{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"<h1>Combining models together will hopefully create something amazing for your score</h1>","metadata":{}},{"cell_type":"markdown","source":"This notebook is inspired by the great notebook: https://www.kaggle.com/code/irohith/aslfr-ctc-based-on-prev-comp-1st-place/comments with author is @irohith","metadata":{}},{"cell_type":"code","source":"import 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","metadata":{},"execution_count":null,"outputs":[]},{"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\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":"2023-08-07T15:40:53.981875Z","iopub.execute_input":"2023-08-07T15:40:53.982296Z","iopub.status.idle":"2023-08-07T15:40:54.179706Z","shell.execute_reply.started":"2023-08-07T15:40:53.982262Z","shell.execute_reply":"2023-08-07T15:40:54.178665Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2023-08-07T15:41:01.724472Z","iopub.execute_input":"2023-08-07T15:41:01.724879Z","iopub.status.idle":"2023-08-07T15:41:05.241346Z","shell.execute_reply.started":"2023-08-07T15:41:01.724845Z","shell.execute_reply":"2023-08-07T15:41:05.240297Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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    hand = tf.concat([rhand, lhand], axis=1)\n    hand = tf.where(tf.math.is_nan(hand), 0.0, hand)\n    mask = tf.math.not_equal(tf.reduce_sum(hand, axis=[1, 2]), 0.0)\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):\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)\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":"2023-08-07T15:41:13.230478Z","iopub.execute_input":"2023-08-07T15:41:13.230882Z","iopub.status.idle":"2023-08-07T15:41:16.216366Z","shell.execute_reply.started":"2023-08-07T15:41:13.230843Z","shell.execute_reply":"2023-08-07T15:41:16.215442Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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\n\ndef pre_process_fn(lip, rhand, lhand, rpose, lpose, phrase):\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\n    \ntffiles = [f\"/kaggle/input/aslfr-dataset-tfrecords/tfds/{file_id}.tfrecord\" for file_id in df.file_id.unique()]\nval_len = 1#int(0.05 * len(pqfiles))\ntrain_batch_size = 32\nval_batch_size = 32\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":"2023-08-07T15:41:22.567679Z","iopub.execute_input":"2023-08-07T15:41:22.568753Z","iopub.status.idle":"2023-08-07T15:41:23.424956Z","shell.execute_reply.started":"2023-08-07T15:41:22.568715Z","shell.execute_reply":"2023-08-07T15:41:23.423811Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class 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, \n        kernel_size=17,\n        dilation_rate=1,\n        use_bias=False,\n        depthwise_initializer='glorot_uniform',\n        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(\n                            kernel_size,\n                            strides=1,\n                            dilation_rate=dilation_rate,\n                            padding='valid',\n                            use_bias=use_bias,\n                            depthwise_initializer=depthwise_initializer,\n                            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,\n          kernel_size,\n          dilation_rate=1,\n          drop_rate=0.0,\n          expand_ratio=2,\n          se_ratio=0.25,\n          activation='swish',\n          name=None):\n    '''\n    efficient conv1d block, @hoyso48\n    '''\n    if name is None:\n        name = str(tf.keras.backend.get_uid(\"mbblock\"))\n    # Expansion phase\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(\n            channels_expand,\n            use_bias=True,\n            activation=activation,\n            name=name + '_expand_conv')(inputs)\n\n        # Depthwise Convolution\n        x = CausalDWConv1D(kernel_size,\n            dilation_rate=dilation_rate,\n            use_bias=False,\n            name=name + '_dwconv')(x)\n\n        x = tf.keras.layers.BatchNormalization(momentum=0.95, name=name + '_bn')(x)\n\n        x  = ECA()(x)\n\n        x = tf.keras.layers.Dense(\n            channel_size,\n            use_bias=True,\n            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        return x\n\n    return apply\n\nclass MultiHeadSelfAttention(tf.keras.layers.Layer):\n    def __init__(self, dim=256, 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\n\ndef TransformerBlock(dim=256, num_heads=6, expand=4, attn_dropout=0.2, drop_rate=0.2, activation='swish'):\n    def apply(inputs):\n        x = inputs\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(drop_rate, noise_shape=(None,1,1))(x)\n        x = tf.keras.layers.Add()([inputs, x])\n        attn_out = x\n\n        x = tf.keras.layers.LayerNormalization(epsilon=1e-6)(x)\n        x = tf.keras.layers.Dense(dim*expand, use_bias=False, activation=activation)(x)\n        x = tf.keras.layers.Dense(dim, use_bias=False)(x)\n        x = tf.keras.layers.Dropout(drop_rate, noise_shape=(None,1,1))(x)\n        x = tf.keras.layers.Add()([attn_out, x])\n        return x\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(\n          [tf.math.sin(angle_rads), tf.math.cos(angle_rads)],\n          axis=-1)\n        return pos_encoding","metadata":{"execution":{"iopub.status.busy":"2023-08-07T15:41:36.451885Z","iopub.execute_input":"2023-08-07T15:41:36.452329Z","iopub.status.idle":"2023-08-07T15:41:36.491148Z","shell.execute_reply.started":"2023-08-07T15:41:36.452291Z","shell.execute_reply":"2023-08-07T15:41:36.489743Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2023-08-07T15:41:43.965422Z","iopub.execute_input":"2023-08-07T15:41:43.966511Z","iopub.status.idle":"2023-08-07T15:41:43.973277Z","shell.execute_reply.started":"2023-08-07T15:41:43.966472Z","shell.execute_reply":"2023-08-07T15:41:43.972162Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_model(dim = 384):\n    inp = tf.keras.Input(INPUT_SHAPE)\n    \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) + positional_encoding(INPUT_SHAPE[0], dim)\n    x = tf.keras.layers.BatchNormalization(momentum=0.95,name='stem_bn')(x)\n\n    x = Conv1DBlock(dim, 11, drop_rate=0.4)(x)\n    x = Conv1DBlock(dim,  5, drop_rate=0.4)(x)\n    x = Conv1DBlock(dim,  3, drop_rate=0.4)(x)\n    x = TransformerBlock(dim, expand=2)(x)\n\n    x = Conv1DBlock(dim, 11, drop_rate=0.4)(x)\n    x = Conv1DBlock(dim,  5, drop_rate=0.4)(x)\n    x = Conv1DBlock(dim,  3, drop_rate=0.4)(x)\n    x = TransformerBlock(dim, expand=2)(x)\n\n    x = Conv1DBlock(dim, 11, drop_rate=0.4)(x)\n    x = Conv1DBlock(dim,  5, drop_rate=0.4)(x)\n    x = Conv1DBlock(dim,  3, drop_rate=0.4)(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 = tf.keras.layers.Dense(len(char_to_num))(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","metadata":{"execution":{"iopub.status.busy":"2023-08-07T15:54:43.638982Z","iopub.execute_input":"2023-08-07T15:54:43.639426Z","iopub.status.idle":"2023-08-07T15:54:43.653138Z","shell.execute_reply.started":"2023-08-07T15:54:43.63939Z","shell.execute_reply":"2023-08-07T15:54:43.6523Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h2>Read some pretrained models</h2>","metadata":{}},{"cell_type":"code","source":"tf.keras.backend.clear_session()\n\nmodels_path = [\n              '/kaggle/input/conv-2-models/conv/aug/model-1.h5',\n               '/kaggle/input/conv-2-models/conv/baseline-0.69/model.h5'\n              ]\nmodels = [get_model() for _ in models_path]\nfor model,path in zip(models,models_path):\n    model.load_weights(path)\nmodels[0].summary()","metadata":{"execution":{"iopub.status.busy":"2023-08-07T15:54:50.348775Z","iopub.execute_input":"2023-08-07T15:54:50.349202Z","iopub.status.idle":"2023-08-07T15:54:55.903909Z","shell.execute_reply.started":"2023-08-07T15:54:50.349168Z","shell.execute_reply":"2023-08-07T15:54:55.902766Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2023-08-07T15:42:51.69094Z","iopub.execute_input":"2023-08-07T15:42:51.69132Z","iopub.status.idle":"2023-08-07T15:42:51.700713Z","shell.execute_reply.started":"2023-08-07T15:42:51.691291Z","shell.execute_reply":"2023-08-07T15:42:51.699594Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"N_EPOCHS = 50\nN_WARMUP_EPOCHS = 10\nLR_MAX = 1e-3\nWD_RATIO = 0.05\nWARMUP_METHOD = \"exp\"","metadata":{"execution":{"iopub.status.busy":"2023-08-07T15:42:58.841101Z","iopub.execute_input":"2023-08-07T15:42:58.841502Z","iopub.status.idle":"2023-08-07T15:42:58.847074Z","shell.execute_reply.started":"2023-08-07T15:42:58.841471Z","shell.execute_reply":"2023-08-07T15:42:58.84588Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class TFLiteModel(tf.Module):\n    def __init__(self, models):\n        super(TFLiteModel, self).__init__()\n        self.models = models\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_process0(x)\n        x = pre_process1(*x)\n        x = tf.reshape(x, INPUT_SHAPE)\n        x = x[None]\n        # Ensemble by calculate the sum of the probabilities of the classes and get the class that corresponds to the largest sum\n        outputs = [tf.expand_dims(model(x, training=False), axis=-1) for model in self.models]\n        outputs = tf.concat(outputs, axis=-1)\n        outputs = tf.math.reduce_sum(outputs, axis=-1)\n        x = outputs[0]\n        x = decode_phrase(x)\n        x = tf.cond(tf.shape(x)[0] == 0, lambda: tf.zeros(1, tf.int64), lambda: tf.identity(x))\n        x = tf.one_hot(x, 59)\n        return {'outputs': x}\n\ntflitemodel_base = TFLiteModel(models)\ntflitemodel_base(frames)[\"outputs\"].shape","metadata":{"execution":{"iopub.status.busy":"2023-08-07T15:43:09.202436Z","iopub.execute_input":"2023-08-07T15:43:09.203363Z","iopub.status.idle":"2023-08-07T15:43:13.911984Z","shell.execute_reply.started":"2023-08-07T15:43:09.203323Z","shell.execute_reply":"2023-08-07T15:43:13.911113Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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]\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":"2023-08-07T15:43:18.288294Z","iopub.execute_input":"2023-08-07T15:43:18.288782Z","iopub.status.idle":"2023-08-07T15:44:52.314503Z","shell.execute_reply.started":"2023-08-07T15:43:18.28874Z","shell.execute_reply":"2023-08-07T15:44:52.312625Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2023-08-07T15:45:17.5626Z","iopub.execute_input":"2023-08-07T15:45:17.56303Z","iopub.status.idle":"2023-08-07T15:45:17.608751Z","shell.execute_reply.started":"2023-08-07T15:45:17.562995Z","shell.execute_reply":"2023-08-07T15:45:17.607603Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2023-08-07T15:45:27.145512Z","iopub.execute_input":"2023-08-07T15:45:27.145997Z","iopub.status.idle":"2023-08-07T15:45:32.286602Z","shell.execute_reply.started":"2023-08-07T15:45:27.14596Z","shell.execute_reply":"2023-08-07T15:45:32.285576Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2023-08-07T15:45:34.986184Z","iopub.execute_input":"2023-08-07T15:45:34.986586Z","iopub.status.idle":"2023-08-07T15:48:45.579057Z","shell.execute_reply.started":"2023-08-07T15:45:34.986556Z","shell.execute_reply":"2023-08-07T15:48:45.578234Z"},"trusted":true},"execution_count":null,"outputs":[]}]}