grounded-sam-osx/nets/layer.py

import torch
import torch.nn as nn
from torch.nn import functional as F
from config import cfg

def make_linear_layers(feat_dims, relu_final=True, use_bn=False):
    layers = []
    for i in range(len(feat_dims)-1):
        layers.append(nn.Linear(feat_dims[i], feat_dims[i+1]))

        # Do not use ReLU for final estimation
        if i < len(feat_dims)-2 or (i == len(feat_dims)-2 and relu_final):
            if use_bn:
                layers.append(nn.BatchNorm1d(feat_dims[i+1]))
            layers.append(nn.ReLU(inplace=True))

    return nn.Sequential(*layers)

def make_conv_layers(feat_dims, kernel=3, stride=1, padding=1, bnrelu_final=True):
    layers = []
    for i in range(len(feat_dims)-1):
        layers.append(
            nn.Conv2d(
                in_channels=feat_dims[i],
                out_channels=feat_dims[i+1],
                kernel_size=kernel,
                stride=stride,
                padding=padding
                ))
        # Do not use BN and ReLU for final estimation
        if i < len(feat_dims)-2 or (i == len(feat_dims)-2 and bnrelu_final):
            layers.append(nn.BatchNorm2d(feat_dims[i+1]))
            layers.append(nn.ReLU(inplace=True))

    return nn.Sequential(*layers)

def make_deconv_layers(feat_dims, bnrelu_final=True):
    layers = []
    for i in range(len(feat_dims)-1):
        layers.append(
            nn.ConvTranspose2d(
                in_channels=feat_dims[i],
                out_channels=feat_dims[i+1],
                kernel_size=4,
                stride=2,
                padding=1,
                output_padding=0,
                bias=False))

        # Do not use BN and ReLU for final estimation
        if i < len(feat_dims)-2 or (i == len(feat_dims)-2 and bnrelu_final):
            layers.append(nn.BatchNorm2d(feat_dims[i+1]))
            layers.append(nn.ReLU(inplace=True))

    return nn.Sequential(*layers)