{"cells":[{"metadata":{},"cell_type":"markdown","source":"**Efficient-Net Code from this github repo: https://github.com/lukemelas/EfficientNet-PyTorch**"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"\"\"\"\nThis file contains helper functions for building the model and for loading model parameters.\nThese helper functions are built to mirror those in the official TensorFlow implementation.\n\"\"\"\n\nimport re\nimport math\nimport collections\nfrom functools import partial\nimport torch\nfrom torch import nn\nfrom torch.nn import functional as F\nfrom torch.utils import model_zoo\n\n########################################################################\n############### HELPERS FUNCTIONS FOR MODEL ARCHITECTURE ###############\n########################################################################\n\n\n# Parameters for the entire model (stem, all blocks, and head)\nGlobalParams = collections.namedtuple('GlobalParams', [\n    'batch_norm_momentum', 'batch_norm_epsilon', 'dropout_rate',\n    'num_classes', 'width_coefficient', 'depth_coefficient',\n    'depth_divisor', 'min_depth', 'drop_connect_rate', 'image_size'])\n\n# Parameters for an individual model block\nBlockArgs = collections.namedtuple('BlockArgs', [\n    'kernel_size', 'num_repeat', 'input_filters', 'output_filters',\n    'expand_ratio', 'id_skip', 'stride', 'se_ratio'])\n\n# Change namedtuple defaults\nGlobalParams.__new__.__defaults__ = (None,) * len(GlobalParams._fields)\nBlockArgs.__new__.__defaults__ = (None,) * len(BlockArgs._fields)\n\n\nclass SwishImplementation(torch.autograd.Function):\n    @staticmethod\n    def forward(ctx, i):\n        result = i * torch.sigmoid(i)\n        ctx.save_for_backward(i)\n        return result\n\n    @staticmethod\n    def backward(ctx, grad_output):\n        i = ctx.saved_variables[0]\n        sigmoid_i = torch.sigmoid(i)\n        return grad_output * (sigmoid_i * (1 + i * (1 - sigmoid_i)))\n\n\nclass MemoryEfficientSwish(nn.Module):\n    def forward(self, x):\n        return SwishImplementation.apply(x)\n\nclass Swish(nn.Module):\n    def forward(self, x):\n        return x * torch.sigmoid(x)\n\n\ndef round_filters(filters, global_params):\n    \"\"\" Calculate and round number of filters based on depth multiplier. \"\"\"\n    multiplier = global_params.width_coefficient\n    if not multiplier:\n        return filters\n    divisor = global_params.depth_divisor\n    min_depth = global_params.min_depth\n    filters *= multiplier\n    min_depth = min_depth or divisor\n    new_filters = max(min_depth, int(filters + divisor / 2) // divisor * divisor)\n    if new_filters < 0.9 * filters:  # prevent rounding by more than 10%\n        new_filters += divisor\n    return int(new_filters)\n\n\ndef round_repeats(repeats, global_params):\n    \"\"\" Round number of filters based on depth multiplier. \"\"\"\n    multiplier = global_params.depth_coefficient\n    if not multiplier:\n        return repeats\n    return int(math.ceil(multiplier * repeats))\n\n\ndef drop_connect(inputs, p, training):\n    \"\"\" Drop connect. \"\"\"\n    if not training: return inputs\n    batch_size = inputs.shape[0]\n    keep_prob = 1 - p\n    random_tensor = keep_prob\n    random_tensor += torch.rand([batch_size, 1, 1, 1], dtype=inputs.dtype, device=inputs.device)\n    binary_tensor = torch.floor(random_tensor)\n    output = inputs / keep_prob * binary_tensor\n    return output\n\n\ndef get_same_padding_conv2d(image_size=None):\n    \"\"\" Chooses static padding if you have specified an image size, and dynamic padding otherwise.\n        Static padding is necessary for ONNX exporting of models. \"\"\"\n    if image_size is None:\n        return Conv2dDynamicSamePadding\n    else:\n        return partial(Conv2dStaticSamePadding, image_size=image_size)\n\n\nclass Conv2dDynamicSamePadding(nn.Conv2d):\n    \"\"\" 2D Convolutions like TensorFlow, for a dynamic image size \"\"\"\n\n    def __init__(self, in_channels, out_channels, kernel_size, stride=1, dilation=1, groups=1, bias=True):\n        super().__init__(in_channels, out_channels, kernel_size, stride, 0, dilation, groups, bias)\n        self.stride = self.stride if len(self.stride) == 2 else [self.stride[0]] * 2\n\n    def forward(self, x):\n        ih, iw = x.size()[-2:]\n        kh, kw = self.weight.size()[-2:]\n        sh, sw = self.stride\n        oh, ow = math.ceil(ih / sh), math.ceil(iw / sw)\n        pad_h = max((oh - 1) * self.stride[0] + (kh - 1) * self.dilation[0] + 1 - ih, 0)\n        pad_w = max((ow - 1) * self.stride[1] + (kw - 1) * self.dilation[1] + 1 - iw, 0)\n        if pad_h > 0 or pad_w > 0:\n            x = F.pad(x, [pad_w // 2, pad_w - pad_w // 2, pad_h // 2, pad_h - pad_h // 2])\n        return F.conv2d(x, self.weight, self.bias, self.stride, self.padding, self.dilation, self.groups)\n\n\nclass Conv2dStaticSamePadding(nn.Conv2d):\n    \"\"\" 2D Convolutions like TensorFlow, for a fixed image size\"\"\"\n\n    def __init__(self, in_channels, out_channels, kernel_size, image_size=None, **kwargs):\n        super().__init__(in_channels, out_channels, kernel_size, **kwargs)\n        self.stride = self.stride if len(self.stride) == 2 else [self.stride[0]] * 2\n\n        # Calculate padding based on image size and save it\n        assert image_size is not None\n        ih, iw = image_size if type(image_size) == list else [image_size, image_size]\n        kh, kw = self.weight.size()[-2:]\n        sh, sw = self.stride\n        oh, ow = math.ceil(ih / sh), math.ceil(iw / sw)\n        pad_h = max((oh - 1) * self.stride[0] + (kh - 1) * self.dilation[0] + 1 - ih, 0)\n        pad_w = max((ow - 1) * self.stride[1] + (kw - 1) * self.dilation[1] + 1 - iw, 0)\n        if pad_h > 0 or pad_w > 0:\n            self.static_padding = nn.ZeroPad2d((pad_w // 2, pad_w - pad_w // 2, pad_h // 2, pad_h - pad_h // 2))\n        else:\n            self.static_padding = Identity()\n\n    def forward(self, x):\n        x = self.static_padding(x)\n        x = F.conv2d(x, self.weight, self.bias, self.stride, self.padding, self.dilation, self.groups)\n        return x\n\n\nclass Identity(nn.Module):\n    def __init__(self, ):\n        super(Identity, self).__init__()\n\n    def forward(self, input):\n        return input\n\n\n########################################################################\n############## HELPERS FUNCTIONS FOR LOADING MODEL PARAMS ##############\n########################################################################\n\n\ndef efficientnet_params(model_name):\n    \"\"\" Map EfficientNet model name to parameter coefficients. \"\"\"\n    params_dict = {\n        # Coefficients:   width,depth,res,dropout\n        'efficientnet-b0': (1.0, 1.0, 224, 0.2),\n        'efficientnet-b1': (1.0, 1.1, 240, 0.2),\n        'efficientnet-b2': (1.1, 1.2, 260, 0.3),\n        'efficientnet-b3': (1.2, 1.4, 300, 0.3),\n        'efficientnet-b4': (1.4, 1.8, 380, 0.4),\n        'efficientnet-b5': (1.6, 2.2, 456, 0.4),\n        'efficientnet-b6': (1.8, 2.6, 528, 0.5),\n        'efficientnet-b7': (2.0, 3.1, 600, 0.5),\n        'efficientnet-b8': (2.2, 3.6, 672, 0.5),\n        'efficientnet-l2': (4.3, 5.3, 800, 0.5),\n    }\n    return params_dict[model_name]\n\n\nclass BlockDecoder(object):\n    \"\"\" Block Decoder for readability, straight from the official TensorFlow repository \"\"\"\n\n    @staticmethod\n    def _decode_block_string(block_string):\n        \"\"\" Gets a block through a string notation of arguments. \"\"\"\n        assert isinstance(block_string, str)\n\n        ops = block_string.split('_')\n        options = {}\n        for op in ops:\n            splits = re.split(r'(\\d.*)', op)\n            if len(splits) >= 2:\n                key, value = splits[:2]\n                options[key] = value\n\n        # Check stride\n        assert (('s' in options and len(options['s']) == 1) or\n                (len(options['s']) == 2 and options['s'][0] == options['s'][1]))\n\n        return BlockArgs(\n            kernel_size=int(options['k']),\n            num_repeat=int(options['r']),\n            input_filters=int(options['i']),\n            output_filters=int(options['o']),\n            expand_ratio=int(options['e']),\n            id_skip=('noskip' not in block_string),\n            se_ratio=float(options['se']) if 'se' in options else None,\n            stride=[int(options['s'][0])])\n\n    @staticmethod\n    def _encode_block_string(block):\n        \"\"\"Encodes a block to a string.\"\"\"\n        args = [\n            'r%d' % block.num_repeat,\n            'k%d' % block.kernel_size,\n            's%d%d' % (block.strides[0], block.strides[1]),\n            'e%s' % block.expand_ratio,\n            'i%d' % block.input_filters,\n            'o%d' % block.output_filters\n        ]\n        if 0 < block.se_ratio <= 1:\n            args.append('se%s' % block.se_ratio)\n        if block.id_skip is False:\n            args.append('noskip')\n        return '_'.join(args)\n\n    @staticmethod\n    def decode(string_list):\n        \"\"\"\n        Decodes a list of string notations to specify blocks inside the network.\n        :param string_list: a list of strings, each string is a notation of block\n        :return: a list of BlockArgs namedtuples of block args\n        \"\"\"\n        assert isinstance(string_list, list)\n        blocks_args = []\n        for block_string in string_list:\n            blocks_args.append(BlockDecoder._decode_block_string(block_string))\n        return blocks_args\n\n    @staticmethod\n    def encode(blocks_args):\n        \"\"\"\n        Encodes a list of BlockArgs to a list of strings.\n        :param blocks_args: a list of BlockArgs namedtuples of block args\n        :return: a list of strings, each string is a notation of block\n        \"\"\"\n        block_strings = []\n        for block in blocks_args:\n            block_strings.append(BlockDecoder._encode_block_string(block))\n        return block_strings\n\n\ndef efficientnet(width_coefficient=None, depth_coefficient=None, dropout_rate=0.2,\n                 drop_connect_rate=0.2, image_size=None, num_classes=1000):\n    \"\"\" Creates a efficientnet model. \"\"\"\n\n    blocks_args = [\n        'r1_k3_s11_e1_i32_o16_se0.25', 'r2_k3_s22_e6_i16_o24_se0.25',\n        'r2_k5_s22_e6_i24_o40_se0.25', 'r3_k3_s22_e6_i40_o80_se0.25',\n        'r3_k5_s11_e6_i80_o112_se0.25', 'r4_k5_s22_e6_i112_o192_se0.25',\n        'r1_k3_s11_e6_i192_o320_se0.25',\n    ]\n    blocks_args = BlockDecoder.decode(blocks_args)\n\n    global_params = GlobalParams(\n        batch_norm_momentum=0.99,\n        batch_norm_epsilon=1e-3,\n        dropout_rate=dropout_rate,\n        drop_connect_rate=drop_connect_rate,\n        # data_format='channels_last',  # removed, this is always true in PyTorch\n        num_classes=num_classes,\n        width_coefficient=width_coefficient,\n        depth_coefficient=depth_coefficient,\n        depth_divisor=8,\n        min_depth=None,\n        image_size=image_size,\n    )\n\n    return blocks_args, global_params\n\n\ndef get_model_params(model_name, override_params):\n    \"\"\" Get the block args and global params for a given model \"\"\"\n    if model_name.startswith('efficientnet'):\n        w, d, s, p = efficientnet_params(model_name)\n        # note: all models have drop connect rate = 0.2\n        blocks_args, global_params = efficientnet(\n            width_coefficient=w, depth_coefficient=d, dropout_rate=p, image_size=s)\n    else:\n        raise NotImplementedError('model name is not pre-defined: %s' % model_name)\n    if override_params:\n        # ValueError will be raised here if override_params has fields not included in global_params.\n        global_params = global_params._replace(**override_params)\n    return blocks_args, global_params\n\n\nurl_map = {\n    'efficientnet-b0': 'https://publicmodels.blob.core.windows.net/container/aa/efficientnet-b0-355c32eb.pth',\n    'efficientnet-b1': 'https://publicmodels.blob.core.windows.net/container/aa/efficientnet-b1-f1951068.pth',\n    'efficientnet-b2': 'https://publicmodels.blob.core.windows.net/container/aa/efficientnet-b2-8bb594d6.pth',\n    'efficientnet-b3': 'https://publicmodels.blob.core.windows.net/container/aa/efficientnet-b3-5fb5a3c3.pth',\n    'efficientnet-b4': 'https://publicmodels.blob.core.windows.net/container/aa/efficientnet-b4-6ed6700e.pth',\n    'efficientnet-b5': 'https://publicmodels.blob.core.windows.net/container/aa/efficientnet-b5-b6417697.pth',\n    'efficientnet-b6': 'https://publicmodels.blob.core.windows.net/container/aa/efficientnet-b6-c76e70fd.pth',\n    'efficientnet-b7': 'https://publicmodels.blob.core.windows.net/container/aa/efficientnet-b7-dcc49843.pth',\n}\n\n\nurl_map_advprop = {\n    'efficientnet-b0': 'https://publicmodels.blob.core.windows.net/container/advprop/efficientnet-b0-b64d5a18.pth', \n    'efficientnet-b1': 'https://publicmodels.blob.core.windows.net/container/advprop/efficientnet-b1-0f3ce85a.pth',\n    'efficientnet-b2': 'https://publicmodels.blob.core.windows.net/container/advprop/efficientnet-b2-6e9d97e5.pth',\n    'efficientnet-b3': 'https://publicmodels.blob.core.windows.net/container/advprop/efficientnet-b3-cdd7c0f4.pth',\n    'efficientnet-b4': 'https://publicmodels.blob.core.windows.net/container/advprop/efficientnet-b4-44fb3a87.pth',\n    'efficientnet-b5': 'https://publicmodels.blob.core.windows.net/container/advprop/efficientnet-b5-86493f6b.pth',\n    'efficientnet-b6': 'https://publicmodels.blob.core.windows.net/container/advprop/efficientnet-b6-ac80338e.pth',\n    'efficientnet-b7': 'https://publicmodels.blob.core.windows.net/container/advprop/efficientnet-b7-4652b6dd.pth',\n    'efficientnet-b8': 'https://publicmodels.blob.core.windows.net/container/advprop/efficientnet-b8-22a8fe65.pth',\n}\n\n\ndef load_pretrained_weights(model, model_name, load_fc=True, advprop=False):\n    \"\"\" Loads pretrained weights, and downloads if loading for the first time. \"\"\"\n    # AutoAugment or Advprop (different preprocessing)\n    url_map_ = url_map_advprop if advprop else url_map\n    state_dict = model_zoo.load_url(url_map_[model_name])\n    if load_fc:\n        model.load_state_dict(state_dict)\n    else:\n        state_dict.pop('_fc.weight')\n        state_dict.pop('_fc.bias')\n        res = model.load_state_dict(state_dict, strict=False)\n        assert set(res.missing_keys) == set(['_fc.weight', '_fc.bias']), 'issue loading pretrained weights'\n    print('Loaded pretrained weights for {}'.format(model_name))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import torch\nfrom torch import nn\nfrom torch.nn import functional as F\n\nclass MBConvBlock(nn.Module):\n    \"\"\"\n    Mobile Inverted Residual Bottleneck Block\n    Args:\n        block_args (namedtuple): BlockArgs, see above\n        global_params (namedtuple): GlobalParam, see above\n    Attributes:\n        has_se (bool): Whether the block contains a Squeeze and Excitation layer.\n    \"\"\"\n\n    def __init__(self, block_args, global_params):\n        super().__init__()\n        self._block_args = block_args\n        self._bn_mom = 1 - global_params.batch_norm_momentum\n        self._bn_eps = global_params.batch_norm_epsilon\n        self.has_se = (self._block_args.se_ratio is not None) and (0 < self._block_args.se_ratio <= 1)\n        self.id_skip = block_args.id_skip  # skip connection and drop connect\n\n        # Get static or dynamic convolution depending on image size\n        Conv2d = get_same_padding_conv2d(image_size=global_params.image_size)\n\n        # Expansion phase\n        inp = self._block_args.input_filters  # number of input channels\n        oup = self._block_args.input_filters * self._block_args.expand_ratio  # number of output channels\n        if self._block_args.expand_ratio != 1:\n            self._expand_conv = Conv2d(in_channels=inp, out_channels=oup, kernel_size=1, bias=False)\n            self._bn0 = nn.BatchNorm2d(num_features=oup, momentum=self._bn_mom, eps=self._bn_eps)\n\n        # Depthwise convolution phase\n        k = self._block_args.kernel_size\n        s = self._block_args.stride\n        self._depthwise_conv = Conv2d(\n            in_channels=oup, out_channels=oup, groups=oup,  # groups makes it depthwise\n            kernel_size=k, stride=s, bias=False)\n        self._bn1 = nn.BatchNorm2d(num_features=oup, momentum=self._bn_mom, eps=self._bn_eps)\n\n        # Squeeze and Excitation layer, if desired\n        if self.has_se:\n            num_squeezed_channels = max(1, int(self._block_args.input_filters * self._block_args.se_ratio))\n            self._se_reduce = Conv2d(in_channels=oup, out_channels=num_squeezed_channels, kernel_size=1)\n            self._se_expand = Conv2d(in_channels=num_squeezed_channels, out_channels=oup, kernel_size=1)\n\n        # Output phase\n        final_oup = self._block_args.output_filters\n        self._project_conv = Conv2d(in_channels=oup, out_channels=final_oup, kernel_size=1, bias=False)\n        self._bn2 = nn.BatchNorm2d(num_features=final_oup, momentum=self._bn_mom, eps=self._bn_eps)\n        self._swish = MemoryEfficientSwish()\n\n    def forward(self, inputs, drop_connect_rate=None):\n        \"\"\"\n        :param inputs: input tensor\n        :param drop_connect_rate: drop connect rate (float, between 0 and 1)\n        :return: output of block\n        \"\"\"\n\n        # Expansion and Depthwise Convolution\n        x = inputs\n        if self._block_args.expand_ratio != 1:\n            x = self._swish(self._bn0(self._expand_conv(inputs)))\n        x = self._swish(self._bn1(self._depthwise_conv(x)))\n\n        # Squeeze and Excitation\n        if self.has_se:\n            x_squeezed = F.adaptive_avg_pool2d(x, 1)\n            x_squeezed = self._se_expand(self._swish(self._se_reduce(x_squeezed)))\n            x = torch.sigmoid(x_squeezed) * x\n\n        x = self._bn2(self._project_conv(x))\n\n        # Skip connection and drop connect\n        input_filters, output_filters = self._block_args.input_filters, self._block_args.output_filters\n        if self.id_skip and self._block_args.stride == 1 and input_filters == output_filters:\n            if drop_connect_rate:\n                x = drop_connect(x, p=drop_connect_rate, training=self.training)\n            x = x + inputs  # skip connection\n        return x\n\n    def set_swish(self, memory_efficient=True):\n        \"\"\"Sets swish function as memory efficient (for training) or standard (for export)\"\"\"\n        self._swish = MemoryEfficientSwish() if memory_efficient else Swish()\n\n\nclass EfficientNet(nn.Module):\n    \"\"\"\n    An EfficientNet model. Most easily loaded with the .from_name or .from_pretrained methods\n    Args:\n        blocks_args (list): A list of BlockArgs to construct blocks\n        global_params (namedtuple): A set of GlobalParams shared between blocks\n    Example:\n        model = EfficientNet.from_pretrained('efficientnet-b0')\n    \"\"\"\n\n    def __init__(self, blocks_args=None, global_params=None):\n        super().__init__()\n        assert isinstance(blocks_args, list), 'blocks_args should be a list'\n        assert len(blocks_args) > 0, 'block args must be greater than 0'\n        self._global_params = global_params\n        self._blocks_args = blocks_args\n\n        # Get static or dynamic convolution depending on image size\n        Conv2d = get_same_padding_conv2d(image_size=global_params.image_size)\n\n        # Batch norm parameters\n        bn_mom = 1 - self._global_params.batch_norm_momentum\n        bn_eps = self._global_params.batch_norm_epsilon\n\n        # Stem\n        in_channels = 3  # rgb\n        out_channels = round_filters(32, self._global_params)  # number of output channels\n        self._conv_stem = Conv2d(in_channels, out_channels, kernel_size=3, stride=2, bias=False)\n        self._bn0 = nn.BatchNorm2d(num_features=out_channels, momentum=bn_mom, eps=bn_eps)\n\n        # Build blocks\n        self._blocks = nn.ModuleList([])\n        for block_args in self._blocks_args:\n\n            # Update block input and output filters based on depth multiplier.\n            block_args = block_args._replace(\n                input_filters=round_filters(block_args.input_filters, self._global_params),\n                output_filters=round_filters(block_args.output_filters, self._global_params),\n                num_repeat=round_repeats(block_args.num_repeat, self._global_params)\n            )\n\n            # The first block needs to take care of stride and filter size increase.\n            self._blocks.append(MBConvBlock(block_args, self._global_params))\n            if block_args.num_repeat > 1:\n                block_args = block_args._replace(input_filters=block_args.output_filters, stride=1)\n            for _ in range(block_args.num_repeat - 1):\n                self._blocks.append(MBConvBlock(block_args, self._global_params))\n\n        # Head\n        in_channels = block_args.output_filters  # output of final block\n        out_channels = round_filters(1280, self._global_params)\n        self._conv_head = Conv2d(in_channels, out_channels, kernel_size=1, bias=False)\n        self._bn1 = nn.BatchNorm2d(num_features=out_channels, momentum=bn_mom, eps=bn_eps)\n\n        # Final linear layer\n        self._avg_pooling = nn.AdaptiveAvgPool2d(1)\n        self._dropout = nn.Dropout(self._global_params.dropout_rate)\n        self._fc = nn.Linear(out_channels, self._global_params.num_classes)\n        self._swish = MemoryEfficientSwish()\n\n    def set_swish(self, memory_efficient=True):\n        \"\"\"Sets swish function as memory efficient (for training) or standard (for export)\"\"\"\n        self._swish = MemoryEfficientSwish() if memory_efficient else Swish()\n        for block in self._blocks:\n            block.set_swish(memory_efficient)\n\n\n    def extract_features(self, inputs):\n        \"\"\" Returns output of the final convolution layer \"\"\"\n\n        # Stem\n        x = self._swish(self._bn0(self._conv_stem(inputs)))\n\n        # Blocks\n        for idx, block in enumerate(self._blocks):\n            drop_connect_rate = self._global_params.drop_connect_rate\n            if drop_connect_rate:\n                drop_connect_rate *= float(idx) / len(self._blocks)\n            x = block(x, drop_connect_rate=drop_connect_rate)\n\n        # Head\n        x = self._swish(self._bn1(self._conv_head(x)))\n\n        return x\n\n    def forward(self, inputs):\n        \"\"\" Calls extract_features to extract features, applies final linear layer, and returns logits. \"\"\"\n        bs = inputs.size(0)\n        # Convolution layers\n        x = self.extract_features(inputs)\n\n        # Pooling and final linear layer\n        x = self._avg_pooling(x)\n        x = x.view(bs, -1)\n        x = self._dropout(x)\n        x = self._fc(x)\n        return x\n\n    @classmethod\n    def from_name(cls, model_name, override_params=None):\n        cls._check_model_name_is_valid(model_name)\n        blocks_args, global_params = get_model_params(model_name, override_params)\n        return cls(blocks_args, global_params)\n\n    @classmethod\n    def from_pretrained(cls, model_name, advprop=False, num_classes=1000, in_channels=3):\n        model = cls.from_name(model_name, override_params={'num_classes': num_classes})\n        load_pretrained_weights(model, model_name, load_fc=(num_classes == 1000), advprop=advprop)\n        if in_channels != 3:\n            Conv2d = get_same_padding_conv2d(image_size = model._global_params.image_size)\n            out_channels = round_filters(32, model._global_params)\n            model._conv_stem = Conv2d(in_channels, out_channels, kernel_size=3, stride=2, bias=False)\n        return model\n    \n    @classmethod\n    def get_image_size(cls, model_name):\n        cls._check_model_name_is_valid(model_name)\n        _, _, res, _ = efficientnet_params(model_name)\n        return res\n\n    @classmethod\n    def _check_model_name_is_valid(cls, model_name):\n        \"\"\" Validates model name. \"\"\" \n        valid_models = ['efficientnet-b'+str(i) for i in range(9)]\n        if model_name not in valid_models:\n            raise ValueError('model_name should be one of: ' + ', '.join(valid_models))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Import Libraries**"},{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom tqdm import tqdm\nimport os\nimport cv2\nimport torch\nfrom torch.utils.data import Dataset, DataLoader\nimport torch.nn as nn\nimport torchvision.models as tvm\nimport torch.nn.functional as F\nimport random","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Define Random State**"},{"metadata":{"trusted":true},"cell_type":"code","source":"def set_random_state(seed_value):\n    random.seed(seed_value)\n    torch.manual_seed(seed_value)\n    torch.cuda.manual_seed(seed_value)\n    os.environ['PYTHONHASHSEED'] = str(seed_value)\n    torch.backends.cudnn.deterministic = False\n    torch.backends.cudnn.benchmark = True\n    np.random.seed(seed_value)\n    \nset_random_state(4690)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Load Optimizer Script for Checkpoint Loading Purpose **"},{"metadata":{"trusted":true},"cell_type":"code","source":"import sys\npackage_path = '../input/myscripts/'\nsys.path.append(package_path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from bengali_optimizers import *","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Define Model Architecture**"},{"metadata":{"trusted":true},"cell_type":"code","source":"import torch\nimport torch.nn as nn\nimport torch.nn.functional as F\n            \nclass CNN_Model(nn.Module):\n    def __init__(self,model_name='efficientnet-b5',global_dim=2048):        \n        super(CNN_Model,self).__init__()\n            \n        self.cnn_backbone = EfficientNet.from_name(model_name)\n        self.cnn_backbone.set_swish(memory_efficient=False)\n                \n        self.cnn_head_grapheme_root = CNN_Head(168,global_dim,1024,512)\n        self.cnn_head_vowel_diacritic = CNN_Head(11,global_dim,1024,512)\n        self.cnn_head_consonant_diacritic = CNN_Head(7,global_dim,1024,512)                                                \n                        \n    def forward(self, x):\n        global_feat = self.cnn_backbone.extract_features(x)                              \n                \n        global_feat = (F.adaptive_avg_pool2d(global_feat,1)+F.adaptive_max_pool2d(global_feat,1))*0.5\n        global_feat = global_feat.view(global_feat.size(0), -1)\n            \n        grapheme_output = self.cnn_head_grapheme_root(global_feat)\n        vowel_diacritic_output = self.cnn_head_vowel_diacritic(global_feat)\n        consonant_diacritic_output = self.cnn_head_consonant_diacritic(global_feat)\n        \n        return grapheme_output,vowel_diacritic_output,consonant_diacritic_output\n\nclass CNN_Head(nn.Sequential):\n    def __init__(self, classes, input_dim, linear1_output_dim, linear2_output_dim,\n                 use_batch_norm=True, use_activation_function=False,\n                 global_dropout=0.0, lin1_dropout=0.0, lin2_dropout=0.00):\n        \n        super(CNN_Head, self).__init__()\n        \n        if global_dropout > 0.0:\n            self.add_module('drop_1',nn.Dropout(p=global_dropout,inplace=False))\n                \n        self.add_module('linear_1',nn.Linear(input_dim,linear1_output_dim))\n        \n        if use_batch_norm:\n            self.add_module('norm_1', nn.BatchNorm1d(linear1_output_dim))\n        \n        if use_activation_function:\n            self.add_module('activ_1',nn.ReLU(inplace=False))\n            \n        if lin1_dropout > 0.0:\n            self.add_module('drop_2',nn.Dropout(p=lin1_dropout,inplace=False))\n            \n        self.add_module('linear_2',nn.Linear(linear1_output_dim,linear2_output_dim))\n        \n        if use_batch_norm:\n            self.add_module('norm_2', nn.BatchNorm1d(linear2_output_dim))\n        \n        if use_activation_function:\n            self.add_module('activ_2',nn.ReLU(inplace=False))\n        \n        if lin2_dropout > 0.0:\n            self.add_module('drop_3',nn.Dropout(p=lin2_dropout,inplace=False))\n            \n        self.add_module('linear_final',nn.Linear(linear2_output_dim,classes))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Fold-1**"},{"metadata":{"trusted":true},"cell_type":"code","source":"model_1 = CNN_Model()\n\ncheckpoint_dict = torch.load('/kaggle/input/modelsubmission46/checkpoint_best_Average_recall.pth')\nmodel_1.load_state_dict(checkpoint_dict['Model_state_dict'])\nmodel_1 = model_1.cuda()\nmodel_1.eval()\n\nprint('Validation Average Recall {}  \\\n        \\nValidation Grapheme Root Recall {} \\\n        \\nValidation Vowel Diacritic Recall {} \\\n        \\nValidation Consonant Diacritic Recall {} \\\n        \\nValidation Loss {} '.format(checkpoint_dict['Current_average_recall'],checkpoint_dict['Current_grapheme_root_recall'],checkpoint_dict['Current_vowel_diacritic_recall'], \\\n                                    checkpoint_dict['Current_consonant_diacritic_recall'],checkpoint_dict['Current_val_Loss']))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Fold-2**"},{"metadata":{"trusted":true},"cell_type":"code","source":"model_2 = CNN_Model()\n\ncheckpoint_dict = torch.load('/kaggle/input/modelsubmission58/checkpoint_best_Average_recall.pth')\nmodel_2.load_state_dict(checkpoint_dict['Model_state_dict'])\nmodel_2 = model_2.cuda()\nmodel_2.eval()\n\nprint('Validation Average Recall {}  \\\n        \\nValidation Grapheme Root Recall {} \\\n        \\nValidation Vowel Diacritic Recall {} \\\n        \\nValidation Consonant Diacritic Recall {} \\\n        \\nValidation Loss {} '.format(checkpoint_dict['Current_average_recall'],checkpoint_dict['Current_grapheme_root_recall'],checkpoint_dict['Current_vowel_diacritic_recall'], \\\n                                    checkpoint_dict['Current_consonant_diacritic_recall'],checkpoint_dict['Current_val_Loss']))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Fold-3**"},{"metadata":{"trusted":true},"cell_type":"code","source":"model_3 = CNN_Model()\n\ncheckpoint_dict = torch.load('/kaggle/input/modelsubmission57/checkpoint_best_Average_recall.pth')\nmodel_3.load_state_dict(checkpoint_dict['Model_state_dict'])\nmodel_3 = model_3.cuda()\nmodel_3.eval()\n\nprint('Validation Average Recall {}  \\\n        \\nValidation Grapheme Root Recall {} \\\n        \\nValidation Vowel Diacritic Recall {} \\\n        \\nValidation Consonant Diacritic Recall {} \\\n        \\nValidation Loss {} '.format(checkpoint_dict['Current_average_recall'],checkpoint_dict['Current_grapheme_root_recall'],checkpoint_dict['Current_vowel_diacritic_recall'], \\\n                                    checkpoint_dict['Current_consonant_diacritic_recall'],checkpoint_dict['Current_val_Loss']))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Fold-4**"},{"metadata":{"trusted":true},"cell_type":"code","source":"model_4 = CNN_Model()\n\ncheckpoint_dict = torch.load('/kaggle/input/modelsubmission73/checkpoint_best_Average_recall.pth')\nmodel_4.load_state_dict(checkpoint_dict['Model_state_dict'])\nmodel_4 = model_4.cuda()\nmodel_4.eval()\n\nprint('Validation Average Recall {}  \\\n        \\nValidation Grapheme Root Recall {} \\\n        \\nValidation Vowel Diacritic Recall {} \\\n        \\nValidation Consonant Diacritic Recall {} \\\n        \\nValidation Loss {} '.format(checkpoint_dict['Current_average_recall'],checkpoint_dict['Current_grapheme_root_recall'],checkpoint_dict['Current_vowel_diacritic_recall'], \\\n                                    checkpoint_dict['Current_consonant_diacritic_recall'],checkpoint_dict['Current_val_Loss']))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Fold-5**"},{"metadata":{"trusted":true},"cell_type":"code","source":"model_5 = CNN_Model()\n\ncheckpoint_dict = torch.load('/kaggle/input/modelsubmission74/checkpoint_best_Average_recall.pth')\nmodel_5.load_state_dict(checkpoint_dict['Model_state_dict'])\nmodel_5 = model_5.cuda()\nmodel_5.eval()\n\nprint('Validation Average Recall {}  \\\n        \\nValidation Grapheme Root Recall {} \\\n        \\nValidation Vowel Diacritic Recall {} \\\n        \\nValidation Consonant Diacritic Recall {} \\\n        \\nValidation Loss {} '.format(checkpoint_dict['Current_average_recall'],checkpoint_dict['Current_grapheme_root_recall'],checkpoint_dict['Current_vowel_diacritic_recall'], \\\n                                    checkpoint_dict['Current_consonant_diacritic_recall'],checkpoint_dict['Current_val_Loss']))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Test-Dataloader**"},{"metadata":{"trusted":true},"cell_type":"code","source":"class BengaliAiDataset(Dataset):\n    def __init__(self, all_imgs):\n        super(BengaliAiDataset, self).__init__()               \n        self.all_imgs = all_imgs\n                    \n    def __len__(self):\n        return self.all_imgs.shape[0]\n            \n    def __getitem__(self, index): \n        img = self.all_imgs[index,:,:]\n        img = img[:,:,np.newaxis]\n        img = np.concatenate([img,img,img],axis=2)\n        img = (img/255).astype(np.float32)                \n        img = np.transpose(img, (2, 0, 1))\n        img = torch.from_numpy(img).float()                \n        return img","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"HEIGHT = 137\nWIDTH = 236\nTEST = ['/kaggle/input/bengaliai-cv19/test_image_data_0.parquet',\n        '/kaggle/input/bengaliai-cv19/test_image_data_1.parquet',\n        '/kaggle/input/bengaliai-cv19/test_image_data_2.parquet',\n        '/kaggle/input/bengaliai-cv19/test_image_data_3.parquet']\n\nall_grapheme_labels = []\nall_vowel_diacritic_labels = []\nall_consonant_diacritic_labels = []\n\ntorch.set_grad_enabled(False)                                \nwith torch.no_grad():\n    for fname in TEST:\n        df = pd.read_parquet(fname)\n        data = df.iloc[:, 1:].values.reshape(-1, HEIGHT, WIDTH).astype(np.uint8)\n        all_imgs = []\n        for idx in tqdm(range(len(df))):\n            img = data[idx].astype(np.uint8)\n            img = img[np.newaxis,...]\n            all_imgs.append(img)\n\n        all_imgs = np.concatenate(all_imgs,axis=0)\n        ds_test = BengaliAiDataset(all_imgs)\n        dl_test = DataLoader(ds_test, shuffle=False, batch_size=100, num_workers=4, pin_memory=True)\n\n        for i,(imgs) in enumerate(dl_test):\n            imgs = imgs.cuda()\n            \n            # fold 1\n            grapheme_output_1,vowel_diacritic_output_1,consonant_diacritic_output_1 = model_1(imgs)\n                        \n            # fold2\n            grapheme_output_2,vowel_diacritic_output_2,consonant_diacritic_output_2 = model_2(imgs)\n            \n            # fold 3\n            grapheme_output_3,vowel_diacritic_output_3,consonant_diacritic_output_3 = model_3(imgs)\n                       \n            # fold 4\n            grapheme_output_4,vowel_diacritic_output_4,consonant_diacritic_output_4 = model_4(imgs)\n                        \n            # fold5\n            grapheme_output_5,vowel_diacritic_output_5,consonant_diacritic_output_5 = model_5(imgs)\n                        \n            # all folds\n            grapheme_output = (grapheme_output_1+grapheme_output_2+grapheme_output_3+grapheme_output_4+grapheme_output_5)/5\n            vowel_diacritic_output = (vowel_diacritic_output_1+vowel_diacritic_output_2+vowel_diacritic_output_3+vowel_diacritic_output_4+vowel_diacritic_output_5)/5\n            consonant_diacritic_output = (consonant_diacritic_output_1+consonant_diacritic_output_2+consonant_diacritic_output_3+consonant_diacritic_output_4+consonant_diacritic_output_5)/5\n            \n            submission_grapheme_root_labels = torch.argmax(grapheme_output.clone(),dim=1)\n            submission_vowel_diacritic_labels = torch.argmax(vowel_diacritic_output.clone(),dim=1)\n            submission_consonant_diacritic_labels = torch.argmax(consonant_diacritic_output.clone(),dim=1)\n            \n            submission_grapheme_root_labels = submission_grapheme_root_labels.tolist()\n            submission_vowel_diacritic_labels = submission_vowel_diacritic_labels.tolist()\n            submission_consonant_diacritic_labels = submission_consonant_diacritic_labels.tolist()\n\n            all_grapheme_labels = all_grapheme_labels+submission_grapheme_root_labels\n            all_vowel_diacritic_labels = all_vowel_diacritic_labels+submission_vowel_diacritic_labels\n            all_consonant_diacritic_labels = all_consonant_diacritic_labels+submission_consonant_diacritic_labels","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Generate Submission CSV"},{"metadata":{"trusted":true},"cell_type":"code","source":"row_id = []\ntarget = []\nfor i in tqdm(range(len(all_vowel_diacritic_labels))):\n    row_id += [f'Test_{i}_grapheme_root', f'Test_{i}_vowel_diacritic',\n               f'Test_{i}_consonant_diacritic']\n    target += [all_grapheme_labels[i], all_vowel_diacritic_labels[i], all_consonant_diacritic_labels[i]]\nsubmission_df = pd.DataFrame({'row_id': row_id, 'target': target})\nsubmission_df.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}