yolov5/models/experimental.py

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Experimental modules
"""
import math

import numpy as np
import torch
import torch.nn as nn

from models.common import Conv
from utils.downloads import attempt_download


class CrossConv(nn.Module):
    # Cross Convolution Downsample
    def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
        # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, (1, k), (1, s))
        self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))


class Sum(nn.Module):
    # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
    def __init__(self, n, weight=False):  # n: number of inputs
        super().__init__()
        self.weight = weight  # apply weights boolean
        self.iter = range(n - 1)  # iter object
        if weight:
            self.w = nn.Parameter(-torch.arange(1.0, n) / 2, requires_grad=True)  # layer weights

    def forward(self, x):
        y = x[0]  # no weight
        if self.weight:
            w = torch.sigmoid(self.w) * 2
            for i in self.iter:
                y = y + x[i + 1] * w[i]
        else:
            for i in self.iter:
                y = y + x[i + 1]
        return y


class MixConv2d(nn.Module):
    # Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595
    def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):  # ch_in, ch_out, kernel, stride, ch_strategy
        super().__init__()
        n = len(k)  # number of convolutions
        if equal_ch:  # equal c_ per group
            i = torch.linspace(0, n - 1E-6, c2).floor()  # c2 indices
            c_ = [(i == g).sum() for g in range(n)]  # intermediate channels
        else:  # equal weight.numel() per group
            b = [c2] + [0] * n
            a = np.eye(n + 1, n, k=-1)
            a -= np.roll(a, 1, axis=1)
            a *= np.array(k) ** 2
            a[0] = 1
            c_ = np.linalg.lstsq(a, b, rcond=None)[0].round()  # solve for equal weight indices, ax = b

        self.m = nn.ModuleList(
            [nn.Conv2d(c1, int(c_), k, s, k // 2, groups=math.gcd(c1, int(c_)), bias=False) for k, c_ in zip(k, c_)])
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.SiLU()

    def forward(self, x):
        return self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))


class Ensemble(nn.ModuleList):
    # Ensemble of models
    def __init__(self):
        super().__init__()

    def forward(self, x, augment=False, profile=False, visualize=False):
        y = []
        for module in self:
            y.append(module(x, augment, profile, visualize)[0])
        # y = torch.stack(y).max(0)[0]  # max ensemble
        # y = torch.stack(y).mean(0)  # mean ensemble
        y = torch.cat(y, 1)  # nms ensemble
        return y, None  # inference, train output


def attempt_load(weights, map_location=None, inplace=True, fuse=True):
    from models.yolo import Detect, Model

    # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
    model = Ensemble()
    for w in weights if isinstance(weights, list) else [weights]:
        ckpt = torch.load(attempt_download(w), map_location=map_location)  # load
        ckpt = (ckpt.get('ema') or ckpt['model']).float()  # FP32 model
        model.append(ckpt.fuse().eval() if fuse else ckpt.eval())  # fused or un-fused model in eval mode

    # Compatibility updates
    for m in model.modules():
        t = type(m)
        if t in (nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model):
            m.inplace = inplace  # torch 1.7.0 compatibility
            if t is Detect:
                if not isinstance(m.anchor_grid, list):  # new Detect Layer compatibility
                    delattr(m, 'anchor_grid')
                    setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl)
        elif t is Conv:
            m._non_persistent_buffers_set = set()  # torch 1.6.0 compatibility
        elif t is nn.Upsample and not hasattr(m, 'recompute_scale_factor'):
            m.recompute_scale_factor = None  # torch 1.11.0 compatibility

    if len(model) == 1:
        return model[-1]  # return model
    else:
        print(f'Ensemble created with {weights}\n')
        for k in ['names']:
            setattr(model, k, getattr(model[-1], k))
        model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride  # max stride
        return model  # return ensemble