add VIT

 .DS_Store
 logs/
+
+__pycache__
+
+*.log
+
+dataset/

+seed: 3407
+
+dataset:
+  name: 'CoordinatesData'
+  args:
+    data_root: '/Users/zhouweiqi/Downloads/gcfp/data/dataset'
+    train_anno_file: '/Users/zhouweiqi/Downloads/gcfp/data/dataset/train.csv'
+    val_anno_file: '/Users/zhouweiqi/Downloads/gcfp/data/dataset/valid.csv'
+
+dataloader:
+  batch_size: 32
+  num_workers: 4
+  pin_memory: true
+  shuffle: true
+
+model:
+  name: 'VisionTransformer'
+  args:
+    img_size: 224
+    patch_size: 16
+    in_c: 3
+    num_classes: 5
+    embed_dim: 8
+    depth: 12
+    num_heads: 12
+    mlp_ratio: 4.0
+    qkv_bias: true
+    qk_scale: none
+    representation_size: none
+    distilled: false 
+    drop_ratio: 0.
+    attn_drop_ratio: 0.
+    drop_path_ratio: 0.
+    norm_layer: none
+    act_layer: none
+
+solver:
+  name: 'VITSolver'
+  args:
+    epoch: 100
+
+  optimizer:
+    name: 'Adam'
+    args:
+      lr: !!float 1e-4
+      weight_decay: !!float 5e-5
+
+  lr_scheduler:
+    name: 'StepLR'
+    args:
+      step_size: 15
+      gamma: 0.1
+
+  loss:
+    name: 'SigmoidFocalLoss'
+    # name: 'CrossEntropyLoss'
+    args:
+      reduction: "mean"
+
+  logger:
+    log_root: '/Users/zhouweiqi/Downloads/test/logs'
+    suffix: 'vit'
\ No newline at end of file

+from functools import partial
+from collections import OrderedDict
+
+import torch
+import torch.nn as nn
+from utils.registery import MODEL_REGISTRY
+
+
+def _init_vit_weights(m):
+    """
+    ViT weight initialization
+    :param m: module
+    """
+    if isinstance(m, nn.Linear):
+        nn.init.trunc_normal_(m.weight, std=.01)
+        if m.bias is not None:
+            nn.init.zeros_(m.bias)
+    elif isinstance(m, nn.Conv2d):
+        nn.init.kaiming_normal_(m.weight, mode="fan_out")
+        if m.bias is not None:
+            nn.init.zeros_(m.bias)
+    elif isinstance(m, nn.LayerNorm):
+        nn.init.zeros_(m.bias)
+        nn.init.ones_(m.weight)
+
+
+def drop_path(x, drop_prob: float = 0., training: bool = False):
+    """
+    Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
+    This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
+    the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
+    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
+    changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
+    'survival rate' as the argument.
+    """
+    if drop_prob == 0. or not training:
+        return x
+    keep_prob = 1 - drop_prob
+    shape = (x.shape[0],) + (1,) * (x.ndim - 1)  # work with diff dim tensors, not just 2D ConvNets
+    random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
+    random_tensor.floor_()  # binarize
+    output = x.div(keep_prob) * random_tensor
+    return output
+
+
+class DropPath(nn.Module):
+    """
+    Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
+    """
+    def __init__(self, drop_prob=None):
+        super(DropPath, self).__init__()
+        self.drop_prob = drop_prob
+
+    def forward(self, x):
+        return drop_path(x, self.drop_prob, self.training)
+
+
+class Attention(nn.Module):
+    def __init__(self,
+                 dim,   # 输入token的dim
+                 num_heads=8,
+                 qkv_bias=False,
+                 qk_scale=None,
+                 attn_drop_ratio=0.,
+                 proj_drop_ratio=0.):
+        super(Attention, self).__init__()
+        self.num_heads = num_heads
+        head_dim = dim // num_heads
+        self.scale = qk_scale or head_dim ** -0.5
+        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
+        self.attn_drop = nn.Dropout(attn_drop_ratio)
+        self.proj = nn.Linear(dim, dim)
+        self.proj_drop = nn.Dropout(proj_drop_ratio)
+
+    def forward(self, x):
+        # [batch_size, num_patches + 1, total_embed_dim]
+        B, N, C = x.shape
+
+        # qkv(): -> [batch_size, num_patches + 1, 3 * total_embed_dim]
+        # reshape: -> [batch_size, num_patches + 1, 3, num_heads, embed_dim_per_head]
+        # permute: -> [3, batch_size, num_heads, num_patches + 1, embed_dim_per_head]
+        qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
+        # [batch_size, num_heads, num_patches + 1, embed_dim_per_head]
+        q, k, v = qkv[0], qkv[1], qkv[2]  # make torchscript happy (cannot use tensor as tuple)
+
+        # transpose: -> [batch_size, num_heads, embed_dim_per_head, num_patches + 1]
+        # @: multiply -> [batch_size, num_heads, num_patches + 1, num_patches + 1]
+        attn = (q @ k.transpose(-2, -1)) * self.scale
+        attn = attn.softmax(dim=-1)
+        attn = self.attn_drop(attn)
+
+        # @: multiply -> [batch_size, num_heads, num_patches + 1, embed_dim_per_head]
+        # transpose: -> [batch_size, num_patches + 1, num_heads, embed_dim_per_head]
+        # reshape: -> [batch_size, num_patches + 1, total_embed_dim]
+        x = (attn @ v).transpose(1, 2).reshape(B, N, C)
+        x = self.proj(x)
+        x = self.proj_drop(x)
+        return x
+
+
+class Mlp(nn.Module):
+    """
+    MLP as used in Vision Transformer, MLP-Mixer and related networks
+    """
+    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.fc1 = nn.Linear(in_features, hidden_features)
+        self.act = act_layer()
+        self.fc2 = nn.Linear(hidden_features, out_features)
+        self.drop = nn.Dropout(drop)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+        return x
+
+
+class Block(nn.Module):
+    def __init__(self,
+                 dim,
+                 num_heads,
+                 mlp_ratio=4.,
+                 qkv_bias=False,
+                 qk_scale=None,
+                 drop_ratio=0.,
+                 attn_drop_ratio=0.,
+                 drop_path_ratio=0.,
+                 act_layer=nn.GELU,
+                 norm_layer=nn.LayerNorm):
+        super(Block, self).__init__()
+        self.norm1 = norm_layer(dim)
+        self.attn = Attention(dim, num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale,
+                              attn_drop_ratio=attn_drop_ratio, proj_drop_ratio=drop_ratio)
+        # NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
+        self.drop_path = DropPath(drop_path_ratio) if drop_path_ratio > 0. else nn.Identity()
+        self.norm2 = norm_layer(dim)
+        mlp_hidden_dim = int(dim * mlp_ratio)
+        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop_ratio)
+
+    def forward(self, x):
+        x = x + self.drop_path(self.attn(self.norm1(x)))
+        x = x + self.drop_path(self.mlp(self.norm2(x)))
+        return x
+
+
+class PatchEmbed(nn.Module):
+    """
+    2D Image to Patch Embedding
+    """
+    def __init__(self, img_size=224, patch_size=16, in_c=3, embed_dim=768, norm_layer=None):
+        super().__init__()
+        img_size = (img_size, img_size)
+        patch_size = (patch_size, patch_size)
+        self.img_size = img_size
+        self.patch_size = patch_size
+        self.grid_size = (img_size[0] // patch_size[0], img_size[1] // patch_size[1])
+        self.num_patches = self.grid_size[0] * self.grid_size[1]
+
+        self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=patch_size, stride=patch_size)
+        self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()
+
+    def forward(self, x):
+        B, C, H, W = x.shape
+        assert H == self.img_size[0] and W == self.img_size[1], \
+            f"Input image size ({H}*{W}) doesn't match model ({self.img_size[0]}*{self.img_size[1]})."
+
+        # flatten: [B, C, H, W] -> [B, C, HW]
+        # transpose: [B, C, HW] -> [B, HW, C]
+        x = self.proj(x).flatten(2).transpose(1, 2)
+        x = self.norm(x)
+        return x
+
+
+@MODEL_REGISTRY.register()
+class VisionTransformer(nn.Module):
+    def __init__(self, img_size=224, patch_size=16, in_c=3, num_classes=1000,
+                 embed_dim=768, depth=12, num_heads=12, mlp_ratio=4.0, qkv_bias=True,
+                 qk_scale=None, representation_size=None, distilled=False, drop_ratio=0.,
+                 attn_drop_ratio=0., drop_path_ratio=0., embed_layer=PatchEmbed, norm_layer=None,
+                 act_layer=None):
+        """
+        Args:
+            img_size (int, tuple): input image size
+            patch_size (int, tuple): patch size
+            in_c (int): number of input channels
+            num_classes (int): number of classes for classification head
+            embed_dim (int): embedding dimension
+            depth (int): depth of transformer
+            num_heads (int): number of attention heads
+            mlp_ratio (int): ratio of mlp hidden dim to embedding dim
+            qkv_bias (bool): enable bias for qkv if True
+            qk_scale (float): override default qk scale of head_dim ** -0.5 if set
+            representation_size (Optional[int]): enable and set representation layer (pre-logits) to this value if set
+            distilled (bool): model includes a distillation token and head as in DeiT models
+            drop_ratio (float): dropout rate
+            attn_drop_ratio (float): attention dropout rate
+            drop_path_ratio (float): stochastic depth rate
+            embed_layer (nn.Module): patch embedding layer
+            norm_layer: (nn.Module): normalization layer
+        """
+        super(VisionTransformer, self).__init__()
+        self.num_classes = num_classes
+        self.num_features = self.embed_dim = embed_dim  # num_features for consistency with other models
+        self.num_tokens = 2 if distilled else 1
+        norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6)
+        act_layer = act_layer or nn.GELU
+
+        self.patch_embed = embed_layer(img_size=img_size, patch_size=patch_size, in_c=in_c, embed_dim=embed_dim)
+        num_patches = self.patch_embed.num_patches
+
+        self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))
+        self.dist_token = nn.Parameter(torch.zeros(1, 1, embed_dim)) if distilled else None
+        self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + self.num_tokens, embed_dim))
+        self.pos_drop = nn.Dropout(p=drop_ratio)
+
+        dpr = [x.item() for x in torch.linspace(0, drop_path_ratio, depth)]  # stochastic depth decay rule
+        self.blocks = nn.Sequential(*[
+            Block(dim=embed_dim, num_heads=num_heads, mlp_ratio=mlp_ratio, qkv_bias=qkv_bias, qk_scale=qk_scale,
+                  drop_ratio=drop_ratio, attn_drop_ratio=attn_drop_ratio, drop_path_ratio=dpr[i],
+                  norm_layer=norm_layer, act_layer=act_layer)
+            for i in range(depth)
+        ])
+        self.norm = norm_layer(embed_dim)
+
+        # Representation layer
+        if representation_size and not distilled:
+            self.has_logits = True
+            self.num_features = representation_size
+            self.pre_logits = nn.Sequential(OrderedDict([
+                ("fc", nn.Linear(embed_dim, representation_size)),
+                ("act", nn.Tanh())
+            ]))
+        else:
+            self.has_logits = False
+            self.pre_logits = nn.Identity()
+
+        # Classifier head(s)
+        self.head = nn.Linear(self.num_features, num_classes) if num_classes > 0 else nn.Identity()
+        self.head_dist = None
+        if distilled:
+            self.head_dist = nn.Linear(self.embed_dim, self.num_classes) if num_classes > 0 else nn.Identity()
+
+        # Weight init
+        nn.init.trunc_normal_(self.pos_embed, std=0.02)
+        if self.dist_token is not None:
+            nn.init.trunc_normal_(self.dist_token, std=0.02)
+
+        nn.init.trunc_normal_(self.cls_token, std=0.02)
+        self.apply(_init_vit_weights)
+
+    def forward_features(self, x):
+        # [B, C, H, W] -> [B, num_patches, embed_dim]
+        # x = self.patch_embed(x)  # [B, 196, 768]
+        # [1, 1, 768] -> [B, 1, 768]
+
+        # [B, 28+1, 8]
+        cls_token = self.cls_token.expand(x.shape[0], -1, -1)
+        if self.dist_token is None:
+            x = torch.cat((cls_token, x), dim=1)  # [B, 197, 768]
+        else:
+            x = torch.cat((cls_token, self.dist_token.expand(x.shape[0], -1, -1), x), dim=1)
+
+        x = self.pos_drop(x + self.pos_embed)
+        x = self.blocks(x)
+        x = self.norm(x)
+        if self.dist_token is None:
+            return self.pre_logits(x[:, 0])
+        else:
+            return x[:, 0], x[:, 1]
+
+    def forward(self, x):
+        x = self.forward_features(x)
+        if self.head_dist is not None:
+            x, x_dist = self.head(x[0]), self.head_dist(x[1])
+            if self.training and not torch.jit.is_scripting():
+                # during inference, return the average of both classifier predictions
+                return x, x_dist
+            else:
+                return (x + x_dist) / 2
+        else:
+            x = self.head(x)
+        return x

+import os
+import copy
+import torch
+
+from model import build_model
+from data import build_dataloader
+from optimizer import build_optimizer, build_lr_scheduler
+from loss import build_loss
+from utils import SOLVER_REGISTRY, get_logger_and_log_dir
+
+
+@SOLVER_REGISTRY.register()
+class VITSolver(object):
+
+    def __init__(self, cfg):
+        self.device = "cuda" if torch.cuda.is_available() else "cpu"
+
+        self.cfg = copy.deepcopy(cfg)
+
+        self.train_loader, self.val_loader = build_dataloader(cfg)
+        self.train_loader_size, self.val_loader_size = len(self.train_loader), len(self.val_loader)
+        self.train_dataset_size, self.val_dataset_size = len(self.train_loader.dataset), len(self.val_loader.dataset)
+
+        # BatchNorm ?
+        self.model = build_model(cfg).to(self.device)
+
+        self.loss_fn = build_loss(cfg)
+
+        self.optimizer = build_optimizer(cfg)(self.model.parameters(), **cfg['solver']['optimizer']['args'])
+
+        self.hyper_params = cfg['solver']['args']
+        try:
+            self.epoch = self.hyper_params['epoch']
+        except Exception:
+            raise 'should contain epoch in {solver.args}'
+
+        self.logger, self.log_dir = get_logger_and_log_dir(**cfg['solver']['logger'])
+
+    @staticmethod
+    def evaluate(y_pred, y_true, thresholds=0.5):
+        y_pred_idx = torch.argmax(y_pred, dim=1) + 1
+        y_pred_is_other = (torch.amax(y_pred, dim=1) > 0.5).int()
+        y_pred_rebuild = torch.multiply(y_pred_idx, y_pred_is_other)
+
+        y_true_idx = torch.argmax(y_true, dim=1) + 1
+        y_true_is_other = torch.sum(y_true, dim=1)
+        y_true_rebuild = torch.multiply(y_true_idx, y_true_is_other)
+
+        return torch.sum((y_pred_rebuild == y_true_rebuild).int()).item()
+
+    def train_loop(self):
+        self.model.train()
+
+        train_loss = torch.zeros(1).to(self.device)
+        correct = torch.zeros(1).to(self.device)
+        for batch, (X, y) in enumerate(self.train_loader):
+            X, y = X.to(self.device), y.to(self.device)
+
+            pred = self.model(X)
+
+            correct += self.evaluate(pred, y)
+
+            # loss = self.loss_fn(pred, y, reduction="mean")
+            loss = self.loss_fn(pred, y)
+            train_loss += loss.item()
+
+            if batch % 100 == 0:
+                loss_value, current = loss.item(), batch
+                self.logger.info(f'train iteration: {current}/{self.train_loader_size}, train loss: {loss_value :.4f}')
+            
+            self.optimizer.zero_grad()
+            loss.backward()
+            self.optimizer.step()
+
+        correct /= self.train_dataset_size
+        train_loss /= self.train_loader_size
+        self.logger.info(f'train accuracy: {correct.item() :.4f}, train mean loss: {train_loss.item() :.4f}')
+
+    @torch.no_grad()
+    def val_loop(self, t):
+        self.model.eval()
+
+        val_loss = torch.zeros(1).to(self.device)
+        correct = torch.zeros(1).to(self.device)
+        for X, y in self.val_loader:
+            X, y = X.to(self.device), y.to(self.device)
+
+            pred = self.model(X)
+
+            correct += self.evaluate(pred, y)
+
+            loss = self.loss_fn(pred, y)
+            val_loss += loss.item()
+
+        correct /= self.val_dataset_size
+        val_loss /= self.val_loader_size
+            
+        self.logger.info(f"val accuracy: {correct.item() :.4f}, val mean loss: {val_loss.item() :.4f}")
+
+    def save_checkpoint(self, epoch_id):
+        self.model.eval()
+        torch.save(self.model.state_dict(), os.path.join(self.log_dir, f'ckpt_epoch_{epoch_id}.pt'))
+
+    def run(self):
+        self.logger.info('==> Start Training')
+        print(self.model)
+
+        # lr_scheduler = build_lr_scheduler(self.cfg)(self.optimizer, **self.cfg['solver']['lr_scheduler']['args'])
+
+        for t in range(self.epoch):
+            self.logger.info(f'==> epoch {t + 1}')
+
+            self.train_loop()
+            self.val_loop(t + 1)
+            self.save_checkpoint(t + 1)
+
+            # lr_scheduler.step()
+
+        self.logger.info('==> End Training')