{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.10","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":52950,"databundleVersionId":5973250,"sourceType":"competition"},{"sourceId":6182721,"sourceType":"datasetVersion","datasetId":3497052},{"sourceId":6342181,"sourceType":"datasetVersion","datasetId":3651580}],"dockerImageVersionId":30512,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os\nimport gc\nimport json\nimport math\nimport pickle\nimport numpy as np\nimport pandas as pd\nfrom tqdm import tqdm\nimport matplotlib.pyplot as plt\nimport tensorflow as tf\nimport tensorflow_addons as tfa\nIS_INTERACTIVE = os.environ['KAGGLE_KERNEL_RUN_TYPE'] == 'Interactive'","metadata":{"execution":{"iopub.status.busy":"2024-12-08T08:53:25.011814Z","iopub.execute_input":"2024-12-08T08:53:25.012085Z","iopub.status.idle":"2024-12-08T08:53:32.665481Z","shell.execute_reply.started":"2024-12-08T08:53:25.012063Z","shell.execute_reply":"2024-12-08T08:53:32.664618Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"with open (\"/kaggle/input/asl-fingerspelling/character_to_prediction_index.json\", \"r\") as f:\n    char_to_num = json.load(f)\n\npad_token = '^'\npad_token_idx = 59\n\nchar_to_num[pad_token] = pad_token_idx\n\nnum_to_char = {j:i for i,j in char_to_num.items()}\ndf = pd.read_csv('/kaggle/input/asl-fingerspelling/train.csv')\n\nLIP = [\n    61, 185, 40, 39, 37, 0, 267, 269, 270, 409,\n    291, 146, 91, 181, 84, 17, 314, 405, 321, 375,\n    78, 191, 80, 81, 82, 13, 312, 311, 310, 415,\n    95, 88, 178, 87, 14, 317, 402, 318, 324, 308,\n]\nLPOSE = [13, 15, 17, 19, 21]\nRPOSE = [14, 16, 18, 20, 22]\nPOSE = LPOSE + RPOSE\n\nX = [f'x_right_hand_{i}' for i in range(21)]  +[f'x_left_hand_{i}' for i in range(21)] + [f'x_pose_{i}' for i in POSE] + [f'x_face_{i}' for i in LIP] #+ \nY = [f'y_right_hand_{i}' for i in range(21)]  +[f'y_left_hand_{i}' for i in range(21)]+ [f'y_pose_{i}' for i in POSE] + [f'y_face_{i}' for i in LIP] #+\nZ = [f'z_right_hand_{i}' for i in range(21)]  + [f'z_left_hand_{i}' for i in range(21)]+ [f'z_pose_{i}' for i in POSE] + [f'z_face_{i}' for i in LIP] #+ \n\nSEL_COLS = X + Y + Z\nFRAME_LEN = 128 + 48\nMAX_PHRASE_LENGTH = 64\n\nLIP_IDX_X   = [i for i, col in enumerate(SEL_COLS)  if  \"face\" in col and \"x\" in col]\nRHAND_IDX_X = [i for i, col in enumerate(SEL_COLS)  if \"right\" in col and \"x\" in col]\nLHAND_IDX_X = [i for i, col in enumerate(SEL_COLS)  if  \"left\" in col and \"x\" in col]\nRPOSE_IDX_X = [i for i, col in enumerate(SEL_COLS)  if  \"pose\" in col and int(col[-2:]) in RPOSE and \"x\" in col]\nLPOSE_IDX_X = [i for i, col in enumerate(SEL_COLS)  if  \"pose\" in col and int(col[-2:]) in LPOSE and \"x\" in col]\n\nLIP_IDX_Y   = [i for i, col in enumerate(SEL_COLS)  if  \"face\" in col and \"y\" in col]\nRHAND_IDX_Y = [i for i, col in enumerate(SEL_COLS)  if \"right\" in col and \"y\" in col]\nLHAND_IDX_Y = [i for i, col in enumerate(SEL_COLS)  if  \"left\" in col and \"y\" in col]\nRPOSE_IDX_Y = [i for i, col in enumerate(SEL_COLS)  if  \"pose\" in col and int(col[-2:]) in RPOSE and \"y\" in col]\nLPOSE_IDX_Y = [i for i, col in enumerate(SEL_COLS)  if  \"pose\" in col and int(col[-2:]) in LPOSE and \"y\" in col]\n\nLIP_IDX_Z   = [i for i, col in enumerate(SEL_COLS)  if  \"face\" in col and \"z\" in col]\nRHAND_IDX_Z = [i for i, col in enumerate(SEL_COLS)  if \"right\" in col and \"z\" in col]\nLHAND_IDX_Z = [i for i, col in enumerate(SEL_COLS)  if  \"left\" in col and \"z\" in col]\nRPOSE_IDX_Z = [i for i, col in enumerate(SEL_COLS)  if  \"pose\" in col and int(col[-2:]) in RPOSE and \"z\" in col]\nLPOSE_IDX_Z = [i for i, col in enumerate(SEL_COLS)  if  \"pose\" in col and int(col[-2:]) in LPOSE and \"z\" in col]\n\nRHM = np.load(\"/kaggle/input/aslfr-dataset-tfrecords/mean_std/rh_mean.npy\")\nLHM = np.load(\"/kaggle/input/aslfr-dataset-tfrecords/mean_std/lh_mean.npy\")\nRPM = np.load(\"/kaggle/input/aslfr-dataset-tfrecords/mean_std/rp_mean.npy\")\nLPM = np.load(\"/kaggle/input/aslfr-dataset-tfrecords/mean_std/lp_mean.npy\")\nLIPM = np.load(\"/kaggle/input/aslfr-dataset-tfrecords/mean_std/lip_mean.npy\")\n\nRHS = np.load(\"/kaggle/input/aslfr-dataset-tfrecords/mean_std/rh_std.npy\")\nLHS = np.load(\"/kaggle/input/aslfr-dataset-tfrecords/mean_std/lh_std.npy\")\nRPS = np.load(\"/kaggle/input/aslfr-dataset-tfrecords/mean_std/rp_std.npy\")\nLPS = np.load(\"/kaggle/input/aslfr-dataset-tfrecords/mean_std/lp_std.npy\")\nLIPS = np.load(\"/kaggle/input/aslfr-dataset-tfrecords/mean_std/lip_std.npy\")","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:16:45.128814Z","iopub.execute_input":"2023-07-28T15:16:45.129632Z","iopub.status.idle":"2023-07-28T15:16:45.272277Z","shell.execute_reply.started":"2023-07-28T15:16:45.129592Z","shell.execute_reply":"2023-07-28T15:16:45.271153Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def load_relevant_data_subset(pq_path):\n    return pd.read_parquet(pq_path, columns=SEL_COLS)\n\nfile_id = df.file_id.iloc[0]\ninpdir = \"/kaggle/input/asl-fingerspelling/train_landmarks\"\npqfile = f\"{inpdir}/{file_id}.parquet\"\nseq_refs = df.loc[df.file_id == file_id]\nseqs = load_relevant_data_subset(pqfile)\n\nseq_id = seq_refs.sequence_id.iloc[0]\nframes = seqs.iloc[seqs.index == seq_id]\nphrase = str(df.loc[df.sequence_id == seq_id].phrase.iloc[0])","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:16:45.276498Z","iopub.execute_input":"2023-07-28T15:16:45.276909Z","iopub.status.idle":"2023-07-28T15:16:45.916261Z","shell.execute_reply.started":"2023-07-28T15:16:45.276868Z","shell.execute_reply":"2023-07-28T15:16:45.915283Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"@tf.function()\ndef resize_pad(x):\n    if tf.shape(x)[0] < FRAME_LEN:\n        x = tf.pad(x, ([[0, FRAME_LEN-tf.shape(x)[0]], [0, 0], [0, 0]]), constant_values=float(\"NaN\"))\n    else:\n        x = tf.image.resize(x, (FRAME_LEN, tf.shape(x)[1]))\n    return x\n\n#@tf.function(jit_compile=True)\ndef pre_process0(x):\n    lip_x = tf.gather(x, LIP_IDX_X, axis=1)\n    lip_y = tf.gather(x, LIP_IDX_Y, axis=1)\n    lip_z = tf.gather(x, LIP_IDX_Z, axis=1)\n\n    rhand_x = tf.gather(x, RHAND_IDX_X, axis=1)\n    rhand_y = tf.gather(x, RHAND_IDX_Y, axis=1)\n    rhand_z = tf.gather(x, RHAND_IDX_Z, axis=1)\n    \n    lhand_x = tf.gather(x, LHAND_IDX_X, axis=1)\n    lhand_y = tf.gather(x, LHAND_IDX_Y, axis=1)\n    lhand_z = tf.gather(x, LHAND_IDX_Z, axis=1)\n\n    rpose_x = tf.gather(x, RPOSE_IDX_X, axis=1)\n    rpose_y = tf.gather(x, RPOSE_IDX_Y, axis=1)\n    rpose_z = tf.gather(x, RPOSE_IDX_Z, axis=1)\n    \n    lpose_x = tf.gather(x, LPOSE_IDX_X, axis=1)\n    lpose_y = tf.gather(x, LPOSE_IDX_Y, axis=1)\n    lpose_z = tf.gather(x, LPOSE_IDX_Z, axis=1)\n    \n    lip   = tf.concat([lip_x[..., tf.newaxis], lip_y[..., tf.newaxis], lip_z[..., tf.newaxis]], axis=-1)\n    rhand = tf.concat([rhand_x[..., tf.newaxis], rhand_y[..., tf.newaxis], rhand_z[..., tf.newaxis]], axis=-1)\n    lhand = tf.concat([lhand_x[..., tf.newaxis], lhand_y[..., tf.newaxis], lhand_z[..., tf.newaxis]], axis=-1)\n    rpose = tf.concat([rpose_x[..., tf.newaxis], rpose_y[..., tf.newaxis], rpose_z[..., tf.newaxis]], axis=-1)\n    lpose = tf.concat([lpose_x[..., tf.newaxis], lpose_y[..., tf.newaxis], lpose_z[..., tf.newaxis]], axis=-1)\n        \n    # TIME AUGMENTATION\n    if tf.random.uniform(shape=(), minval=0, maxval=1)<0.8:\n        new_width = tf.shape(lip)[1]\n        new_height = tf.random.uniform(\n    shape=(), \n    minval=tf.cast(tf.cast(tf.shape(lip)[0], tf.float32) / 2.0, tf.int32),  \n    maxval=tf.cast(tf.cast(tf.shape(lip)[0], tf.float32) * 1.5, tf.int32),   \n    dtype=tf.int32\n)\n        resized_lip = tf.image.resize(lip, (new_height, new_width))\n        resized_rhand = tf.image.resize(rhand, (new_height, new_width))\n        resized_lhand = tf.image.resize(lhand, (new_height, new_width))\n        resized_rpose = tf.image.resize(rpose, (new_height, new_width))\n        resized_lpose = tf.image.resize(lpose, (new_height, new_width))\n        return resized_lip, resized_rhand, resized_lhand, resized_rpose, resized_lpose        \n        \n    return lip, rhand, lhand,  rpose, lpose \n\n@tf.function(jit_compile=True)\ndef pre_process00(x):\n    lip_x = tf.gather(x, LIP_IDX_X, axis=1)\n    lip_y = tf.gather(x, LIP_IDX_Y, axis=1)\n    lip_z = tf.gather(x, LIP_IDX_Z, axis=1)\n\n    rhand_x = tf.gather(x, RHAND_IDX_X, axis=1)\n    rhand_y = tf.gather(x, RHAND_IDX_Y, axis=1)\n    rhand_z = tf.gather(x, RHAND_IDX_Z, axis=1)\n    \n    lhand_x = tf.gather(x, LHAND_IDX_X, axis=1)\n    lhand_y = tf.gather(x, LHAND_IDX_Y, axis=1)\n    lhand_z = tf.gather(x, LHAND_IDX_Z, axis=1)\n\n    rpose_x = tf.gather(x, RPOSE_IDX_X, axis=1)\n    rpose_y = tf.gather(x, RPOSE_IDX_Y, axis=1)\n    rpose_z = tf.gather(x, RPOSE_IDX_Z, axis=1)\n    \n    lpose_x = tf.gather(x, LPOSE_IDX_X, axis=1)\n    lpose_y = tf.gather(x, LPOSE_IDX_Y, axis=1)\n    lpose_z = tf.gather(x, LPOSE_IDX_Z, axis=1)\n    \n    lip   = tf.concat([lip_x[..., tf.newaxis], lip_y[..., tf.newaxis], lip_z[..., tf.newaxis]], axis=-1)\n    rhand = tf.concat([rhand_x[..., tf.newaxis], rhand_y[..., tf.newaxis], rhand_z[..., tf.newaxis]], axis=-1)\n    lhand = tf.concat([lhand_x[..., tf.newaxis], lhand_y[..., tf.newaxis], lhand_z[..., tf.newaxis]], axis=-1)\n    rpose = tf.concat([rpose_x[..., tf.newaxis], rpose_y[..., tf.newaxis], rpose_z[..., tf.newaxis]], axis=-1)\n    lpose = tf.concat([lpose_x[..., tf.newaxis], lpose_y[..., tf.newaxis], lpose_z[..., tf.newaxis]], axis=-1)\n                \n    hand = tf.concat([rhand, lhand], axis=1)\n    hand = tf.where(tf.math.is_nan(hand), 0.0, hand)\n    input_tensor = tf.math.not_equal(tf.reduce_sum(hand, axis=[1, 2]), 0.0)\n    alternating_tensor = tf.math.equal( tf.cumsum(tf.ones_like( tf.reduce_sum(hand, axis=[1, 2]) ))%2, 1.0 )\n    mask = tf.math.logical_or(input_tensor, alternating_tensor)\n    \n    lip = lip[mask]\n    rhand = rhand[mask]\n    lhand = lhand[mask]\n    rpose = rpose[mask]\n    lpose = lpose[mask]\n\n    return lip, rhand, lhand,  rpose, lpose\n\n@tf.function()\ndef pre_process1(lip, rhand,lhand,  rpose, lpose): #lhand,\n    lip   = (resize_pad(lip) - LIPM) / LIPS\n    rhand = (resize_pad(rhand) - RHM) / RHS\n    lhand = (resize_pad(lhand) - LHM) / LHS\n    rpose = (resize_pad(rpose) - RPM) / RPS\n    lpose = (resize_pad(lpose) - LPM) / LPS\n\n    x = tf.concat([lip, rhand, lhand, rpose, lpose], axis=1) #lhand,\n    s = tf.shape(x)\n    x = tf.reshape(x, (s[0], s[1]*s[2]))\n    x = tf.where(tf.math.is_nan(x), 0.0, x)\n    return x\n\npre0 = pre_process0(frames)\npre1 = pre_process1(*pre0)\nINPUT_SHAPE = list(pre1.shape)\nprint(INPUT_SHAPE)","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:16:45.920304Z","iopub.execute_input":"2023-07-28T15:16:45.920909Z","iopub.status.idle":"2023-07-28T15:16:49.745302Z","shell.execute_reply.started":"2023-07-28T15:16:45.920873Z","shell.execute_reply":"2023-07-28T15:16:49.744126Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def decode_fn(record_bytes):\n    schema = {\n        \"lip\": tf.io.VarLenFeature(tf.float32),\n        \"rhand\": tf.io.VarLenFeature(tf.float32),\n        \"lhand\": tf.io.VarLenFeature(tf.float32),\n        \"rpose\": tf.io.VarLenFeature(tf.float32),\n        \"lpose\": tf.io.VarLenFeature(tf.float32),\n        \"phrase\": tf.io.VarLenFeature(tf.int64)\n    }\n    x = tf.io.parse_single_example(record_bytes, schema)\n\n    lip = tf.reshape(tf.sparse.to_dense(x[\"lip\"]), (-1, 40, 3))\n    rhand = tf.reshape(tf.sparse.to_dense(x[\"rhand\"]), (-1, 21, 3))\n    lhand = tf.reshape(tf.sparse.to_dense(x[\"lhand\"]), (-1, 21, 3))\n    rpose = tf.reshape(tf.sparse.to_dense(x[\"rpose\"]), (-1, 5, 3))\n    lpose = tf.reshape(tf.sparse.to_dense(x[\"lpose\"]), (-1, 5, 3))\n    phrase = tf.sparse.to_dense(x[\"phrase\"])\n\n    return lip, rhand, lhand,  rpose, lpose, phrase #lhand,\n\ndef pre_process_fn(lip, rhand,lhand,  rpose, lpose, phrase): #lhand,\n    phrase = tf.pad(phrase, [[0, MAX_PHRASE_LENGTH-tf.shape(phrase)[0]]], constant_values=pad_token_idx)\n    return pre_process1(lip, rhand, lhand, rpose, lpose), phrase #lhand,\n    \ntffiles = [f\"/kaggle/input/chris-tf-v9/{file_id}.tfrecord\" for file_id in df.file_id.unique()]\nval_len = 1\ntrain_batch_size = 64\nval_batch_size = 64\n\ntrain_dataset =  tf.data.TFRecordDataset(tffiles[val_len:]).prefetch(tf.data.AUTOTUNE).shuffle(5000).map(decode_fn, num_parallel_calls=tf.data.AUTOTUNE).map(pre_process_fn, num_parallel_calls=tf.data.AUTOTUNE).batch(train_batch_size).prefetch(tf.data.AUTOTUNE)\nval_dataset =  tf.data.TFRecordDataset(tffiles[:val_len]).prefetch(tf.data.AUTOTUNE).map(decode_fn, num_parallel_calls=tf.data.AUTOTUNE).map(pre_process_fn, num_parallel_calls=tf.data.AUTOTUNE).batch(val_batch_size).prefetch(tf.data.AUTOTUNE)\n\nbatch = next(iter(val_dataset))\nbatch[0].shape, batch[1].shape","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:16:49.746934Z","iopub.execute_input":"2023-07-28T15:16:49.747337Z","iopub.status.idle":"2023-07-28T15:16:50.454515Z","shell.execute_reply.started":"2023-07-28T15:16:49.7473Z","shell.execute_reply":"2023-07-28T15:16:50.453395Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow as tf\nimport tensorflow_addons as tfa\n\n# Custom layers from previous implementation\nclass ECA(tf.keras.layers.Layer):\n    def __init__(self, kernel_size=5, **kwargs):\n        super().__init__(**kwargs)\n        self.supports_masking = True\n        self.kernel_size = kernel_size\n        self.conv = tf.keras.layers.Conv1D(1, kernel_size=kernel_size, strides=1, padding=\"same\", use_bias=False)\n\n    def call(self, inputs, mask=None):\n        nn = tf.keras.layers.GlobalAveragePooling1D()(inputs, mask=mask)\n        nn = tf.expand_dims(nn, -1)\n        nn = self.conv(nn)\n        nn = tf.squeeze(nn, -1)\n        nn = tf.nn.sigmoid(nn)\n        nn = nn[:, None, :]\n        return inputs * nn\n\nclass CausalDWConv1D(tf.keras.layers.Layer):\n    def __init__(self, kernel_size=17, dilation_rate=1, use_bias=False, depthwise_initializer='glorot_uniform', name='', **kwargs):\n        super().__init__(name=name, **kwargs)\n        self.causal_pad = tf.keras.layers.ZeroPadding1D((dilation_rate * (kernel_size - 1), 0), name=name + '_pad')\n        self.dw_conv = tf.keras.layers.DepthwiseConv1D(kernel_size, strides=1, dilation_rate=dilation_rate, padding='valid', use_bias=use_bias, depthwise_initializer=depthwise_initializer, name=name + '_dwconv')\n        self.supports_masking = True\n        \n    def call(self, inputs):\n        x = self.causal_pad(inputs)\n        x = self.dw_conv(x)\n        return x\n\ndef Conv1DBlock(channel_size, kernel_size, dilation_rate=1, drop_rate=0.0, expand_ratio=2, se_ratio=0.25, activation='swish', name=None):\n    if name is None:\n        name = str(tf.keras.backend.get_uid(\"mbblock\"))\n\n    def apply(inputs):\n        channels_in = tf.keras.backend.int_shape(inputs)[-1]\n        channels_expand = channels_in * expand_ratio\n\n        skip = inputs\n\n        x = tf.keras.layers.Dense(channels_expand, use_bias=True, activation=activation, name=name + '_expand_conv')(inputs)\n        x = CausalDWConv1D(kernel_size, dilation_rate=dilation_rate, use_bias=False, name=name + '_dwconv')(x)\n        x = tf.keras.layers.BatchNormalization(momentum=0.95, name=name + '_bn')(x)\n        x = ECA()(x)\n\n        x = tf.keras.layers.Dense(channel_size, use_bias=True, name=name + '_project_conv')(x)\n\n        if drop_rate > 0:\n            x = tf.keras.layers.Dropout(drop_rate, noise_shape=(None, 1, 1), name=name + '_drop')(x)\n\n        if channels_in == channel_size:\n            x = tf.keras.layers.add([x, skip], name=name + '_add')\n\n        return x\n\n    return apply\n\nclass MultiHeadSelfAttention(tf.keras.layers.Layer):\n    def __init__(self, dim=512, num_heads=4, dropout=0, **kwargs):\n        super().__init__(**kwargs)\n        self.dim = dim\n        self.scale = self.dim ** -0.5\n        self.num_heads = num_heads\n        self.qkv = tf.keras.layers.Dense(3 * dim, use_bias=False)\n        self.drop1 = tf.keras.layers.Dropout(dropout)\n        self.proj = tf.keras.layers.Dense(dim, use_bias=False)\n        self.supports_masking = True\n\n    def call(self, inputs, mask=None):\n        qkv = self.qkv(inputs)\n        qkv = tf.keras.layers.Permute((2, 1, 3))(tf.keras.layers.Reshape((-1, self.num_heads, self.dim * 3 // self.num_heads))(qkv))\n        q, k, v = tf.split(qkv, [self.dim // self.num_heads] * 3, axis=-1)\n\n        attn = tf.matmul(q, k, transpose_b=True) * self.scale\n\n        if mask is not None:\n            mask = mask[:, None, None, :]\n\n        attn = tf.keras.layers.Softmax(axis=-1)(attn, mask=mask)\n        attn = self.drop1(attn)\n\n        x = attn @ v\n        x = tf.keras.layers.Reshape((-1, self.dim))(tf.keras.layers.Permute((2, 1, 3))(x))\n        x = self.proj(x)\n        return x\n\ndef ConformerBlock(dim=512, num_heads=8, expand=4, attn_dropout=0.2, conv_kernel_size=17, conv_dilation_rate=1, ffn_dropout=0.2, activation='swish', drop_rate=0.2):\n    def apply(inputs):\n        # Feed-Forward Block\n        x = tf.keras.layers.LayerNormalization(epsilon=1e-6)(inputs)\n        x = tf.keras.layers.Dense(dim * expand, activation=activation, use_bias=True)(x)\n\n        # Multi-Head Self Attention\n        x = tf.keras.layers.LayerNormalization(epsilon=1e-6)(x)\n        x = MultiHeadSelfAttention(dim=dim, num_heads=num_heads, dropout=attn_dropout)(x)\n        x = tf.keras.layers.Dropout(ffn_dropout)(x)\n        x = tf.keras.layers.Add()([inputs, x])  # Residual connection\n\n        # Convolution Block (Conv1D)\n        x = tf.keras.layers.LayerNormalization(epsilon=1e-6)(x)\n        x = Conv1DBlock(channel_size=dim, kernel_size=conv_kernel_size, dilation_rate=conv_dilation_rate, drop_rate=drop_rate, expand_ratio=4)(x)\n\n        # Feed-Forward Block\n        x = tf.keras.layers.LayerNormalization(epsilon=1e-6)(x)\n        x = tf.keras.layers.Dense(dim, activation=activation, use_bias=True)(x)\n        x = tf.keras.layers.Dropout(ffn_dropout)(x)\n\n        # Final Residual Add\n        x = tf.keras.layers.Add()([x, inputs])\n        return x\n\n    return apply\n\ndef positional_encoding(maxlen, num_hid):\n    depth = num_hid // 2\n    positions = tf.range(maxlen, dtype=tf.float32)[..., tf.newaxis]\n    depths = tf.range(depth, dtype=tf.float32)[np.newaxis, :] / depth\n    angle_rates = tf.math.divide(1, tf.math.pow(tf.cast(10000, tf.float32), depths))\n    angle_rads = tf.linalg.matmul(positions, angle_rates)\n    pos_encoding = tf.concat([tf.math.sin(angle_rads), tf.math.cos(angle_rads)], axis=-1)\n    return pos_encoding","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:16:50.456222Z","iopub.execute_input":"2023-07-28T15:16:50.456569Z","iopub.status.idle":"2023-07-28T15:16:50.494542Z","shell.execute_reply.started":"2023-07-28T15:16:50.456543Z","shell.execute_reply":"2023-07-28T15:16:50.493425Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def CTCLoss(labels, logits):\n    label_length = tf.reduce_sum(tf.cast(labels != pad_token_idx, tf.int32), axis=-1)\n    logit_length = tf.ones(tf.shape(logits)[0], dtype=tf.int32) * tf.shape(logits)[1]\n    loss = tf.nn.ctc_loss(\n            labels=labels,\n            logits=logits,\n            label_length=label_length,\n            logit_length=logit_length,\n            blank_index=pad_token_idx,\n            logits_time_major=False\n        )\n    loss = tf.reduce_mean(loss)\n    return loss","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:16:50.496402Z","iopub.execute_input":"2023-07-28T15:16:50.496827Z","iopub.status.idle":"2023-07-28T15:16:50.504277Z","shell.execute_reply.started":"2023-07-28T15:16:50.496792Z","shell.execute_reply":"2023-07-28T15:16:50.503021Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# def get_model(dim = 384):\n#     inp = tf.keras.Input(INPUT_SHAPE)\n#     x = tf.keras.layers.Masking(mask_value=0.0)(inp)\n#     x = tf.keras.layers.Dense(dim, use_bias=False, name='stem_conv')(x)\n#     pe = tf.cast(positional_encoding(INPUT_SHAPE[0], dim), dtype=x.dtype)\n#     x = x + pe\n#     x = tf.keras.layers.BatchNormalization(momentum=0.95,name='stem_bn')(x)\n#     num_blocks = 6\n#     drop_rate  = 0.4\n#     for i in range(num_blocks):\n#         x = Conv1DBlock(dim, 11, drop_rate=drop_rate)(x)\n#         x = Conv1DBlock(dim,  5, drop_rate=drop_rate)(x)\n#         x = Conv1DBlock(dim,  3, drop_rate=drop_rate)(x)\n#         x = TransformerBlock(dim, expand=2)(x)\n\n#     x = tf.keras.layers.Dense(dim*2,activation='relu',name='top_conv')(x)\n#     x = tf.keras.layers.Dropout(0.4)(x)\n#     #x = LateDropout(0.7)(x)\n#     x = tf.keras.layers.Dense(len(char_to_num),name='classifier')(x)\n\n#     model = tf.keras.Model(inp, x)\n\n#     loss = CTCLoss\n    \n#     # Adam Optimizer\n#     optimizer = tfa.optimizers.RectifiedAdam(sma_threshold=4)\n#     optimizer = tfa.optimizers.Lookahead(optimizer, sync_period=5)\n\n#     model.compile(loss=loss, optimizer=optimizer)\n\n#     return model\n\ndef get_model(dim=512, num_blocks=4, conv_kernel_size=17, conv_dilation_rate=1, ffn_dropout=0.2, drop_rate=0.2):\n    inp = tf.keras.Input(INPUT_SHAPE)\n    x = tf.keras.layers.Masking(mask_value=0.0)(inp)\n    x = tf.keras.layers.Dense(dim, use_bias=False, name='stem_conv')(x)\n\n    # Add Positional Encoding\n    pe = tf.cast(positional_encoding(INPUT_SHAPE[0], dim), dtype=x.dtype)\n    x = x + pe\n    x = tf.keras.layers.BatchNormalization(momentum=0.95, name='stem_bn')(x)\n\n    # Apply Conformer Blocks\n    for i in range(num_blocks):\n        # First Convolutional layer\n        conv_x = tf.keras.layers.Conv1D(dim, kernel_size=conv_kernel_size, dilation_rate=conv_dilation_rate, padding='same', activation='swish', name=f'conv_block_{i}_1')(x)\n        conv_x = tf.keras.layers.BatchNormalization(momentum=0.95, name=f'conv_block_{i}_1_bn')(conv_x)\n        conv_x = tf.keras.layers.Dropout(drop_rate)(conv_x)\n\n        # Second Convolutional layer\n        conv_x = tf.keras.layers.Conv1D(dim, kernel_size=conv_kernel_size, dilation_rate=conv_dilation_rate, padding='same', activation='swish', name=f'conv_block_{i}_2')(conv_x)\n        conv_x = tf.keras.layers.BatchNormalization(momentum=0.95, name=f'conv_block_{i}_2_bn')(conv_x)\n        conv_x = tf.keras.layers.Dropout(drop_rate)(conv_x)\n\n        # Third Convolutional layer\n        conv_x = tf.keras.layers.Conv1D(dim, kernel_size=conv_kernel_size, dilation_rate=conv_dilation_rate, padding='same', activation='swish', name=f'conv_block_{i}_3')(conv_x)\n        conv_x = tf.keras.layers.BatchNormalization(momentum=0.95, name=f'conv_block_{i}_3_bn')(conv_x)\n        conv_x = tf.keras.layers.Dropout(drop_rate)(conv_x)\n        \n        x = ConformerBlock(dim, num_heads=6, expand=4, conv_kernel_size=conv_kernel_size, conv_dilation_rate=conv_dilation_rate, ffn_dropout=ffn_dropout, drop_rate=drop_rate)(x)\n\n    # Final output layer\n    x = tf.keras.layers.Dense(dim * 2, activation='relu', name='top_conv')(x)\n    x = tf.keras.layers.Dropout(0.4)(x)\n    x = tf.keras.layers.Dense(len(char_to_num), name='classifier')(x)\n\n    model = tf.keras.Model(inp, x)\n\n    # Define loss and optimizer\n    loss = CTCLoss\n    optimizer = tfa.optimizers.RectifiedAdam(sma_threshold=4)\n    optimizer = tfa.optimizers.Lookahead(optimizer, sync_period=5)\n\n    model.compile(loss=loss, optimizer=optimizer)\n\n    return model\n\n# Clear\ntf.keras.backend.clear_session()\nmodel = get_model()\nmodel(batch[0])\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:16:50.505885Z","iopub.execute_input":"2023-07-28T15:16:50.506408Z","iopub.status.idle":"2023-07-28T15:16:56.077558Z","shell.execute_reply.started":"2023-07-28T15:16:50.506374Z","shell.execute_reply":"2023-07-28T15:16:56.076738Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def num_to_char_fn(y):\n    return [num_to_char.get(x, \"\") for x in y]\n\n@tf.function()\ndef decode_phrase(pred):\n    x = tf.argmax(pred, axis=1)\n    diff = tf.not_equal(x[:-1], x[1:])\n    adjacent_indices = tf.where(diff)[:, 0]\n    x = tf.gather(x, adjacent_indices)\n    mask = x != pad_token_idx\n    x = tf.boolean_mask(x, mask, axis=0)\n    return x\n\n# A utility function to decode the output of the network\ndef decode_batch_predictions(pred):\n    output_text = []\n    for result in pred:\n        result = \"\".join(num_to_char_fn(decode_phrase(result).numpy()))\n        output_text.append(result)\n    return output_text","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:16:56.078661Z","iopub.execute_input":"2023-07-28T15:16:56.079019Z","iopub.status.idle":"2023-07-28T15:16:56.095309Z","shell.execute_reply.started":"2023-07-28T15:16:56.078973Z","shell.execute_reply":"2023-07-28T15:16:56.094333Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\n# A callback class to output a few transcriptions during training\nclass CallbackEval(tf.keras.callbacks.Callback):\n    \"\"\"Displays a batch of outputs after every epoch.\"\"\"\n\n    def __init__(self, dataset):\n        super().__init__()\n        self.dataset = dataset\n\n    def on_epoch_end(self, epoch: int, logs=None):\n        model.save_weights(\"model.h5\")\n        predictions = []\n        targets = []\n        for batch in self.dataset:\n            X, y = batch\n            batch_predictions = model(X)\n            batch_predictions = decode_batch_predictions(batch_predictions)\n            predictions.extend(batch_predictions)\n            for label in y:\n                label = \"\".join(num_to_char_fn(label.numpy()))\n                targets.append(label)\n        print(\"-\" * 100)\n        # for i in np.random.randint(0, len(predictions), 2):\n        for i in range(32):\n            print(f\"Target    : {targets[i]}\")\n            print(f\"Prediction: {predictions[i]}, len: {len(predictions[i])}\")\n            print(\"-\" * 100)\n\n# Callback function to check transcription on the val set.\nvalidation_callback = CallbackEval(val_dataset.take(1))","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:16:56.096747Z","iopub.execute_input":"2023-07-28T15:16:56.097105Z","iopub.status.idle":"2023-07-28T15:16:56.12454Z","shell.execute_reply.started":"2023-07-28T15:16:56.097073Z","shell.execute_reply":"2023-07-28T15:16:56.123391Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"N_EPOCHS = 2 if IS_INTERACTIVE else 30\nN_WARMUP_EPOCHS = 0 if IS_INTERACTIVE else 5\nLR_MAX = 4e-3\nWD_RATIO = 0.05\nWARMUP_METHOD = \"exp\"","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:16:56.126121Z","iopub.execute_input":"2023-07-28T15:16:56.126629Z","iopub.status.idle":"2023-07-28T15:16:56.137595Z","shell.execute_reply.started":"2023-07-28T15:16:56.126561Z","shell.execute_reply":"2023-07-28T15:16:56.136422Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def lrfn(current_step, num_warmup_steps, lr_max, num_cycles=0.50, num_training_steps=N_EPOCHS):\n    \n    if current_step < num_warmup_steps:\n        if WARMUP_METHOD == 'log':\n            return lr_max * 0.10 ** (num_warmup_steps - current_step)\n        else:\n            return lr_max * 2 ** -(num_warmup_steps - current_step)\n    else:\n        progress = float(current_step - num_warmup_steps) / float(max(1, num_training_steps - num_warmup_steps))\n\n        return max(0.0, 0.5 * (1.0 + math.cos(math.pi * float(num_cycles) * 2.0 * progress))) * lr_max\n    \ndef plot_lr_schedule(lr_schedule, epochs):\n    fig = plt.figure(figsize=(20, 10))\n    plt.plot([None] + lr_schedule + [None])\n    # X Labels\n    x = np.arange(1, epochs + 1)\n    x_axis_labels = [i if epochs <= 40 or i % 5 == 0 or i == 1 else None for i in range(1, epochs + 1)]\n    plt.xlim([1, epochs])\n    plt.xticks(x, x_axis_labels) # set tick step to 1 and let x axis start at 1\n    \n    # Increase y-limit for better readability\n    plt.ylim([0, max(lr_schedule) * 1.1])\n    \n    # Title\n    schedule_info = f'start: {lr_schedule[0]:.1E}, max: {max(lr_schedule):.1E}, final: {lr_schedule[-1]:.1E}'\n    plt.title(f'Step Learning Rate Schedule, {schedule_info}', size=18, pad=12)\n    \n    # Plot Learning Rates\n    for x, val in enumerate(lr_schedule):\n        if epochs <= 40 or x % 5 == 0 or x is epochs - 1:\n            if x < len(lr_schedule) - 1:\n                if lr_schedule[x - 1] < val:\n                    ha = 'right'\n                else:\n                    ha = 'left'\n            elif x == 0:\n                ha = 'right'\n            else:\n                ha = 'left'\n            plt.plot(x + 1, val, 'o', color='black');\n            offset_y = (max(lr_schedule) - min(lr_schedule)) * 0.02\n            plt.annotate(f'{val:.1E}', xy=(x + 1, val + offset_y), size=12, ha=ha)\n    \n    plt.xlabel('Epoch', size=16, labelpad=5)\n    plt.ylabel('Learning Rate', size=16, labelpad=5)\n    plt.grid()\n    plt.show()\n\n# Learning rate for encoder\nLR_SCHEDULE = [lrfn(step, num_warmup_steps=N_WARMUP_EPOCHS, lr_max=LR_MAX, num_cycles=0.50) for step in range(N_EPOCHS)]\n# Plot Learning Rate Schedule\nplot_lr_schedule(LR_SCHEDULE, epochs=N_EPOCHS)\n# Learning Rate Callback\nlr_callback = tf.keras.callbacks.LearningRateScheduler(lambda step: LR_SCHEDULE[step], verbose=0)\n\n# Custom callback to update weight decay with learning rate\nclass WeightDecayCallback(tf.keras.callbacks.Callback):\n    def __init__(self, wd_ratio=WD_RATIO):\n        self.step_counter = 0\n        self.wd_ratio = wd_ratio\n    \n    def on_epoch_begin(self, epoch, logs=None):\n        model.optimizer.weight_decay = model.optimizer.learning_rate * self.wd_ratio\n        print(f'learning rate: {model.optimizer.learning_rate.numpy():.2e}, weight decay: {model.optimizer.weight_decay.numpy():.2e}')","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:16:56.139501Z","iopub.execute_input":"2023-07-28T15:16:56.140391Z","iopub.status.idle":"2023-07-28T15:16:56.794762Z","shell.execute_reply.started":"2023-07-28T15:16:56.1403Z","shell.execute_reply":"2023-07-28T15:16:56.793817Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"history = model.fit(\n    train_dataset,\n    validation_data=val_dataset,\n    epochs=N_EPOCHS,\n    callbacks=[\n        validation_callback,\n        lr_callback,\n        WeightDecayCallback(),\n    ]\n)","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:16:56.799121Z","iopub.execute_input":"2023-07-28T15:16:56.799851Z","iopub.status.idle":"2023-07-28T15:17:30.607822Z","shell.execute_reply.started":"2023-07-28T15:16:56.799813Z","shell.execute_reply":"2023-07-28T15:17:30.604703Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class TFLiteModel(tf.Module):\n    def __init__(self, model):\n        super(TFLiteModel, self).__init__()\n        self.model = model\n    \n    @tf.function(input_signature=[tf.TensorSpec(shape=[None, len(SEL_COLS)], dtype=tf.float32, name='inputs')])\n    def __call__(self, inputs, training=False):\n        # Preprocess Data\n        x = tf.cast(inputs, tf.float32)\n        x = x[None]\n        x = tf.cond(tf.shape(x)[1] == 0, lambda: tf.zeros((1, 1, len(SEL_COLS))), lambda: tf.identity(x))\n        x = x[0]\n        x = pre_process00(x)\n        x = pre_process1(*x)\n        x = tf.reshape(x, INPUT_SHAPE)\n        x = x[None]\n        x = self.model(x, training=False)\n        x = x[0]\n        x = decode_phrase(x)\n        # POST PROCESS. IF PRED LESS THAN 3, USE CONSTANT PREDICTION FROM\n        # https://www.kaggle.com/code/anokas/static-greedy-baseline-0-157-lb\n        x = tf.cond(tf.shape(x)[0] < 3, lambda: tf.constant(\n            [17, 0, 32, 12, 36, 0, 12, 32, 49, 46, 36], tf.int64), lambda: tf.identity(x))\n        x = tf.one_hot(x, 59)\n        return {'outputs': x}\n\ntflitemodel_base = TFLiteModel(model)\ntflitemodel_base(frames)[\"outputs\"].shape","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:17:30.611295Z","iopub.status.idle":"2023-07-28T15:17:30.613808Z","shell.execute_reply.started":"2023-07-28T15:17:30.613532Z","shell.execute_reply":"2023-07-28T15:17:30.613558Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"keras_model_converter = tf.lite.TFLiteConverter.from_keras_model(tflitemodel_base)\nkeras_model_converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS]#, tf.lite.OpsSet.SELECT_TF_OPS]\nkeras_model_converter.optimizations = [tf.lite.Optimize.DEFAULT]\nkeras_model_converter.target_spec.supported_types = [tf.float16]\ntflite_model = keras_model_converter.convert()\nwith open('model.tflite', 'wb') as f:\n    f.write(tflite_model)\n    \nwith open('inference_args.json', \"w\") as f:\n    json.dump({\"selected_columns\" : SEL_COLS}, f)\n    \n!zip submission.zip  './model.tflite' './inference_args.json'","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:17:30.617936Z","iopub.status.idle":"2023-07-28T15:17:30.620425Z","shell.execute_reply.started":"2023-07-28T15:17:30.620132Z","shell.execute_reply":"2023-07-28T15:17:30.62016Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"with open (\"inference_args.json\", \"r\") as f:\n    SEL_COLS = json.load(f)[\"selected_columns\"]\n    \ndef load_relevant_data_subset(pq_path):\n    return pd.read_parquet(pq_path, columns=SEL_COLS)\n\ndef create_data_gen(file_ids, y_mul=1):\n    def gen():\n        for file_id in file_ids:\n            pqfile = f\"{inpdir}/{file_id}.parquet\"\n            seq_refs = df.loc[df.file_id == file_id]\n            seqs = load_relevant_data_subset(pqfile)\n\n            for seq_id in seq_refs.sequence_id:\n                x = seqs.iloc[seqs.index == seq_id].to_numpy()\n                y = str(df.loc[df.sequence_id == seq_id].phrase.iloc[0])\n                \n                r_nonan = np.sum(np.sum(np.isnan(x[:, RHAND_IDX_X]), axis = 1) == 0)\n                l_nonan = np.sum(np.sum(np.isnan(x[:, LHAND_IDX_X]), axis = 1) == 0)\n                no_nan = max(r_nonan, l_nonan)\n                \n                if y_mul*len(y)<no_nan:\n                    yield x, y\n    return gen\n\npqfiles = df.file_id.unique()\nval_len = int(0.05 * len(pqfiles))\n\ntest_dataset = tf.data.Dataset.from_generator(create_data_gen(pqfiles[:val_len], 0),\n    output_signature=(tf.TensorSpec(shape=(None, len(SEL_COLS)), dtype=tf.float32), tf.TensorSpec(shape=(), dtype=tf.string))\n).prefetch(buffer_size=2000)","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:17:30.622044Z","iopub.status.idle":"2023-07-28T15:17:30.626835Z","shell.execute_reply.started":"2023-07-28T15:17:30.626563Z","shell.execute_reply":"2023-07-28T15:17:30.626588Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"interpreter = tf.lite.Interpreter(\"model.tflite\")\n\nREQUIRED_SIGNATURE = \"serving_default\"\nREQUIRED_OUTPUT = \"outputs\"\n\nwith open (\"/kaggle/input/asl-fingerspelling/character_to_prediction_index.json\", \"r\") as f:\n    character_map = json.load(f)\nrev_character_map = {j:i for i,j in character_map.items()}\n\nprediction_fn = interpreter.get_signature_runner(REQUIRED_SIGNATURE)\n\nfor frame, target in test_dataset.skip(100).take(10):\n    output = prediction_fn(inputs=frame)\n    prediction_str = \"\".join([rev_character_map.get(s, \"\") for s in np.argmax(output[REQUIRED_OUTPUT], axis=1)])\n    target = target.numpy().decode(\"utf-8\")\n    print(\"pred =\", prediction_str, \"; target =\", target)","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:17:30.628442Z","iopub.status.idle":"2023-07-28T15:17:30.629262Z","shell.execute_reply.started":"2023-07-28T15:17:30.629011Z","shell.execute_reply":"2023-07-28T15:17:30.629036Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%timeit -n 10\noutput = prediction_fn(inputs=frame)","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:17:30.63078Z","iopub.status.idle":"2023-07-28T15:17:30.631608Z","shell.execute_reply.started":"2023-07-28T15:17:30.631322Z","shell.execute_reply":"2023-07-28T15:17:30.631345Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from Levenshtein import distance\n\nscores = []\n\nfor i, (frame, target) in tqdm(enumerate(test_dataset.take(1000))):\n    output = prediction_fn(inputs=frame)\n    prediction_str = \"\".join([rev_character_map.get(s, \"\") for s in np.argmax(output[REQUIRED_OUTPUT], axis=1)])\n    target = target.numpy().decode(\"utf-8\")\n    score = (len(target) - distance(prediction_str, target)) / len(target)\n    scores.append(score)\n    if i % 50 == 0:\n        print(np.sum(scores) / len(scores))\n    \nscores = np.array(scores)\nprint(np.sum(scores) / len(scores))","metadata":{"execution":{"iopub.status.busy":"2023-07-28T15:17:30.639192Z","iopub.status.idle":"2023-07-28T15:17:30.639959Z","shell.execute_reply.started":"2023-07-28T15:17:30.639727Z","shell.execute_reply":"2023-07-28T15:17:30.639749Z"},"trusted":true},"outputs":[],"execution_count":null}]}