{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import torch\n",
    "from onnx2pytorch import ConvertModel\n",
    "from keras.models import load_model\n",
    "import onnx"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Metal device set to: Apple M1\n",
      "\n",
      "systemMemory: 8.00 GB\n",
      "maxCacheSize: 2.67 GB\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2024-02-01 19:38:26.414359: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:305] Could not identify NUMA node of platform GPU ID 0, defaulting to 0. Your kernel may not have been built with NUMA support.\n",
      "2024-02-01 19:38:26.414541: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:271] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 0 MB memory) -> physical PluggableDevice (device: 0, name: METAL, pci bus id: <undefined>)\n"
     ]
    }
   ],
   "source": [
    "\n",
    "model1 = load_model('/Users/jarvis/pymycod/Deepfakes/DeepDetect/mesonet_trained.hdf5')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 0s 198ms/step\n",
      "the image is realllll boii\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2024-02-01 14:03:47.045296: W tensorflow/core/platform/profile_utils/cpu_utils.cc:128] Failed to get CPU frequency: 0 Hz\n",
      "2024-02-01 14:03:47.118034: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:113] Plugin optimizer for device_type GPU is enabled.\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import keras.utils as image\n",
    "\n",
    "img_width, img_height = 256,256\n",
    "img = image.load_img(f'/Users/jarvis/Downloads/im6.jpeg', target_size = (img_width, img_height))\n",
    "img = image.img_to_array(img)\n",
    "img = np.expand_dims(img, axis = 0)\n",
    "ans = model1.predict(img)\n",
    "if ans[0] ==0:\n",
    "    print(\"the image is fake afff\")\n",
    "else:\n",
    "    print(\"the image is realllll boii\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "ename": "DecodeError",
     "evalue": "Wrong wire type in tag.",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mDecodeError\u001b[0m                               Traceback (most recent call last)",
      "Input \u001b[0;32mIn [11]\u001b[0m, in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0m onnx_model \u001b[38;5;241m=\u001b[39m \u001b[43monnx\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;43m/Users/jarvis/pymycod/Deepfakes/multimodal_deepfake_detection/checkpoints/efficientnet.onnx\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/anaconda3/envs/tensor/lib/python3.8/site-packages/onnx/__init__.py:208\u001b[0m, in \u001b[0;36mload_model\u001b[0;34m(f, format, load_external_data)\u001b[0m\n\u001b[1;32m    187\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mload_model\u001b[39m(\n\u001b[1;32m    188\u001b[0m     f: IO[\u001b[38;5;28mbytes\u001b[39m] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28mstr\u001b[39m \u001b[38;5;241m|\u001b[39m os\u001b[38;5;241m.\u001b[39mPathLike,\n\u001b[1;32m    189\u001b[0m     \u001b[38;5;28mformat\u001b[39m: _SupportedFormat \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m    190\u001b[0m     load_external_data: \u001b[38;5;28mbool\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m    191\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ModelProto:\n\u001b[1;32m    192\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Loads a serialized ModelProto into memory.\u001b[39;00m\n\u001b[1;32m    193\u001b[0m \n\u001b[1;32m    194\u001b[0m \u001b[38;5;124;03m    Args:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    206\u001b[0m \u001b[38;5;124;03m        Loaded in-memory ModelProto.\u001b[39;00m\n\u001b[1;32m    207\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 208\u001b[0m     model \u001b[38;5;241m=\u001b[39m \u001b[43m_get_serializer\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mformat\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdeserialize_proto\u001b[49m\u001b[43m(\u001b[49m\u001b[43m_load_bytes\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mModelProto\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    210\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m load_external_data:\n\u001b[1;32m    211\u001b[0m         model_filepath \u001b[38;5;241m=\u001b[39m _get_file_path(f)\n",
      "File \u001b[0;32m/opt/anaconda3/envs/tensor/lib/python3.8/site-packages/onnx/serialization.py:118\u001b[0m, in \u001b[0;36m_ProtobufSerializer.deserialize_proto\u001b[0;34m(self, serialized, proto)\u001b[0m\n\u001b[1;32m    114\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(serialized, \u001b[38;5;28mbytes\u001b[39m):\n\u001b[1;32m    115\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\n\u001b[1;32m    116\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mParameter \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mserialized\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m must be bytes, but got type: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mtype\u001b[39m(serialized)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    117\u001b[0m     )\n\u001b[0;32m--> 118\u001b[0m decoded \u001b[38;5;241m=\u001b[39m typing\u001b[38;5;241m.\u001b[39mcast(Optional[\u001b[38;5;28mint\u001b[39m], \u001b[43mproto\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mParseFromString\u001b[49m\u001b[43m(\u001b[49m\u001b[43mserialized\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[1;32m    119\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m decoded \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m decoded \u001b[38;5;241m!=\u001b[39m \u001b[38;5;28mlen\u001b[39m(serialized):\n\u001b[1;32m    120\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m google\u001b[38;5;241m.\u001b[39mprotobuf\u001b[38;5;241m.\u001b[39mmessage\u001b[38;5;241m.\u001b[39mDecodeError(\n\u001b[1;32m    121\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mProtobuf decoding consumed too few bytes: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdecoded\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m out of \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mlen\u001b[39m(serialized)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    122\u001b[0m     )\n",
      "File \u001b[0;32m/opt/anaconda3/envs/tensor/lib/python3.8/site-packages/google/protobuf/message.py:202\u001b[0m, in \u001b[0;36mMessage.ParseFromString\u001b[0;34m(self, serialized)\u001b[0m\n\u001b[1;32m    194\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Parse serialized protocol buffer data into this message.\u001b[39;00m\n\u001b[1;32m    195\u001b[0m \n\u001b[1;32m    196\u001b[0m \u001b[38;5;124;03mLike :func:`MergeFromString()`, except we clear the object first.\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    199\u001b[0m \u001b[38;5;124;03m  message.DecodeError if the input cannot be parsed.\u001b[39;00m\n\u001b[1;32m    200\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    201\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mClear()\n\u001b[0;32m--> 202\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mMergeFromString\u001b[49m\u001b[43m(\u001b[49m\u001b[43mserialized\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/anaconda3/envs/tensor/lib/python3.8/site-packages/google/protobuf/internal/python_message.py:1128\u001b[0m, in \u001b[0;36m_AddMergeFromStringMethod.<locals>.MergeFromString\u001b[0;34m(self, serialized)\u001b[0m\n\u001b[1;32m   1126\u001b[0m length \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlen\u001b[39m(serialized)\n\u001b[1;32m   1127\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1128\u001b[0m   \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_InternalParse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mserialized\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlength\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;241m!=\u001b[39m length:\n\u001b[1;32m   1129\u001b[0m     \u001b[38;5;66;03m# The only reason _InternalParse would return early is if it\u001b[39;00m\n\u001b[1;32m   1130\u001b[0m     \u001b[38;5;66;03m# encountered an end-group tag.\u001b[39;00m\n\u001b[1;32m   1131\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m message_mod\u001b[38;5;241m.\u001b[39mDecodeError(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mUnexpected end-group tag.\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m   1132\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mIndexError\u001b[39;00m, \u001b[38;5;167;01mTypeError\u001b[39;00m):\n\u001b[1;32m   1133\u001b[0m   \u001b[38;5;66;03m# Now ord(buf[p:p+1]) == ord('') gets TypeError.\u001b[39;00m\n",
      "File \u001b[0;32m/opt/anaconda3/envs/tensor/lib/python3.8/site-packages/google/protobuf/internal/python_message.py:1181\u001b[0m, in \u001b[0;36m_AddMergeFromStringMethod.<locals>.InternalParse\u001b[0;34m(self, buffer, pos, end)\u001b[0m\n\u001b[1;32m   1179\u001b[0m \u001b[38;5;66;03m# TODO(jieluo): remove old_pos.\u001b[39;00m\n\u001b[1;32m   1180\u001b[0m old_pos \u001b[38;5;241m=\u001b[39m new_pos\n\u001b[0;32m-> 1181\u001b[0m (data, new_pos) \u001b[38;5;241m=\u001b[39m \u001b[43mdecoder\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_DecodeUnknownField\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1182\u001b[0m \u001b[43m    \u001b[49m\u001b[43mbuffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnew_pos\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mwire_type\u001b[49m\u001b[43m)\u001b[49m  \u001b[38;5;66;03m# pylint: disable=protected-access\u001b[39;00m\n\u001b[1;32m   1183\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m new_pos \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m   1184\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m pos\n",
      "File \u001b[0;32m/opt/anaconda3/envs/tensor/lib/python3.8/site-packages/google/protobuf/internal/decoder.py:965\u001b[0m, in \u001b[0;36m_DecodeUnknownField\u001b[0;34m(buffer, pos, wire_type)\u001b[0m\n\u001b[1;32m    963\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m (\u001b[38;5;241m0\u001b[39m, \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m    964\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 965\u001b[0m   \u001b[38;5;28;01mraise\u001b[39;00m _DecodeError(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mWrong wire type in tag.\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m    967\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m (data, pos)\n",
      "\u001b[0;31mDecodeError\u001b[0m: Wrong wire type in tag."
     ]
    }
   ],
   "source": [
    "\n",
    "onnx_model = onnx.load('/Users/jarvis/pymycod/Deepfakes/multimodal_deepfake_detection/checkpoints/efficientnet.onnx')\n",
    "# pytorch_model = ConvertModel(onnx_model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "def load_img_modality_model(args):\n",
    "    '''Loads image modality model.'''\n",
    "    rgb_encoder = pytorch_model\n",
    "\n",
    "    ckpt = torch.load('checkpoints/model.pth', map_location = torch.device('cpu'))\n",
    "    rgb_encoder.load_state_dict(ckpt['rgb_encoder'], strict = True)\n",
    "    rgb_encoder.eval()\n",
    "    return rgb_encoder\n",
    "img_model = load_img_modality_model(args)\n",
    "\n",
    "def preprocess_img(face):\n",
    "    face = face / 255\n",
    "    face = cv2.resize(face, (256, 256))\n",
    "    # face = face.transpose(2, 0, 1) #(W, H, C) -> (C, W, H)\n",
    "    face_pt = torch.unsqueeze(torch.Tensor(face), dim = 0) \n",
    "    return face_pt\n",
    "def preprocess_video(input_video, n_frames = 3):\n",
    "    v_cap = cv2.VideoCapture(input_video)\n",
    "    v_len = int(v_cap.get(cv2.CAP_PROP_FRAME_COUNT))\n",
    "\n",
    "    # Pick 'n_frames' evenly spaced frames to sample\n",
    "    if n_frames is None:\n",
    "        sample = np.arange(0, v_len)\n",
    "    else:\n",
    "        sample = np.linspace(0, v_len - 1, n_frames).astype(int)\n",
    "\n",
    "    #Loop through frames.\n",
    "    frames = []\n",
    "    for j in range(v_len):\n",
    "        success = v_cap.grab()\n",
    "        if j in sample:\n",
    "            # Load frame\n",
    "            success, frame = v_cap.retrieve()\n",
    "            if not success:\n",
    "                continue\n",
    "            frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)\n",
    "            frame = preprocess_img(frame)\n",
    "            frames.append(frame)\n",
    "    v_cap.release()\n",
    "    return frames\n",
    "\n",
    "\n",
    "def deepfakes_video_predict(input_video):\n",
    "    '''Perform inference on a video.'''\n",
    "    video_frames = preprocess_video(input_video)\n",
    "    real_faces_list = []\n",
    "    fake_faces_list = []\n",
    "\n",
    "    for face in video_frames:\n",
    "        # face = preprocess_img(face)\n",
    "\n",
    "        img_grads = img_model.forward(face)\n",
    "        img_grads = img_grads.cpu().detach().numpy()\n",
    "        img_grads_np = np.squeeze(img_grads)\n",
    "        real_faces_list.append(img_grads_np[0])\n",
    "        fake_faces_list.append(img_grads_np[1])\n",
    "\n",
    "    real_faces_mean = np.mean(real_faces_list)\n",
    "    fake_faces_mean = np.mean(fake_faces_list)\n",
    "\n",
    "    if real_faces_mean > 0.5:\n",
    "        preds = round(real_faces_mean * 100, 3)\n",
    "        text2 = f\"The video is REAL. \\nConfidence score is: {preds}%\"\n",
    "\n",
    "    else:\n",
    "        preds = round(fake_faces_mean * 100, 3)\n",
    "        text2 = f\"The video is FAKE. \\nConfidence score is: {preds}%\"\n",
    "\n",
    "    return text2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "'Functional' object has no attribute 'forward'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "Input \u001b[0;32mIn [25]\u001b[0m, in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mdeepfakes_video_predict\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/Users/jarvis/Documents/Ss/ras_df.mov\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "Input \u001b[0;32mIn [24]\u001b[0m, in \u001b[0;36mdeepfakes_video_predict\u001b[0;34m(input_video)\u001b[0m\n\u001b[1;32m     37\u001b[0m fake_faces_list \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m     39\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m face \u001b[38;5;129;01min\u001b[39;00m video_frames:\n\u001b[1;32m     40\u001b[0m     \u001b[38;5;66;03m# face = preprocess_img(face)\u001b[39;00m\n\u001b[0;32m---> 42\u001b[0m     img_grads \u001b[38;5;241m=\u001b[39m \u001b[43mmodel1\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mforward\u001b[49m(face)\n\u001b[1;32m     43\u001b[0m     img_grads \u001b[38;5;241m=\u001b[39m img_grads\u001b[38;5;241m.\u001b[39mcpu()\u001b[38;5;241m.\u001b[39mdetach()\u001b[38;5;241m.\u001b[39mnumpy()\n\u001b[1;32m     44\u001b[0m     img_grads_np \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39msqueeze(img_grads)\n",
      "\u001b[0;31mAttributeError\u001b[0m: 'Functional' object has no attribute 'forward'"
     ]
    }
   ],
   "source": [
    "deepfakes_video_predict(\"/Users/jarvis/Documents/Ss/ras_df.mov\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValidationError",
     "evalue": "Unable to parse proto from file: /Users/jarvis/pymycod/Deepfakes/multimodal_deepfake_detection/checkpoints/efficientnet.onnx. Please check if it is a valid protobuf file of proto. ",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValidationError\u001b[0m                           Traceback (most recent call last)",
      "Input \u001b[0;32mIn [10]\u001b[0m, in \u001b[0;36m<cell line: 3>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01monnx\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m checker\n\u001b[0;32m----> 3\u001b[0m \u001b[43mchecker\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcheck_model\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/Users/jarvis/pymycod/Deepfakes/multimodal_deepfake_detection/checkpoints/efficientnet.onnx\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/anaconda3/envs/tensor/lib/python3.8/site-packages/onnx/checker.py:137\u001b[0m, in \u001b[0;36mcheck_model\u001b[0;34m(model, full_check, skip_opset_compatibility_check)\u001b[0m\n\u001b[1;32m    135\u001b[0m \u001b[38;5;66;03m# If model is a path instead of ModelProto\u001b[39;00m\n\u001b[1;32m    136\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(model, (\u001b[38;5;28mstr\u001b[39m, os\u001b[38;5;241m.\u001b[39mPathLike)):\n\u001b[0;32m--> 137\u001b[0m     \u001b[43mC\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcheck_model_path\u001b[49m\u001b[43m(\u001b[49m\u001b[43mos\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfspath\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfull_check\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mskip_opset_compatibility_check\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    138\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    139\u001b[0m     protobuf_string \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    140\u001b[0m         model \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(model, \u001b[38;5;28mbytes\u001b[39m) \u001b[38;5;28;01melse\u001b[39;00m model\u001b[38;5;241m.\u001b[39mSerializeToString()\n\u001b[1;32m    141\u001b[0m     )\n",
      "\u001b[0;31mValidationError\u001b[0m: Unable to parse proto from file: /Users/jarvis/pymycod/Deepfakes/multimodal_deepfake_detection/checkpoints/efficientnet.onnx. Please check if it is a valid protobuf file of proto. "
     ]
    }
   ],
   "source": [
    "from onnx import checker\n",
    "\n",
    "checker.check_model(\"/Users/jarvis/pymycod/Deepfakes/multimodal_deepfake_detection/checkpoints/efficientnet.onnx\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "tensor",
   "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": "3.8.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}