFO: Application startup complete.\n",
"INFO: Uvicorn running on http://127.0.0.1:8001 (Press CTRL+C to quit)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"5\n",
"0\n",
"INFO: 127.0.0.1:60625 - \"POST /score HTTP/1.1\" 200 OK\n"
]
}
],
"source": [
"if __name__ == \"__main__\":\n",
" loop = asyncio.get_event_loop()\n",
" loop.create_task(uvicorn.run(app, host=\"127.0.0.1\", port=8001))\n",
" loop.run_forever()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "34c5efea",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Project/Backend/ML_Models/Learning_Model/.ipynb_checkpoints/API_Calculate_Similarity_Score-2-checkpoint.ipynb 0 → 100644
View file @ 2053bb22
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "c898b57c",
"metadata": {},
"outputs": [],
"source": [
"pip install python-multipart"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "a99b4156",
"metadata": {},
"outputs": [],
"source": [
"import nest_asyncio\n",
"import asyncio\n",
"import torch.nn.functional as F\n",
"\n",
"# Apply the patch\n",
"nest_asyncio.apply()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "01b6e57c",
"metadata": {},
"outputs": [],
"source": [
"from fastapi import FastAPI, UploadFile\n",
"from PIL import Image\n",
"import torch\n",
"import torchvision.transforms as transforms\n",
"import numpy as np\n",
"import io\n",
"import torch.nn as nn\n",
"import asyncio\n",
"import uvicorn "
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "2e561f13",
"metadata": {},
"outputs": [],
"source": [
"app = FastAPI()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "1e9e4208",
"metadata": {},
"outputs": [],
"source": [
"transform = transforms.Compose([\n",
" transforms.Resize((300, 300)),\n",
" transforms.Grayscale(num_output_channels=1),\n",
" transforms.ToTensor(),\n",
" transforms.Normalize(mean=(0.5), std=(0.5))\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "4d86d2b8",
"metadata": {},
"outputs": [],
"source": [
"class theCNN(nn.Module):\n",
" def __init__(self):\n",
" super(theCNN, self).__init__()\n",
" \n",
" self.conv01 = nn.Conv2d(\n",
" in_channels=1,\n",
" out_channels=10,\n",
" kernel_size=5,\n",
" stride=1,\n",
" padding=1\n",
" )\n",
" \n",
" self.conv02 = nn.Conv2d(\n",
" in_channels=10,\n",
" out_channels=20,\n",
" kernel_size=5,\n",
" stride=1,\n",
" padding=1\n",
" )\n",
" \n",
" expectedSize = int(np.floor((73 + 2 * 0 - 1) / 1) + 1)\n",
" expectedSize = 20 * int(expectedSize ** 2)\n",
" \n",
" self.fc01 = nn.Linear(expectedSize, 50)\n",
" self.output = nn.Linear(50, 16)\n",
"\n",
" def forward(self, x):\n",
" x = F.relu(F.max_pool2d(self.conv01(x), 2))\n",
" x = F.relu(F.max_pool2d(self.conv02(x), 2))\n",
" nUnits = x.shape.numel() / x.shape[0]\n",
" x = x.view(-1, int(nUnits))\n",
" x = F.relu(self.fc01(x))\n",
" return torch.softmax(self.output(x), axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "9379bf73",
"metadata": {},
"outputs": [
{
"ename": "TypeError",
"evalue": "Expected state_dict to be dict-like, got <class '__main__.theCNN'>.",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[6], line 2\u001b[0m\n\u001b[0;32m 1\u001b[0m model \u001b[38;5;241m=\u001b[39m theCNN()\n\u001b[1;32m----> 2\u001b[0m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload_state_dict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodel1.pth\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 3\u001b[0m model\u001b[38;5;241m.\u001b[39meval()\n",
"File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python310\\site-packages\\torch\\nn\\modules\\module.py:1994\u001b[0m, in \u001b[0;36mModule.load_state_dict\u001b[1;34m(self, state_dict, strict)\u001b[0m\n\u001b[0;32m 1971\u001b[0m \u001b[38;5;124mr\u001b[39m\u001b[38;5;124;03m\"\"\"Copies parameters and buffers from :attr:`state_dict` into\u001b[39;00m\n\u001b[0;32m 1972\u001b[0m \u001b[38;5;124;03mthis module and its descendants. If :attr:`strict` is ``True``, then\u001b[39;00m\n\u001b[0;32m 1973\u001b[0m \u001b[38;5;124;03mthe keys of :attr:`state_dict` must exactly match the keys returned\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 1991\u001b[0m \u001b[38;5;124;03m ``RuntimeError``.\u001b[39;00m\n\u001b[0;32m 1992\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 1993\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(state_dict, Mapping):\n\u001b[1;32m-> 1994\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mExpected state_dict to be dict-like, got \u001b[39m\u001b[38;5;132;01m{}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mformat(\u001b[38;5;28mtype\u001b[39m(state_dict)))\n\u001b[0;32m 1996\u001b[0m missing_keys: List[\u001b[38;5;28mstr\u001b[39m] \u001b[38;5;241m=\u001b[39m []\n\u001b[0;32m 1997\u001b[0m unexpected_keys: List[\u001b[38;5;28mstr\u001b[39m] \u001b[38;5;241m=\u001b[39m []\n",
"\u001b[1;31mTypeError\u001b[0m: Expected state_dict to be dict-like, got <class '__main__.theCNN'>."
]
}
],
"source": [
"model = theCNN()\n",
"model.load_state_dict(torch.load(\"model.pth\"))\n",
"model.eval()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "18b869d3",
"metadata": {},
"outputs": [],
"source": [
"@app.post(\"/score\")\n",
"async def calculate_score(image_file: UploadFile):\n",
" image = Image.open(io.BytesIO(await image_file.read())).convert(\"L\")\n",
" image = transform(image).unsqueeze(0)\n",
"\n",
" with torch.no_grad():\n",
" output = model(image)\n",
"\n",
" probabilities = torch.softmax(output, dim=1)[0]\n",
" similarity_scores = probabilities.numpy()\n",
"\n",
" return {\"similarity_scores\": similarity_scores.tolist()}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4a99a8b6",
"metadata": {},
"outputs": [],
"source": [
"@app.get(\"/\")\n",
"async def hello_world(): \n",
"\n",
" return {\"Hello World\"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7b30f5c6",
"metadata": {},
"outputs": [],
"source": [
"if __name__ == \"__main__\":\n",
" loop = asyncio.get_event_loop()\n",
" loop.create_task(uvicorn.run(app, host=\"127.0.0.1\", port=8001))\n",
" loop.run_forever()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3e2e07d8",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Project/Backend/ML_Models/Learning_Model/.ipynb_checkpoints/API_Calculate_Similarity_Score-3-checkpoint.ipynb 0 → 100644
View file @ 2053bb22
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "60c58fd2",
"metadata": {},
"outputs": [],
"source": [
"import nest_asyncio\n",
"import asyncio\n",
"import torch.nn.functional as F\n",
"\n",
"# Apply the patch\n",
"nest_asyncio.apply()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "c1b7af91",
"metadata": {},
"outputs": [],
"source": [
"from fastapi import FastAPI, UploadFile\n",
"from PIL import Image\n",
"import torch\n",
"import torchvision.transforms as transforms\n",
"import numpy as np\n",
"import io\n",
"import torch.nn as nn\n",
"import asyncio\n",
"import uvicorn \n",
"from io import BytesIO"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "7f1cd8a4",
"metadata": {},
"outputs": [],
"source": [
"app = FastAPI()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "2035acf5",
"metadata": {},
"outputs": [],
"source": [
"transform = transforms.Compose([\n",
" transforms.Resize((300, 300)),\n",
" transforms.Grayscale(num_output_channels=1),\n",
" transforms.ToTensor(),\n",
" transforms.Normalize(mean=(0.5), std=(0.5))\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "2cfca47d",
"metadata": {},
"outputs": [],
"source": [
"class theCNN(nn.Module):\n",
" def __init__(self):\n",
" super(theCNN, self).__init__()\n",
" \n",
" self.conv01 = nn.Conv2d(\n",
" in_channels=1,\n",
" out_channels=10,\n",
" kernel_size=5,\n",
" stride=1,\n",
" padding=1\n",
" )\n",
" \n",
" self.conv02 = nn.Conv2d(\n",
" in_channels=10,\n",
" out_channels=20,\n",
" kernel_size=5,\n",
" stride=1,\n",
" padding=1\n",
" )\n",
" \n",
" expectedSize = int(np.floor((73 + 2 * 0 - 1) / 1) + 1)\n",
" expectedSize = 20 * int(expectedSize ** 2)\n",
" \n",
" self.fc01 = nn.Linear(expectedSize, 50)\n",
" self.output = nn.Linear(50, 16)\n",
"\n",
" def forward(self, x):\n",
" x = F.relu(F.max_pool2d(self.conv01(x), 2))\n",
" x = F.relu(F.max_pool2d(self.conv02(x), 2))\n",
" nUnits = x.shape.numel() / x.shape[0]\n",
" x = x.view(-1, int(nUnits))\n",
" x = F.relu(self.fc01(x))\n",
" return torch.softmax(self.output(x), axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "2786c4df",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"theCNN(\n",
" (conv01): Conv2d(1, 10, kernel_size=(5, 5), stride=(1, 1), padding=(1, 1))\n",
" (conv02): Conv2d(10, 20, kernel_size=(5, 5), stride=(1, 1), padding=(1, 1))\n",
" (fc01): Linear(in_features=106580, out_features=50, bias=True)\n",
" (output): Linear(in_features=50, out_features=16, bias=True)\n",
")"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model = theCNN()\n",
"model.load_state_dict(torch.load(\"model.pth\"))\n",
"model.eval()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "30569105",
"metadata": {},
"outputs": [],
"source": [
"# @app.post(\"/predict-similarity\")\n",
"# async def predict_similarity(image: UploadFile):\n",
"# image_bytes = await image.read()\n",
"# img = Image.open(BytesIO(image_bytes))\n",
"# img = transform(img).unsqueeze(0)\n",
"# output = model(img)\n",
"# similarity_score = torch.max(output).item() * 100 # Get the maximum predicted probability as the similarity score\n",
"# return {\"similarity_score\": similarity_score}\n",
"\n",
"\n",
"@app.post(\"/predict-similarity\")\n",
"async def predict_similarity(sign: str, image: UploadFile):\n",
" image_bytes = await image.read()\n",
" img = Image.open(BytesIO(image_bytes))\n",
" img = transform(img).unsqueeze(0)\n",
" output = model(img)\n",
" similarity_score = torch.max(output).item() * 100 # Get the maximum predicted probability as the similarity score\n",
" return {\"sign\": sign, \"similarity_score\": similarity_score}"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "5c19e31c",
"metadata": {},
"outputs": [],
"source": [
"@app.get(\"/\")\n",
"async def hello_world(): \n",
"\n",
" return {\"Hello World\"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bea39dc9",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO: Started server process [36440]\n",
"INFO: Waiting for application startup.\n",
"INFO: Application startup complete.\n",
"INFO: Uvicorn running on http://127.0.0.1:8001 (Press CTRL+C to quit)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"INFO: 127.0.0.1:63408 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n",
"INFO: 127.0.0.1:63440 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n",
"INFO: 127.0.0.1:63461 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n",
"INFO: 127.0.0.1:63484 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n"
]
}
],
"source": [
"if __name__ == \"__main__\":\n",
" loop = asyncio.get_event_loop()\n",
" loop.create_task(uvicorn.run(app, host=\"127.0.0.1\", port=8001))\n",
" loop.run_forever()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "52ede8b7",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "3d7bb1db",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Project/Backend/ML_Models/Learning_Model/API_Calculate_Similarity_Score-1.ipynb 0 → 100644
View file @ 2053bb22
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "49b49c05",
"metadata": {},
"outputs": [],
"source": [
"import nest_asyncio\n",
"import asyncio\n",
"import torch.nn.functional as F\n",
"import torch.nn as nn\n",
"import torchvision.transforms as transforms\n",
"import numpy as np\n",
"import io\n",
"import uvicorn\n",
"from fastapi import FastAPI, UploadFile\n",
"from PIL import Image\n",
"import torch"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3f0148a4",
"metadata": {},
"outputs": [],
"source": [
"nest_asyncio.apply()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "26e5f198",
"metadata": {},
"outputs": [],
"source": [
"app = FastAPI()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d4359663",
"metadata": {},
"outputs": [],
"source": [
"transform = transforms.Compose([\n",
" transforms.Resize((300, 300)),\n",
" transforms.Grayscale(num_output_channels=1),\n",
" transforms.ToTensor(),\n",
" transforms.Normalize(mean=(0.5), std=(0.5))\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "308a25d3",
"metadata": {},
"outputs": [],
"source": [
"class theCNN(nn.Module):\n",
" def __init__(self):\n",
" super(theCNN, self).__init__()\n",
" \n",
" self.conv01 = nn.Conv2d(\n",
" in_channels=1,\n",
" out_channels=10,\n",
" kernel_size=5,\n",
" stride=1,\n",
" padding=1\n",
" )\n",
" \n",
" self.conv02 = nn.Conv2d(\n",
" in_channels=10,\n",
" out_channels=20,\n",
" kernel_size=5,\n",
" stride=1,\n",
" padding=1\n",
" )\n",
" \n",
" expectedSize = int(np.floor((73 + 2 * 0 - 1) / 1) + 1)\n",
" expectedSize = 20 * int(expectedSize ** 2)\n",
" \n",
" self.fc01 = nn.Linear(expectedSize, 50)\n",
" self.output = nn.Linear(50, 16)\n",
"\n",
" def forward(self, x):\n",
" x = F.relu(F.max_pool2d(self.conv01(x), 2))\n",
" x = F.relu(F.max_pool2d(self.conv02(x), 2))\n",
" nUnits = x.shape.numel() / x.shape[0]\n",
" x = x.view(-1, int(nUnits))\n",
" x = F.relu(self.fc01(x))\n",
" return torch.softmax(self.output(x), axis=1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4e3544d2",
"metadata": {},
"outputs": [],
"source": [
"model = theCNN()\n",
"model.load_state_dict(torch.load(\"model.pth\"))\n",
"model.eval()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d521a8ca",
"metadata": {},
"outputs": [],
"source": [
"@app.post(\"/score\")\n",
"async def calculate_score(image_file: UploadFile):\n",
" image = Image.open(io.BytesIO(await image_file.read())).convert(\"L\")\n",
" image = transform(image).unsqueeze(0)\n",
"\n",
" with torch.no_grad():\n",
" output = model(image)\n",
"\n",
" probabilities = torch.softmax(output, dim=1)[0]\n",
" predicted_class = torch.argmax(probabilities).item()\n",
"\n",
" # Get the actual number corresponding to the hand sign\n",
" actual_number = get_actual_number_from_image(image)\n",
" \n",
" print(actual_number)\n",
"\n",
" # Compare predicted class with actual number and calculate correctness percentage\n",
" correct = int(predicted_class + 1 == actual_number)\n",
" print(correct)\n",
" correctness_percentage = correct / 1.0 * 100.0\n",
"\n",
" return {\"predicted_class\": predicted_class, \"correctness_percentage\": correctness_percentage}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "030c5fbc",
"metadata": {},
"outputs": [],
"source": [
"import cv2\n",
"import numpy as np\n",
"\n",
"def get_actual_number_from_image(image):\n",
" # Convert the image to numpy array\n",
" image_array = np.array(image)\n",
"\n",
" # Apply image processing techniques to detect and recognize digits\n",
" # Example steps: thresholding, contour detection, character segmentation, digit recognition\n",
"\n",
" # Apply thresholding\n",
" _, binary_image = cv2.threshold(image_array, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)\n",
"\n",
" # Find contours\n",
" contours, _ = cv2.findContours(binary_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n",
"\n",
" # Sort contours based on their x-coordinate\n",
" contours = sorted(contours, key=lambda cnt: cv2.boundingRect(cnt)[0])\n",
"\n",
" # Initialize the recognized digit sequence\n",
" digit_sequence = \"\"\n",
"\n",
" # Iterate over the contours and recognize digits\n",
" for contour in contours:\n",
" # Get the bounding box of the contour\n",
" x, y, w, h = cv2.boundingRect(contour)\n",
"\n",
" # Crop the digit region from the image\n",
" digit_image = binary_image[y:y + h, x:x + w]\n",
"\n",
" # Resize the digit image to a fixed size (e.g., 28x28)\n",
" resized_digit_image = cv2.resize(digit_image, (28, 28))\n",
"\n",
" # Preprocess the resized digit image (e.g., normalize pixel values)\n",
" preprocessed_digit_image = resized_digit_image / 255.0\n",
"\n",
" # Flatten the preprocessed digit image\n",
" flattened_digit_image = preprocessed_digit_image.flatten()\n",
"\n",
" # Pass the flattened digit image to your digit recognition model\n",
" # to get the predicted digit (e.g., using a separate model or the same model you used for training)\n",
"\n",
" # Here, let's assume you have a function `predict_digit` that takes the flattened digit image\n",
" # and returns the predicted digit as an integer\n",
" predicted_digit = predict_digit(flattened_digit_image)\n",
"\n",
" # Add the predicted digit to the digit sequence\n",
" digit_sequence += str(predicted_digit)\n",
"\n",
" # Convert the digit sequence to an integer\n",
" actual_number = int(digit_sequence)\n",
"\n",
" return actual_number\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5035c79a",
"metadata": {},
"outputs": [],
"source": [
"if __name__ == \"__main__\":\n",
" loop = asyncio.get_event_loop()\n",
" loop.create_task(uvicorn.run(app, host=\"127.0.0.1\", port=8001))\n",
" loop.run_forever()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c0449757",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Project/Backend/ML_Models/Learning_Model/API_Calculate_Similarity_Score-2.ipynb 0 → 100644
View file @ 2053bb22
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "c898b57c",
"metadata": {},
"outputs": [],
"source": [
"pip install python-multipart"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a99b4156",
"metadata": {},
"outputs": [],
"source": [
"import nest_asyncio\n",
"import asyncio\n",
"import torch.nn.functional as F\n",
"\n",
"# Apply the patch\n",
"nest_asyncio.apply()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "01b6e57c",
"metadata": {},
"outputs": [],
"source": [
"from fastapi import FastAPI, UploadFile\n",
"from PIL import Image\n",
"import torch\n",
"import torchvision.transforms as transforms\n",
"import numpy as np\n",
"import io\n",
"import torch.nn as nn\n",
"import asyncio\n",
"import uvicorn "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2e561f13",
"metadata": {},
"outputs": [],
"source": [
"app = FastAPI()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1e9e4208",
"metadata": {},
"outputs": [],
"source": [
"transform = transforms.Compose([\n",
" transforms.Resize((300, 300)),\n",
" transforms.Grayscale(num_output_channels=1),\n",
" transforms.ToTensor(),\n",
" transforms.Normalize(mean=(0.5), std=(0.5))\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4d86d2b8",
"metadata": {},
"outputs": [],
"source": [
"class theCNN(nn.Module):\n",
" def __init__(self):\n",
" super(theCNN, self).__init__()\n",
" \n",
" self.conv01 = nn.Conv2d(\n",
" in_channels=1,\n",
" out_channels=10,\n",
" kernel_size=5,\n",
" stride=1,\n",
" padding=1\n",
" )\n",
" \n",
" self.conv02 = nn.Conv2d(\n",
" in_channels=10,\n",
" out_channels=20,\n",
" kernel_size=5,\n",
" stride=1,\n",
" padding=1\n",
" )\n",
" \n",
" expectedSize = int(np.floor((73 + 2 * 0 - 1) / 1) + 1)\n",
" expectedSize = 20 * int(expectedSize ** 2)\n",
" \n",
" self.fc01 = nn.Linear(expectedSize, 50)\n",
" self.output = nn.Linear(50, 16)\n",
"\n",
" def forward(self, x):\n",
" x = F.relu(F.max_pool2d(self.conv01(x), 2))\n",
" x = F.relu(F.max_pool2d(self.conv02(x), 2))\n",
" nUnits = x.shape.numel() / x.shape[0]\n",
" x = x.view(-1, int(nUnits))\n",
" x = F.relu(self.fc01(x))\n",
" return torch.softmax(self.output(x), axis=1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9379bf73",
"metadata": {},
"outputs": [],
"source": [
"model = theCNN()\n",
"model.load_state_dict(torch.load(\"model.pth\"))\n",
"model.eval()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "18b869d3",
"metadata": {},
"outputs": [],
"source": [
"@app.post(\"/score\")\n",
"async def calculate_score(image_file: UploadFile):\n",
" image = Image.open(io.BytesIO(await image_file.read())).convert(\"L\")\n",
" image = transform(image).unsqueeze(0)\n",
"\n",
" with torch.no_grad():\n",
" output = model(image)\n",
"\n",
" probabilities = torch.softmax(output, dim=1)[0]\n",
" similarity_scores = probabilities.numpy()\n",
"\n",
" return {\"similarity_scores\": similarity_scores.tolist()}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4a99a8b6",
"metadata": {},
"outputs": [],
"source": [
"@app.get(\"/\")\n",
"async def hello_world(): \n",
"\n",
" return {\"Hello World\"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7b30f5c6",
"metadata": {},
"outputs": [],
"source": [
"if __name__ == \"__main__\":\n",
" loop = asyncio.get_event_loop()\n",
" loop.create_task(uvicorn.run(app, host=\"127.0.0.1\", port=8001))\n",
" loop.run_forever()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3e2e07d8",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Project/Backend/ML_Models/Learning_Model/API_Calculate_Similarity_Score-3.ipynb 0 → 100644
View file @ 2053bb22
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "3d735e52",
"metadata": {},
"outputs": [],
"source": [
"import nest_asyncio\n",
"import asyncio\n",
"import torch.nn.functional as F\n",
"\n",
"# Apply the patch\n",
"nest_asyncio.apply()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "db756418",
"metadata": {},
"outputs": [],
"source": [
"from fastapi import FastAPI, UploadFile\n",
"from PIL import Image\n",
"import torch\n",
"import torchvision.transforms as transforms\n",
"import numpy as np\n",
"import io\n",
"import torch.nn as nn\n",
"import asyncio\n",
"import uvicorn \n",
"from io import BytesIO"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "fc83d1b8",
"metadata": {},
"outputs": [],
"source": [
"app = FastAPI()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "63dbfc01",
"metadata": {},
"outputs": [],
"source": [
"transform = transforms.Compose([\n",
" transforms.Resize((300, 300)),\n",
" transforms.Grayscale(num_output_channels=1),\n",
" transforms.ToTensor(),\n",
" transforms.Normalize(mean=(0.5), std=(0.5))\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "f7e5cdba",
"metadata": {},
"outputs": [],
"source": [
"class theCNN(nn.Module):\n",
" def __init__(self):\n",
" super(theCNN, self).__init__()\n",
" \n",
" self.conv01 = nn.Conv2d(\n",
" in_channels=1,\n",
" out_channels=10,\n",
" kernel_size=5,\n",
" stride=1,\n",
" padding=1\n",
" )\n",
" \n",
" self.conv02 = nn.Conv2d(\n",
" in_channels=10,\n",
" out_channels=20,\n",
" kernel_size=5,\n",
" stride=1,\n",
" padding=1\n",
" )\n",
" \n",
" expectedSize = int(np.floor((73 + 2 * 0 - 1) / 1) + 1)\n",
" expectedSize = 20 * int(expectedSize ** 2)\n",
" \n",
" self.fc01 = nn.Linear(expectedSize, 50)\n",
" self.output = nn.Linear(50, 16)\n",
"\n",
" def forward(self, x):\n",
" x = F.relu(F.max_pool2d(self.conv01(x), 2))\n",
" x = F.relu(F.max_pool2d(self.conv02(x), 2))\n",
" nUnits = x.shape.numel() / x.shape[0]\n",
" x = x.view(-1, int(nUnits))\n",
" x = F.relu(self.fc01(x))\n",
" return torch.softmax(self.output(x), axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "d86a9515",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"theCNN(\n",
" (conv01): Conv2d(1, 10, kernel_size=(5, 5), stride=(1, 1), padding=(1, 1))\n",
" (conv02): Conv2d(10, 20, kernel_size=(5, 5), stride=(1, 1), padding=(1, 1))\n",
" (fc01): Linear(in_features=106580, out_features=50, bias=True)\n",
" (output): Linear(in_features=50, out_features=16, bias=True)\n",
")"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model = theCNN()\n",
"model.load_state_dict(torch.load(\"model.pth\"))\n",
"model.eval()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "4b527135",
"metadata": {},
"outputs": [],
"source": [
"# @app.post(\"/predict-similarity\")\n",
"# async def predict_similarity(image: UploadFile):\n",
"# image_bytes = await image.read()\n",
"# img = Image.open(BytesIO(image_bytes))\n",
"# img = transform(img).unsqueeze(0)\n",
"# output = model(img)\n",
"# similarity_score = torch.max(output).item() * 100 # Get the maximum predicted probability as the similarity score\n",
"# return {\"similarity_score\": similarity_score}\n",
"\n",
"\n",
"@app.post(\"/predict-similarity\")\n",
"async def predict_similarity(sign: str, image: UploadFile):\n",
" image_bytes = await image.read()\n",
" img = Image.open(BytesIO(image_bytes))\n",
" img = transform(img).unsqueeze(0)\n",
" output = model(img)\n",
" similarity_score = torch.max(output).item() * 100 # Get the maximum predicted probability as the similarity score\n",
" return {\"sign\": sign, \"similarity_score\": similarity_score}"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "df08611e",
"metadata": {},
"outputs": [],
"source": [
"@app.get(\"/\")\n",
"async def hello_world(): \n",
"\n",
" return {\"Hello World\"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "84b9601b",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO: Started server process [36440]\n",
"INFO: Waiting for application startup.\n",
"INFO: Application startup complete.\n",
"INFO: Uvicorn running on http://127.0.0.1:8001 (Press CTRL+C to quit)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"INFO: 127.0.0.1:63408 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n",
"INFO: 127.0.0.1:63440 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n",
"INFO: 127.0.0.1:63461 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n",
"INFO: 127.0.0.1:63484 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n",
"INFO: 127.0.0.1:63502 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n",
"INFO: 127.0.0.1:63517 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n",
"INFO: 127.0.0.1:63523 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n",
"INFO: 127.0.0.1:63536 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n",
"INFO: 127.0.0.1:63536 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n",
"INFO: 127.0.0.1:63536 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n",
"INFO: 127.0.0.1:63546 - \"POST /predict-similarity HTTP/1.1\" 422 Unprocessable Entity\n"
]
}
],
"source": [
"if __name__ == \"__main__\":\n",
" loop = asyncio.get_event_loop()\n",
" loop.create_task(uvicorn.run(app, host=\"127.0.0.1\", port=8001))\n",
" loop.run_forever()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ab358400",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "504cf81d",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Project/Frontend/Web_App/yarn.lock
View file @ 2053bb22
This diff is collapsed.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment