Release detection and segmentation

detection/ops_dcnv3/src/dcnv3.h

+/*!
+**************************************************************************************************
+* InternImage
+* Copyright (c) 2022 OpenGVLab
+* Licensed under The MIT License [see LICENSE for details]
+**************************************************************************************************
+* Modified from
+*https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch/tree/pytorch_1.0.0
+**************************************************************************************************
+*/
+
+#pragma once
+
+#include "cpu/dcnv3_cpu.h"
+
+#ifdef WITH_CUDA
+#include "cuda/dcnv3_cuda.h"
+#endif
+
+at::Tensor dcnv3_forward(const at::Tensor &input, const at::Tensor &offset,
+                         const at::Tensor &mask, const int kernel_h,
+                         const int kernel_w, const int stride_h,
+                         const int stride_w, const int pad_h, const int pad_w,
+                         const int dilation_h, const int dilation_w,
+                         const int group, const int group_channels,
+                         const float offset_scale, const int im2col_step) {
+    if (input.type().is_cuda()) {
+#ifdef WITH_CUDA
+        return dcnv3_cuda_forward(input, offset, mask, kernel_h, kernel_w,
+                                  stride_h, stride_w, pad_h, pad_w, dilation_h,
+                                  dilation_w, group, group_channels,
+                                  offset_scale, im2col_step);
+#else
+        AT_ERROR("Not compiled with GPU support");
+#endif
+    }
+    AT_ERROR("Not implemented on the CPU");
+}
+
+std::vector<at::Tensor>
+dcnv3_backward(const at::Tensor &input, const at::Tensor &offset,
+               const at::Tensor &mask, const int kernel_h, const int kernel_w,
+               const int stride_h, const int stride_w, const int pad_h,
+               const int pad_w, const int dilation_h, const int dilation_w,
+               const int group, const int group_channels,
+               const float offset_scale, const at::Tensor &grad_output,
+               const int im2col_step) {
+    if (input.type().is_cuda()) {
+#ifdef WITH_CUDA
+        return dcnv3_cuda_backward(input, offset, mask, kernel_h, kernel_w,
+                                   stride_h, stride_w, pad_h, pad_w, dilation_h,
+                                   dilation_w, group, group_channels,
+                                   offset_scale, grad_output, im2col_step);
+#else
+        AT_ERROR("Not compiled with GPU support");
+#endif
+    }
+    AT_ERROR("Not implemented on the CPU");
+}

detection/ops_dcnv3/src/vision.cpp

+/*!
+**************************************************************************************************
+* InternImage
+* Copyright (c) 2022 OpenGVLab
+* Licensed under The MIT License [see LICENSE for details]
+**************************************************************************************************
+* Modified from
+*https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch/tree/pytorch_1.0.0
+**************************************************************************************************
+*/
+
+#include "dcnv3.h"
+
+PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
+    m.def("dcnv3_forward", &dcnv3_forward, "dcnv3_forward");
+    m.def("dcnv3_backward", &dcnv3_backward, "dcnv3_backward");
+}

detection/ops_dcnv3/test.py

+# --------------------------------------------------------
+# InternImage
+# Copyright (c) 2022 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+
+from __future__ import absolute_import
+from __future__ import print_function
+from __future__ import division
+
+import time
+import torch
+import torch.nn as nn
+import math
+from torch.autograd import gradcheck
+
+from functions.dcnv3_func import DCNv3Function, dcnv3_core_pytorch
+
+H_in, W_in = 8, 8
+N, M, D = 2, 4, 16
+Kh, Kw = 3, 3
+P = Kh * Kw
+offset_scale = 2.0
+pad = 1
+dilation = 1
+stride = 1
+H_out = (H_in + 2 * pad - (dilation * (Kh - 1) + 1)) // stride + 1
+W_out = (W_in + 2 * pad - (dilation * (Kw - 1) + 1)) // stride + 1
+
+torch.manual_seed(3)
+
+
+@torch.no_grad()
+def check_forward_equal_with_pytorch_double():
+    input = torch.rand(N, H_in, W_in, M*D).cuda() * 0.01
+    offset = torch.rand(N, H_out, W_out, M*P*2).cuda() * 10
+    mask = torch.rand(N, H_out, W_out, M, P).cuda() + 1e-5
+    mask /= mask.sum(-1, keepdim=True)
+    mask = mask.reshape(N, H_out, W_out, M*P)
+
+    output_pytorch = dcnv3_core_pytorch(
+        input.double(),
+        offset.double(),
+        mask.double(),
+        Kh, Kw, stride, stride, Kh // 2, Kw // 2, dilation, dilation, M, D, offset_scale).detach().cpu()
+
+    im2col_step = 2
+    output_cuda = DCNv3Function.apply(
+        input.double(),
+        offset.double(),
+        mask.double(),
+        Kh, Kw, stride, stride, Kh // 2, Kw // 2, dilation, dilation, M, D, offset_scale,
+        im2col_step).detach().cpu()
+
+    fwdok = torch.allclose(output_cuda, output_pytorch)
+    max_abs_err = (output_cuda - output_pytorch).abs().max()
+    max_rel_err = ((output_cuda - output_pytorch).abs() /
+                   output_pytorch.abs()).max()
+    print('>>> forward double')
+    print(f'* {fwdok} check_forward_equal_with_pytorch_double: max_abs_err {max_abs_err:.2e} max_rel_err {max_rel_err:.2e}')
+
+
+@torch.no_grad()
+def check_forward_equal_with_pytorch_float():
+    input = torch.rand(N, H_in, W_in, M*D).cuda() * 0.01
+    offset = torch.rand(N, H_out, W_out, M*P*2).cuda() * 10
+    mask = torch.rand(N, H_out, W_out, M, P).cuda() + 1e-5
+    mask /= mask.sum(-1, keepdim=True)
+    mask = mask.reshape(N, H_out, W_out, M*P)
+
+    output_pytorch = dcnv3_core_pytorch(
+        input,
+        offset,
+        mask,
+        Kh, Kw, stride, stride, Kh // 2, Kw // 2, dilation, dilation, M, D, offset_scale).detach().cpu()
+
+    im2col_step = 2
+    output_cuda = DCNv3Function.apply(
+        input,
+        offset,
+        mask,
+        Kh, Kw, stride, stride, Kh // 2, Kw // 2, dilation, dilation, M, D, offset_scale,
+        im2col_step).detach().cpu()
+
+    fwdok = torch.allclose(output_cuda, output_pytorch, rtol=1e-2, atol=1e-3)
+    max_abs_err = (output_cuda - output_pytorch).abs().max()
+    max_rel_err = ((output_cuda - output_pytorch).abs() /
+                   output_pytorch.abs()).max()
+    print('>>> forward float')
+    print(f'* {fwdok} check_forward_equal_with_pytorch_float: max_abs_err {max_abs_err:.2e} max_rel_err {max_rel_err:.2e}')
+
+
+def check_backward_equal_with_pytorch_double(channels=4, grad_input=True, grad_offset=True, grad_mask=True):
+    # H_in, W_in = 4, 4
+    N = 2
+    M = 2
+    H_out = (H_in + 2 * pad - (dilation * (Kh - 1) + 1)) // stride + 1
+    W_out = (W_in + 2 * pad - (dilation * (Kw - 1) + 1)) // stride + 1
+
+    D = channels
+    input0 = torch.rand(N, H_in, W_in, M*D).cuda() * 0.01
+    offset0 = torch.rand(N, H_out, W_out, M*P*2).cuda() * 10
+    mask0 = torch.rand(N, H_out, W_out, M, P).cuda() + 1e-5
+    mask0 /= mask0.sum(-1, keepdim=True)
+    mask0 = mask0.reshape(N, H_out, W_out, M*P)
+    input0.requires_grad = grad_input
+    offset0.requires_grad = grad_offset
+    mask0.requires_grad = grad_mask
+
+    output_pytorch = dcnv3_core_pytorch(
+        input0.double(),
+        offset0.double(),
+        mask0.double(),
+        Kh, Kw, stride, stride, Kh // 2, Kw // 2, dilation, dilation, M, D, offset_scale)
+    output_pytorch.sum().backward()
+
+    input1 = input0.detach()
+    offset1 = offset0.detach()
+    mask1 = mask0.detach()
+    input1.requires_grad = grad_input
+    offset1.requires_grad = grad_offset
+    mask1.requires_grad = grad_mask
+
+    im2col_step = 2
+    output_cuda = DCNv3Function.apply(
+        input1.double(),
+        offset1.double(),
+        mask1.double(),
+        Kh, Kw, stride, stride, Kh // 2, Kw // 2, dilation, dilation, M, D, offset_scale,
+        im2col_step)
+    output_cuda.sum().backward()
+
+    print(f'>>> backward double: channels {D}')
+    bwdok = torch.allclose(input0.grad, input1.grad, rtol=1e-2, atol=1e-3)
+    max_abs_err = (input0.grad - input1.grad).abs().max()
+    max_rel_err = ((input0.grad - input1.grad).abs() /
+                   input0.grad.abs()).max()
+    print(
+        f'* {bwdok} input_grad check_backward_equal_with_pytorch_double: max_abs_err {max_abs_err:.2e} max_rel_err {max_rel_err:.2e}')
+
+    bwdok = torch.allclose(offset0.grad, offset1.grad, rtol=1e-2, atol=1e-3)
+    max_abs_err = (offset0.grad - offset1.grad).abs().max()
+    max_rel_err = ((offset0.grad - offset1.grad).abs() /
+                   offset0.grad.abs()).max()
+    print(
+        f'* {bwdok} offset_grad check_backward_equal_with_pytorch_double: max_abs_err {max_abs_err:.2e} max_rel_err {max_rel_err:.2e}')
+
+    bwdok = torch.allclose(mask0.grad, mask1.grad, rtol=1e-2, atol=1e-3)
+    max_abs_err = (mask0.grad - mask1.grad).abs().max()
+    max_rel_err = ((mask0.grad - mask1.grad).abs() /
+                   mask0.grad.abs()).max()
+    print(
+        f'* {bwdok} mask_grad check_backward_equal_with_pytorch_double: max_abs_err {max_abs_err:.2e} max_rel_err {max_rel_err:.2e}')
+
+
+def check_backward_equal_with_pytorch_float(channels=4, grad_input=True, grad_offset=True, grad_mask=True):
+    # H_in, W_in = 4, 4
+    N = 2
+    M = 2
+    H_out = (H_in + 2 * pad - (dilation * (Kh - 1) + 1)) // stride + 1
+    W_out = (W_in + 2 * pad - (dilation * (Kw - 1) + 1)) // stride + 1
+
+    D = channels
+    input0 = torch.rand(N, H_in, W_in, M*D).cuda() * 0.01
+    offset0 = torch.rand(N, H_out, W_out, M*P*2).cuda() * 10
+    mask0 = torch.rand(N, H_out, W_out, M, P).cuda() + 1e-5
+    mask0 /= mask0.sum(-1, keepdim=True)
+    mask0 = mask0.reshape(N, H_out, W_out, M*P)
+    input0.requires_grad = grad_input
+    offset0.requires_grad = grad_offset
+    mask0.requires_grad = grad_mask
+
+    output_pytorch = dcnv3_core_pytorch(
+        input0,
+        offset0,
+        mask0,
+        Kh, Kw, stride, stride, Kh // 2, Kw // 2, dilation, dilation, M, D, offset_scale)
+    output_pytorch.sum().backward()
+
+    input1 = input0.detach()
+    offset1 = offset0.detach()
+    mask1 = mask0.detach()
+    input1.requires_grad = grad_input
+    offset1.requires_grad = grad_offset
+    mask1.requires_grad = grad_mask
+
+    im2col_step = 2
+    output_cuda = DCNv3Function.apply(
+        input1,
+        offset1,
+        mask1,
+        Kh, Kw, stride, stride, Kh // 2, Kw // 2, dilation, dilation, M, D, offset_scale,
+        im2col_step)
+    output_cuda.sum().backward()
+
+    print(f'>>> backward float: channels {D}')
+    bwdok = torch.allclose(input0.grad, input1.grad, rtol=1e-2, atol=1e-3)
+    max_abs_err = (input0.grad - input1.grad).abs().max()
+    max_rel_err = ((input0.grad - input1.grad).abs() /
+                   input0.grad.abs()).max()
+    print(
+        f'* {bwdok} input_grad check_backward_equal_with_pytorch_float: max_abs_err {max_abs_err:.2e} max_rel_err {max_rel_err:.2e}')
+
+    bwdok = torch.allclose(offset0.grad, offset1.grad, rtol=1e-2, atol=1e-3)
+    max_abs_err = (offset0.grad - offset1.grad).abs().max()
+    max_rel_err = ((offset0.grad - offset1.grad).abs() /
+                   offset0.grad.abs()).max()
+    print(
+        f'* {bwdok} offset_grad check_backward_equal_with_pytorch_float: max_abs_err {max_abs_err:.2e} max_rel_err {max_rel_err:.2e}')
+
+    bwdok = torch.allclose(mask0.grad, mask1.grad, rtol=1e-2, atol=1e-3)
+    max_abs_err = (mask0.grad - mask1.grad).abs().max()
+    max_rel_err = ((mask0.grad - mask1.grad).abs() /
+                   mask0.grad.abs()).max()
+    print(
+        f'* {bwdok} mask_grad check_backward_equal_with_pytorch_float: max_abs_err {max_abs_err:.2e} max_rel_err {max_rel_err:.2e}')
+
+
+@torch.no_grad()
+def check_time_cost(im2col_step=128):
+    N = 512
+    H_in, W_in = 64, 64
+    H_out = (H_in + 2 * pad - (dilation * (Kh - 1) + 1)) // stride + 1
+    W_out = (W_in + 2 * pad - (dilation * (Kw - 1) + 1)) // stride + 1
+
+    input = torch.rand(N, H_in, W_in, M*D).cuda() * 0.01
+    offset = torch.rand(N, H_out, W_out, M*P*2).cuda() * 10
+    mask = torch.rand(N, H_out, W_out, M, P).cuda() + 1e-5
+    mask /= mask.sum(-1, keepdim=True)
+    mask = mask.reshape(N, H_out, W_out, M*P)
+    print(
+        f'>>> time cost: im2col_step {im2col_step}; input {input.shape}; points {P} ')
+    repeat = 100
+    for i in range(repeat):
+        output_cuda = DCNv3Function.apply(
+            input,
+            offset,
+            mask,
+            Kh, Kw, stride, stride, Kh // 2, Kw // 2, dilation, dilation, M, D, 1.0,
+            im2col_step)
+    torch.cuda.synchronize()
+    start = time.time()
+    for i in range(repeat):
+        output_cuda = DCNv3Function.apply(
+            input,
+            offset,
+            mask,
+            Kh, Kw, stride, stride, Kh // 2, Kw // 2, dilation, dilation, M, D, 1.0,
+            im2col_step)
+    torch.cuda.synchronize()
+    print(f'foward time cost: {(time.time() - start) / repeat}')
+
+
+if __name__ == '__main__':
+    check_forward_equal_with_pytorch_double()
+    check_forward_equal_with_pytorch_float()
+    for channels in [1, 16, 30, 32, 64, 71, 1025]:
+        check_backward_equal_with_pytorch_double(channels, True, True, True)
+    for channels in [1, 16, 30, 32, 64, 71, 1025]:
+        check_backward_equal_with_pytorch_float(channels, True, True, True)
+    for i in range(3):
+        im2col_step = 128 * (2 ** i)
+        check_time_cost(im2col_step)

detection/slurm_test.sh

+#!/usr/bin/env bash
+
+set -x
+
+PARTITION=$1
+JOB_NAME=$2
+CONFIG=$3
+CHECKPOINT=$4
+GPUS=${GPUS:-8}
+GPUS_PER_NODE=${GPUS_PER_NODE:-8}
+CPUS_PER_TASK=${CPUS_PER_TASK:-5}
+PY_ARGS=${@:5}
+SRUN_ARGS=${SRUN_ARGS:-""}
+
+PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \
+srun -p ${PARTITION} \
+    --job-name=${JOB_NAME} \
+    --gres=gpu:${GPUS_PER_NODE} \
+    --ntasks=${GPUS} \
+    --ntasks-per-node=${GPUS_PER_NODE} \
+    --cpus-per-task=${CPUS_PER_TASK} \
+    --kill-on-bad-exit=1 \
+    --quotatype=spot \
+    ${SRUN_ARGS} \
+    python -u test.py ${CONFIG} ${CHECKPOINT} --launcher="slurm" ${PY_ARGS}

detection/slurm_train.sh

+#!/usr/bin/env bash
+
+set -x
+
+PARTITION=$1
+JOB_NAME=$2
+CONFIG=$3
+WORK_DIR=$4
+GPUS=${GPUS:-8}
+GPUS_PER_NODE=${GPUS_PER_NODE:-8}
+CPUS_PER_TASK=${CPUS_PER_TASK:-10}
+SRUN_ARGS=${SRUN_ARGS:-""}
+PY_ARGS=${@:5}
+
+PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \
+srun -p ${PARTITION} \
+    --job-name=${JOB_NAME} \
+    --gres=gpu:${GPUS_PER_NODE} \
+    --ntasks=${GPUS} \
+    --ntasks-per-node=${GPUS_PER_NODE} \
+    --cpus-per-task=${CPUS_PER_TASK} \
+    --kill-on-bad-exit=1 \
+    --quotatype=spot \
+    ${SRUN_ARGS} \
+    python -u train.py ${CONFIG} --work-dir=${WORK_DIR} --launcher="slurm" ${PY_ARGS}
\ No newline at end of file

detection/test.py

+# --------------------------------------------------------
+# InternImage
+# Copyright (c) 2022 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+
+import argparse
+import os
+import os.path as osp
+import time
+import warnings
+
+import mmcv
+import torch
+from mmcv import Config, DictAction
+from mmcv.cnn import fuse_conv_bn
+from mmcv.parallel import MMDataParallel, MMDistributedDataParallel
+from mmcv.runner import (get_dist_info, init_dist, load_checkpoint,
+                         wrap_fp16_model)
+from mmdet.apis import multi_gpu_test, single_gpu_test
+from mmdet.datasets import (build_dataloader, build_dataset,
+                            replace_ImageToTensor)
+from mmdet.models import build_detector
+import mmdet_custom  # noqa: F401,F403
+import mmcv_custom  # noqa: F401,F403
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(
+        description='MMDet test (and eval) a model')
+    parser.add_argument('config', help='test config file path')
+    parser.add_argument('checkpoint', help='checkpoint file')
+    parser.add_argument(
+        '--work-dir',
+        help='the directory to save the file containing evaluation metrics')
+    parser.add_argument('--out', help='output result file in pickle format')
+    parser.add_argument(
+        '--fuse-conv-bn',
+        action='store_true',
+        help='Whether to fuse conv and bn, this will slightly increase'
+        'the inference speed')
+    parser.add_argument('--gpu-ids',
+                        type=int,
+                        nargs='+',
+                        help='ids of gpus to use '
+                        '(only applicable to non-distributed testing)')
+    parser.add_argument(
+        '--format-only',
+        action='store_true',
+        help='Format the output results without perform evaluation. It is'
+        'useful when you want to format the result to a specific format and '
+        'submit it to the test server')
+    parser.add_argument(
+        '--eval',
+        type=str,
+        nargs='+',
+        help='evaluation metrics, which depends on the dataset, e.g., "bbox",'
+        ' "segm", "proposal" for COCO, and "mAP", "recall" for PASCAL VOC')
+    parser.add_argument('--show', action='store_true', help='show results')
+    parser.add_argument('--show-dir',
+                        help='directory where painted images will be saved')
+    parser.add_argument('--show-score-thr',
+                        type=float,
+                        default=0.3,
+                        help='score threshold (default: 0.3)')
+    parser.add_argument('--gpu-collect',
+                        action='store_true',
+                        help='whether to use gpu to collect results.')
+    parser.add_argument(
+        '--tmpdir',
+        help='tmp directory used for collecting results from multiple '
+        'workers, available when gpu-collect is not specified')
+    parser.add_argument(
+        '--cfg-options',
+        nargs='+',
+        action=DictAction,
+        help='override some settings in the used config, the key-value pair '
+        'in xxx=yyy format will be merged into config file. If the value to '
+        'be overwritten is a list, it should be like key="[a,b]" or key=a,b '
+        'It also allows nested list/tuple values, e.g. key="[(a,b),(c,d)]" '
+        'Note that the quotation marks are necessary and that no white space '
+        'is allowed.')
+    parser.add_argument(
+        '--options',
+        nargs='+',
+        action=DictAction,
+        help='custom options for evaluation, the key-value pair in xxx=yyy '
+        'format will be kwargs for dataset.evaluate() function (deprecate), '
+        'change to --eval-options instead.')
+    parser.add_argument(
+        '--eval-options',
+        nargs='+',
+        action=DictAction,
+        help='custom options for evaluation, the key-value pair in xxx=yyy '
+        'format will be kwargs for dataset.evaluate() function')
+    parser.add_argument('--launcher',
+                        choices=['none', 'pytorch', 'slurm', 'mpi'],
+                        default='none',
+                        help='job launcher')
+    parser.add_argument('--local_rank', type=int, default=0)
+    args = parser.parse_args()
+    if 'LOCAL_RANK' not in os.environ:
+        os.environ['LOCAL_RANK'] = str(args.local_rank)
+
+    if args.options and args.eval_options:
+        raise ValueError(
+            '--options and --eval-options cannot be both '
+            'specified, --options is deprecated in favor of --eval-options')
+    if args.options:
+        warnings.warn('--options is deprecated in favor of --eval-options')
+        args.eval_options = args.options
+    return args
+
+
+def main():
+    print('!!!!!!!!!!!!!!!!!!1', flush=True)
+    args = parse_args()
+
+    assert args.out or args.eval or args.format_only or args.show \
+        or args.show_dir, \
+        ('Please specify at least one operation (save/eval/format/show the '
+         'results / save the results) with the argument "--out", "--eval"'
+         ', "--format-only", "--show" or "--show-dir"')
+
+    if args.eval and args.format_only:
+        raise ValueError('--eval and --format_only cannot be both specified')
+
+    if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
+        raise ValueError('The output file must be a pkl file.')
+
+    cfg = Config.fromfile(args.config)
+    if args.cfg_options is not None:
+        cfg.merge_from_dict(args.cfg_options)
+    # set cudnn_benchmark
+    if cfg.get('cudnn_benchmark', False):
+        torch.backends.cudnn.benchmark = True
+
+    cfg.model.pretrained = None
+    if cfg.model.get('neck'):
+        if isinstance(cfg.model.neck, list):
+            for neck_cfg in cfg.model.neck:
+                if neck_cfg.get('rfp_backbone'):
+                    if neck_cfg.rfp_backbone.get('pretrained'):
+                        neck_cfg.rfp_backbone.pretrained = None
+        elif cfg.model.neck.get('rfp_backbone'):
+            if cfg.model.neck.rfp_backbone.get('pretrained'):
+                cfg.model.neck.rfp_backbone.pretrained = None
+
+    # in case the test dataset is concatenated
+    samples_per_gpu = 1
+    if isinstance(cfg.data.test, dict):
+        cfg.data.test.test_mode = True
+        samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
+        if samples_per_gpu > 1:
+            # Replace 'ImageToTensor' to 'DefaultFormatBundle'
+            cfg.data.test.pipeline = replace_ImageToTensor(
+                cfg.data.test.pipeline)
+    elif isinstance(cfg.data.test, list):
+        for ds_cfg in cfg.data.test:
+            ds_cfg.test_mode = True
+        samples_per_gpu = max(
+            [ds_cfg.pop('samples_per_gpu', 1) for ds_cfg in cfg.data.test])
+        if samples_per_gpu > 1:
+            for ds_cfg in cfg.data.test:
+                ds_cfg.pipeline = replace_ImageToTensor(ds_cfg.pipeline)
+
+    if args.gpu_ids is not None:
+        cfg.gpu_ids = args.gpu_ids
+    else:
+        cfg.gpu_ids = range(1)
+
+    print('!!!!!!!!!!!!!!!!!!2', flush=True)
+    # init distributed env first, since logger depends on the dist info.
+    if args.launcher == 'none':
+        distributed = False
+        if len(cfg.gpu_ids) > 1:
+            warnings.warn(
+                f'We treat {cfg.gpu_ids} as gpu-ids, and reset to '
+                f'{cfg.gpu_ids[0:1]} as gpu-ids to avoid potential error in '
+                'non-distribute testing time.')
+            cfg.gpu_ids = cfg.gpu_ids[0:1]
+    else:
+        distributed = True
+        init_dist(args.launcher, **cfg.dist_params)
+    print('!!!!!!!!!!!!!!!!!!3', flush=True)
+
+    rank, _ = get_dist_info()
+    # allows not to create
+    if args.work_dir is not None and rank == 0:
+        mmcv.mkdir_or_exist(osp.abspath(args.work_dir))
+        timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
+        json_file = osp.join(args.work_dir, f'eval_{timestamp}.json')
+
+    # build the dataloader
+    dataset = build_dataset(cfg.data.test)
+    data_loader = build_dataloader(dataset,
+                                   samples_per_gpu=samples_per_gpu,
+                                   workers_per_gpu=cfg.data.workers_per_gpu,
+                                   dist=distributed,
+                                   shuffle=False)
+
+    # build the model and load checkpoint
+    cfg.model.train_cfg = None
+    model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
+    fp16_cfg = cfg.get('fp16', None)
+    if fp16_cfg is not None:
+        wrap_fp16_model(model)
+    checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
+
+    if args.fuse_conv_bn:
+        model = fuse_conv_bn(model)
+    # old versions did not save class info in checkpoints, this walkaround is
+    # for backward compatibility
+    if 'CLASSES' in checkpoint.get('meta', {}):
+        model.CLASSES = checkpoint['meta']['CLASSES']
+    else:
+        model.CLASSES = dataset.CLASSES
+
+    if not distributed:
+        model = MMDataParallel(model, device_ids=cfg.gpu_ids)
+        outputs = single_gpu_test(model, data_loader, args.show, args.show_dir,
+                                  args.show_score_thr)
+    else:
+        model = MMDistributedDataParallel(
+            model.cuda(),
+            device_ids=[torch.cuda.current_device()],
+            broadcast_buffers=False)
+        outputs = multi_gpu_test(model, data_loader, args.tmpdir,
+                                 args.gpu_collect)
+
+    rank, _ = get_dist_info()
+    if rank == 0:
+        if args.out:
+            print(f'\nwriting results to {args.out}')
+            mmcv.dump(outputs, args.out)
+        kwargs = {} if args.eval_options is None else args.eval_options
+        if args.format_only:
+            dataset.format_results(outputs, **kwargs)
+        if args.eval:
+            eval_kwargs = cfg.get('evaluation', {}).copy()
+            # hard-code way to remove EvalHook args
+            for key in [
+                    'interval', 'tmpdir', 'start', 'gpu_collect', 'save_best',
+                    'rule', 'dynamic_intervals'
+            ]:
+                eval_kwargs.pop(key, None)
+            eval_kwargs.update(dict(metric=args.eval, **kwargs))
+            metric = dataset.evaluate(outputs, **eval_kwargs)
+            print(metric)
+            metric_dict = dict(config=args.config, metric=metric)
+            if args.work_dir is not None and rank == 0:
+                mmcv.dump(metric_dict, json_file)
+
+
+if __name__ == '__main__':
+    main()

detection/train.py

+# --------------------------------------------------------
+# InternImage
+# Copyright (c) 2022 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+
+import argparse
+import copy
+import os
+import os.path as osp
+import time
+import warnings
+
+import mmcv
+import torch
+import torch.distributed as dist
+from mmcv import Config, DictAction
+from mmcv.runner import get_dist_info, init_dist
+from mmcv.utils import get_git_hash
+
+from mmdet import __version__
+from mmdet.apis import init_random_seed, set_random_seed, train_detector
+from mmdet.datasets import build_dataset
+from mmdet.models import build_detector
+from mmdet.utils import (collect_env, get_device, get_root_logger,
+                         replace_cfg_vals, setup_multi_processes,
+                         update_data_root)
+import mmcv_custom  # noqa: F401,F403
+import mmdet_custom  # noqa: F401,F403
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='Train a detector')
+    parser.add_argument('config', help='train config file path')
+    parser.add_argument('--work-dir', help='the dir to save logs and models')
+    parser.add_argument('--resume-from',
+                        help='the checkpoint file to resume from')
+    parser.add_argument('--auto-resume',
+                        action='store_true',
+                        help='resume from the latest checkpoint automatically')
+    parser.add_argument(
+        '--no-validate',
+        action='store_true',
+        help='whether not to evaluate the checkpoint during training')
+    group_gpus = parser.add_mutually_exclusive_group()
+    group_gpus.add_argument(
+        '--gpus',
+        type=int,
+        help='(Deprecated, please use --gpu-id) number of gpus to use '
+        '(only applicable to non-distributed training)')
+    group_gpus.add_argument(
+        '--gpu-ids',
+        type=int,
+        nargs='+',
+        help='(Deprecated, please use --gpu-id) ids of gpus to use '
+        '(only applicable to non-distributed training)')
+    group_gpus.add_argument('--gpu-id',
+                            type=int,
+                            default=0,
+                            help='id of gpu to use '
+                            '(only applicable to non-distributed training)')
+    parser.add_argument('--seed', type=int, default=None, help='random seed')
+    parser.add_argument(
+        '--diff-seed',
+        action='store_true',
+        help='Whether or not set different seeds for different ranks')
+    parser.add_argument(
+        '--deterministic',
+        action='store_true',
+        help='whether to set deterministic options for CUDNN backend.')
+    parser.add_argument(
+        '--options',
+        nargs='+',
+        action=DictAction,
+        help='override some settings in the used config, the key-value pair '
+        'in xxx=yyy format will be merged into config file (deprecate), '
+        'change to --cfg-options instead.')
+    parser.add_argument(
+        '--cfg-options',
+        nargs='+',
+        action=DictAction,
+        help='override some settings in the used config, the key-value pair '
+        'in xxx=yyy format will be merged into config file. If the value to '
+        'be overwritten is a list, it should be like key="[a,b]" or key=a,b '
+        'It also allows nested list/tuple values, e.g. key="[(a,b),(c,d)]" '
+        'Note that the quotation marks are necessary and that no white space '
+        'is allowed.')
+    parser.add_argument('--launcher',
+                        choices=['none', 'pytorch', 'slurm', 'mpi'],
+                        default='none',
+                        help='job launcher')
+    parser.add_argument('--local_rank', type=int, default=0)
+    parser.add_argument('--auto-scale-lr',
+                        action='store_true',
+                        help='enable automatically scaling LR.')
+    args = parser.parse_args()
+    if 'LOCAL_RANK' not in os.environ:
+        os.environ['LOCAL_RANK'] = str(args.local_rank)
+
+    if args.options and args.cfg_options:
+        raise ValueError(
+            '--options and --cfg-options cannot be both '
+            'specified, --options is deprecated in favor of --cfg-options')
+    if args.options:
+        warnings.warn('--options is deprecated in favor of --cfg-options')
+        args.cfg_options = args.options
+
+    return args
+
+
+def main():
+    args = parse_args()
+
+    cfg = Config.fromfile(args.config)
+
+    # replace the ${key} with the value of cfg.key
+    cfg = replace_cfg_vals(cfg)
+
+    # update data root according to MMDET_DATASETS
+    update_data_root(cfg)
+
+    if args.cfg_options is not None:
+        cfg.merge_from_dict(args.cfg_options)
+
+    if args.auto_scale_lr:
+        if 'auto_scale_lr' in cfg and \
+                'enable' in cfg.auto_scale_lr and \
+                'base_batch_size' in cfg.auto_scale_lr:
+            cfg.auto_scale_lr.enable = True
+        else:
+            warnings.warn('Can not find "auto_scale_lr" or '
+                          '"auto_scale_lr.enable" or '
+                          '"auto_scale_lr.base_batch_size" in your'
+                          ' configuration file. Please update all the '
+                          'configuration files to mmdet >= 2.24.1.')
+
+    # set multi-process settings
+    setup_multi_processes(cfg)
+
+    # set cudnn_benchmark
+    if cfg.get('cudnn_benchmark', False):
+        torch.backends.cudnn.benchmark = True
+
+    # work_dir is determined in this priority: CLI > segment in file > filename
+    if args.work_dir is not None:
+        # update configs according to CLI args if args.work_dir is not None
+        cfg.work_dir = args.work_dir
+    elif cfg.get('work_dir', None) is None:
+        # use config filename as default work_dir if cfg.work_dir is None
+        cfg.work_dir = osp.join('./work_dirs',
+                                osp.splitext(osp.basename(args.config))[0])
+
+    if args.resume_from is not None:
+        cfg.resume_from = args.resume_from
+    cfg.auto_resume = args.auto_resume
+    if args.gpus is not None:
+        cfg.gpu_ids = range(1)
+        warnings.warn('`--gpus` is deprecated because we only support '
+                      'single GPU mode in non-distributed training. '
+                      'Use `gpus=1` now.')
+    if args.gpu_ids is not None:
+        cfg.gpu_ids = args.gpu_ids[0:1]
+        warnings.warn('`--gpu-ids` is deprecated, please use `--gpu-id`. '
+                      'Because we only support single GPU mode in '
+                      'non-distributed training. Use the first GPU '
+                      'in `gpu_ids` now.')
+    if args.gpus is None and args.gpu_ids is None:
+        cfg.gpu_ids = [args.gpu_id]
+
+    # init distributed env first, since logger depends on the dist info.
+    if args.launcher == 'none':
+        distributed = False
+    else:
+        distributed = True
+        init_dist(args.launcher, **cfg.dist_params)
+        # re-set gpu_ids with distributed training mode
+        _, world_size = get_dist_info()
+        cfg.gpu_ids = range(world_size)
+
+    # create work_dir
+    mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
+    # dump config
+    cfg.dump(osp.join(cfg.work_dir, osp.basename(args.config)))
+    # init the logger before other steps
+    timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
+    log_file = osp.join(cfg.work_dir, f'{timestamp}.log')
+    logger = get_root_logger(log_file=log_file, log_level=cfg.log_level)
+
+    # init the meta dict to record some important information such as
+    # environment info and seed, which will be logged
+    meta = dict()
+    # log env info
+    env_info_dict = collect_env()
+    env_info = '\n'.join([(f'{k}: {v}') for k, v in env_info_dict.items()])
+    dash_line = '-' * 60 + '\n'
+    logger.info('Environment info:\n' + dash_line + env_info + '\n' +
+                dash_line)
+    meta['env_info'] = env_info
+    meta['config'] = cfg.pretty_text
+    # log some basic info
+    logger.info(f'Distributed training: {distributed}')
+    logger.info(f'Config:\n{cfg.pretty_text}')
+
+    cfg.device = get_device()
+    # set random seeds
+    seed = init_random_seed(args.seed, device=cfg.device)
+    seed = seed + dist.get_rank() if args.diff_seed else seed
+    logger.info(f'Set random seed to {seed}, '
+                f'deterministic: {args.deterministic}')
+    set_random_seed(seed, deterministic=args.deterministic)
+    cfg.seed = seed
+    meta['seed'] = seed
+    meta['exp_name'] = osp.basename(args.config)
+
+    model = build_detector(cfg.model,
+                           train_cfg=cfg.get('train_cfg'),
+                           test_cfg=cfg.get('test_cfg'))
+    model.init_weights()
+
+    datasets = [build_dataset(cfg.data.train)]
+    if len(cfg.workflow) == 2:
+        val_dataset = copy.deepcopy(cfg.data.val)
+        val_dataset.pipeline = cfg.data.train.pipeline
+        datasets.append(build_dataset(val_dataset))
+    if cfg.checkpoint_config is not None:
+        # save mmdet version, config file content and class names in
+        # checkpoints as meta data
+        cfg.checkpoint_config.meta = dict(mmdet_version=__version__ +
+                                          get_git_hash()[:7],
+                                          CLASSES=datasets[0].CLASSES)
+    # add an attribute for visualization convenience
+    model.CLASSES = datasets[0].CLASSES
+
+    torch.backends.cuda.matmul.allow_tf32 = True
+    torch.backends.cudnn.allow_tf32 = True
+
+    train_detector(model,
+                   datasets,
+                   cfg,
+                   distributed=distributed,
+                   validate=(not args.no_validate),
+                   timestamp=timestamp,
+                   meta=meta)
+
+
+if __name__ == '__main__':
+    main()
\ No newline at end of file

segmentation/README.md

+# InternImage for Semantic Segmentation
+
+This folder contains the implementation of the InternImage for semantic segmentation. 
+
+Our segmentation code is developed on top of [MMSegmentation v0.27.0](https://github.com/open-mmlab/mmsegmentation/tree/v0.27.0).
+
+
+## Usage
+
+### Install
+
+- Clone this repo:
+
+```bash
+git clone https://github.com/OpenGVLab/InternImage.git
+cd InternImage
+```
+
+- Create a conda virtual environment and activate it:
+
+```bash
+conda create -n internimage python=3.7 -y
+conda activate internimage
+```
+
+- Install `CUDA>=10.2` with `cudnn>=7` following
+  the [official installation instructions](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html)
+- Install `PyTorch>=1.8.0` and `torchvision>=0.9.0` with `CUDA>=10.2`:
+
+For examples, to install torch==1.11 with CUDA==11.3:
+```bash
+pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113  -f https://download.pytorch.org/whl/torch_stable.html
+```
+
+- Install `timm==0.6.11` and `mmcv-full==1.5.0`:
+
+```bash
+pip install -U openmim
+mim install mmcv-full==1.5.0
+pip install timm==0.6.11 mmdet==2.28.1
+```
+
+- Install other requirements:
+
+```bash
+pip install opencv-python termcolor yacs pyyaml scipy
+```
+
+- Compile CUDA operators
+```bash
+cd ./ops_dcnv3
+sh ./make.sh
+# unit test (should see all checking is True)
+python test.py
+```
+
+## Data Preparation
+
+Prepare ADE20K according to the [guidelines](https://github.com/open-mmlab/mmsegmentation/blob/master/docs/en/dataset_prepare.md#prepare-datasets) in MMSegmentation.
+
+
+### Evaluation
+
+To evaluate our `InternImage` on ADE20K val, run:
+
+```bash
+sh dist_test.sh <config-file> <checkpoint> <gpu-num> --eval mIoU
+```
+
+For example, to evaluate the `InternImage-T` with a single GPU:
+
+```bash
+python test.py configs/upernet/upernet_internimage_t_512_160k_ade20k.py checkpoint_dir/seg/upernet_internimage_t_512_160k_ade20k.pth --eval mIoU
+```
+
+For example, to evaluate the `InternImage-B` with a single node with 8 GPUs:
+
+```bash
+sh dist_test.sh configs/upernet/upernet_internimage_b_512_160k_ade20k.py checkpoint_dir/seg/upernet_internimage_b_512_160k_ade20k.py 8 --eval mIoU
+```
+
+### Training on ADE20K
+
+To train an `InternImage` on ADE20K, run:
+
+```bash
+sh dist_train.sh <config-file> <gpu-num>
+```
+
+For example, to train `InternImage-T` with 8 GPU on 1 node, run:
+
+```bash
+sh dist_train.sh configs/upernet/upernet_internimage_t_512_160k_ade20k.py 8
+```
+
+### Manage jobs with Srun
+
+For example, to train `InternImage-XL` with 8 GPU on 1 node, run:
+
+```bash
+GPUS=8 sh slurm_train.sh <partition> <job-name> configs/upernet/upernet_internimage_xl_640_160k_ade20k.py
+```

segmentation/configs/_base_/datasets/ade20k.py

+# dataset settings
+dataset_type = 'ADE20KDataset'
+data_root = 'data/ADEChallengeData2016'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2048, 512),
+        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=4,
+    workers_per_gpu=4,
+    train=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='images/training',
+        ann_dir='annotations/training',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='images/validation',
+        ann_dir='annotations/validation',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='images/validation',
+        ann_dir='annotations/validation',
+        pipeline=test_pipeline))

segmentation/configs/_base_/default_runtime.py

+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook', by_epoch=False),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
+cudnn_benchmark = True

segmentation/configs/_base_/models/upernet_r50.py

+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 1, 1),
+        strides=(1, 2, 2, 2),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='UPerHead',
+        in_channels=[256, 512, 1024, 2048],
+        in_index=[0, 1, 2, 3],
+        pool_scales=(1, 2, 3, 6),
+        channels=512,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    # model training and testing settings
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))

segmentation/configs/_base_/schedules/schedule_160k.py

+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optimizer_config = dict()
+# learning policy
+lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
+# runtime settings
+runner = dict(type='IterBasedRunner', max_iters=160000)
+checkpoint_config = dict(by_epoch=False, interval=16000)
+evaluation = dict(interval=16000, metric='mIoU', pre_eval=True)

segmentation/configs/upernet/README.md

+# UPerNet
+
+[Unified Perceptual Parsing for Scene Understanding](https://arxiv.org/pdf/1807.10221.pdf)
+
+## Introduction
+
+<!-- [ABSTRACT] -->
+
+Humans recognize the visual world at multiple levels: we effortlessly categorize scenes and detect objects inside, while also identifying the textures and surfaces of the objects along with their different compositional parts. In this paper, we study a new task called Unified Perceptual Parsing, which requires the machine vision systems to recognize as many visual concepts as possible from a given image. A multi-task framework called UPerNet and a training strategy are developed to learn from heterogeneous image annotations. We benchmark our framework on Unified Perceptual Parsing and show that it is able to effectively segment a wide range of concepts from images. The trained networks are further applied to discover visual knowledge in natural scenes. Models are available at [this https URL](https://github.com/CSAILVision/unifiedparsing).
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/24582831/142903077-44e8e0da-7276-4bda-bd2b-0df1680ca845.png" width="70%"/>
+</div>
+
+## Results and models
+
+### ADE20K
+
+**ADE20K Semantic Segmentation**
+
+|    backbone    | resolution | single scale | multi scale | #params | FLOPs | Download | 
+| :------------: | :--------: | :----------: | :---------: | :-----: | :---: |   :---:  |
+| InternImage-T  |  512x512   |     47.9     |    48.1     |   59M   | 944G  | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_t_512_160k_ade20k.pth) \| [cfg](./upernet_internimage_t_512_160k_ade20k.py) |
+| InternImage-S  |  512x512   |     50.1     |    50.9     |   80M   | 1017G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_s_512_160k_ade20k.pth) \| [cfg](./upernet_internimage_s_512_160k_ade20k.py) |
+| InternImage-B  |  512x512   |     50.8     |    51.3     |  128M   | 1185G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_b_512_160k_ade20k.pth) \| [cfg](./upernet_internimage_b_512_160k_ade20k.py) |
+| InternImage-L  |  640x640   |     53.9     |    54.1     |  256M   | 2526G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_l_640_160k_ade20k.pth) \| [cfg](./upernet_internimage_l_640_160k_ade20k.py) |
+| InternImage-XL |  640x640   |     55.0     |    55.3     |  368M   | 3142G | [ckpt](https://github.com/OpenGVLab/InternImage/releases/download/seg_models/upernet_internimage_xl_640_160k_ade20k.pth) \| [cfg](./upernet_internimage_xl_640_160k_ade20k.py) |
+

segmentation/configs/upernet/upernet_internimage_b_512_160k_ade20k.py

+# --------------------------------------------------------
+# InternImage
+# Copyright (c) 2022 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+_base_ = [
+    '../_base_/models/upernet_r50.py', '../_base_/datasets/ade20k.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
+]
+pretrained = 'https://github.com/OpenGVLab/InternImage/releases/download/cls_model/internimage_b_1k_224.pth'
+model = dict(
+    backbone=dict(
+        _delete_=True,
+        type='InternImage',
+        core_op='DCNv3',
+        channels=112,
+        depths=[4, 4, 21, 4],
+        groups=[7, 14, 28, 56],
+        mlp_ratio=4.,
+        drop_path_rate=0.4,
+        norm_layer='LN',
+        layer_scale=1.0,
+        offset_scale=1.0,
+        post_norm=True,
+        with_cp=False,
+        out_indices=(0, 1, 2, 3),
+        init_cfg=dict(type='Pretrained', checkpoint=pretrained)),
+    decode_head=dict(num_classes=150, in_channels=[112, 224, 448, 896]),
+    auxiliary_head=dict(num_classes=150, in_channels=448),
+    test_cfg=dict(mode='whole')
+)
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2048, 512),
+        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='ResizeToMultiple', size_divisor=32),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+optimizer = dict(
+    _delete_=True, type='AdamW', lr=0.00006, betas=(0.9, 0.999), weight_decay=0.05,
+    constructor='CustomLayerDecayOptimizerConstructor',
+    paramwise_cfg=dict(num_layers=30, layer_decay_rate=1.0,
+                       depths=[4, 4, 18, 4]))
+lr_config = dict(_delete_=True, policy='poly',
+                 warmup='linear',
+                 warmup_iters=1500,
+                 warmup_ratio=1e-6,
+                 power=1.0, min_lr=0.0, by_epoch=False)
+# By default, models are trained on 8 GPUs with 2 images per GPU
+data=dict(samples_per_gpu=2,
+          val=dict(pipeline=test_pipeline),
+          test=dict(pipeline=test_pipeline))
+runner = dict(type='IterBasedRunner')
+checkpoint_config = dict(by_epoch=False, interval=1000, max_keep_ckpts=1)
+evaluation = dict(interval=16000, metric='mIoU', save_best='mIoU')
+# fp16 = dict(loss_scale=dict(init_scale=512))

segmentation/configs/upernet/upernet_internimage_l_640_160k_ade20k.py

+# --------------------------------------------------------
+# InternImage
+# Copyright (c) 2022 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+_base_ = [
+    '../_base_/models/upernet_r50.py', '../_base_/datasets/ade20k.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
+]
+pretrained = 'https://github.com/OpenGVLab/InternImage/releases/download/cls_model/internimage_l_22k_192to384.pth'
+model = dict(
+    backbone=dict(
+        _delete_=True,
+        type='InternImage',
+        core_op='DCNv3',
+        channels=160,
+        depths=[5, 5, 22, 5],
+        groups=[10, 20, 40, 80],
+        mlp_ratio=4.,
+        drop_path_rate=0.4,
+        norm_layer='LN',
+        layer_scale=1.0,
+        offset_scale=2.0,
+        post_norm=True,
+        with_cp=False,
+        out_indices=(0, 1, 2, 3),
+        init_cfg=dict(type='Pretrained', checkpoint=pretrained)),
+    decode_head=dict(num_classes=150, in_channels=[160, 320, 640, 1280]),
+    auxiliary_head=dict(num_classes=150, in_channels=640),
+    test_cfg=dict(mode='whole'))
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+crop_size = (640, 640)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='Resize', img_scale=(2560, 640), ratio_range=(0.5, 2.0)),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2560, 640),
+        # img_ratios=[0.75, 1.0, 1.25],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='ResizeToMultiple', size_divisor=32),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+optimizer = dict(
+    _delete_=True, type='AdamW', lr=0.00002, betas=(0.9, 0.999), weight_decay=0.05,
+    constructor='CustomLayerDecayOptimizerConstructor',
+    paramwise_cfg=dict(num_layers=37, layer_decay_rate=0.94,
+                       depths=[5, 5, 22, 5], offset_lr_scale=1.0))
+lr_config = dict(_delete_=True, policy='poly',
+                 warmup='linear',
+                 warmup_iters=1500,
+                 warmup_ratio=1e-6,
+                 power=1.0, min_lr=0.0, by_epoch=False)
+# By default, models are trained on 8 GPUs with 2 images per GPU
+data = dict(samples_per_gpu=2,
+            train=dict(pipeline=train_pipeline),
+            val=dict(pipeline=test_pipeline),
+            test=dict(pipeline=test_pipeline))
+runner = dict(type='IterBasedRunner')
+optimizer_config = dict(_delete_=True, grad_clip=dict(max_norm=0.1, norm_type=2))
+checkpoint_config = dict(by_epoch=False, interval=1000, max_keep_ckpts=1)
+evaluation = dict(interval=16000, metric='mIoU', save_best='mIoU')
+# fp16 = dict(loss_scale=dict(init_scale=512))

segmentation/configs/upernet/upernet_internimage_s_512_160k_ade20k.py

+# --------------------------------------------------------
+# InternImage
+# Copyright (c) 2022 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+_base_ = [
+    '../_base_/models/upernet_r50.py', '../_base_/datasets/ade20k.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
+]
+pretrained = 'https://github.com/OpenGVLab/InternImage/releases/download/cls_model/internimage_s_1k_224.pth'
+model = dict(
+    backbone=dict(
+        _delete_=True,
+        type='InternImage',
+        core_op='DCNv3',
+        channels=80,
+        depths=[4, 4, 21, 4],
+        groups=[5, 10, 20, 40],
+        mlp_ratio=4.,
+        drop_path_rate=0.3,
+        norm_layer='LN',
+        layer_scale=1.0,
+        offset_scale=1.0,
+        post_norm=True,
+        with_cp=False,
+        init_cfg=dict(type='Pretrained', checkpoint=pretrained)),
+    decode_head=dict(num_classes=150, in_channels=[80, 160, 320, 640]),
+    auxiliary_head=dict(num_classes=150, in_channels=320),
+    test_cfg=dict(mode='whole')
+)
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2048, 512),
+        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='ResizeToMultiple', size_divisor=32),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+optimizer = dict(
+    _delete_=True, type='AdamW', lr=0.00006, betas=(0.9, 0.999), weight_decay=0.05,
+    constructor='CustomLayerDecayOptimizerConstructor',
+    paramwise_cfg=dict(num_layers=33, layer_decay_rate=1.0,
+                       depths=[4, 4, 21, 4]))
+lr_config = dict(_delete_=True, policy='poly',
+                 warmup='linear',
+                 warmup_iters=1500,
+                 warmup_ratio=1e-6,
+                 power=1.0, min_lr=0.0, by_epoch=False)
+# By default, models are trained on 8 GPUs with 2 images per GPU
+data=dict(samples_per_gpu=2,
+          val=dict(pipeline=test_pipeline),
+          test=dict(pipeline=test_pipeline))
+runner = dict(type='IterBasedRunner')
+checkpoint_config = dict(by_epoch=False, interval=1000, max_keep_ckpts=1)
+evaluation = dict(interval=16000, metric='mIoU', save_best='mIoU')
+# fp16 = dict(loss_scale=dict(init_scale=512))

segmentation/configs/upernet/upernet_internimage_t_512_160k_ade20k.py

+# --------------------------------------------------------
+# InternImage
+# Copyright (c) 2022 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+_base_ = [
+    '../_base_/models/upernet_r50.py', '../_base_/datasets/ade20k.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
+]
+pretrained = 'https://github.com/OpenGVLab/InternImage/releases/download/cls_model/internimage_t_1k_224.pth'
+model = dict(
+    backbone=dict(
+        _delete_=True,
+        type='InternImage',
+        core_op='DCNv3',
+        channels=64,
+        depths=[4, 4, 18, 4],
+        groups=[4, 8, 16, 32],
+        mlp_ratio=4.,
+        drop_path_rate=0.2,
+        norm_layer='LN',
+        layer_scale=1.0,
+        offset_scale=1.0,
+        post_norm=False,
+        with_cp=False,
+        out_indices=(0, 1, 2, 3),
+        init_cfg=dict(type='Pretrained', checkpoint=pretrained)),
+    decode_head=dict(num_classes=150, in_channels=[64, 128, 256, 512]),
+    auxiliary_head=dict(num_classes=150, in_channels=256),
+    test_cfg=dict(mode='whole')
+)
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2048, 512),
+        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='ResizeToMultiple', size_divisor=32),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+optimizer = dict(
+    _delete_=True, type='AdamW', lr=0.00006, betas=(0.9, 0.999), weight_decay=0.05,
+    constructor='CustomLayerDecayOptimizerConstructor',
+    paramwise_cfg=dict(num_layers=30, layer_decay_rate=1.0,
+                       depths=[4, 4, 18, 4]))
+lr_config = dict(_delete_=True, policy='poly',
+                 warmup='linear',
+                 warmup_iters=1500,
+                 warmup_ratio=1e-6,
+                 power=1.0, min_lr=0.0, by_epoch=False)
+# By default, models are trained on 8 GPUs with 2 images per GPU
+data=dict(samples_per_gpu=2,
+          val=dict(pipeline=test_pipeline),
+          test=dict(pipeline=test_pipeline))
+runner = dict(type='IterBasedRunner')
+checkpoint_config = dict(by_epoch=False, interval=1000, max_keep_ckpts=1)
+evaluation = dict(interval=16000, metric='mIoU', save_best='mIoU')
+# fp16 = dict(loss_scale=dict(init_scale=512))

segmentation/configs/upernet/upernet_internimage_xl_640_160k_ade20k.py

+# --------------------------------------------------------
+# InternImage
+# Copyright (c) 2022 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+_base_ = [
+    '../_base_/models/upernet_r50.py', '../_base_/datasets/ade20k.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
+]
+pretrained = 'https://github.com/OpenGVLab/InternImage/releases/download/cls_model/internimage_xl_22k_192to384.pth'
+model = dict(
+    backbone=dict(
+        _delete_=True,
+        type='InternImage',
+        core_op='DCNv3',
+        channels=192,
+        depths=[5, 5, 24, 5],
+        groups=[12, 24, 48, 96],
+        mlp_ratio=4.,
+        drop_path_rate=0.4,
+        norm_layer='LN',
+        layer_scale=1.0,
+        offset_scale=2.0,
+        post_norm=True,
+        with_cp=False,
+        out_indices=(0, 1, 2, 3),
+        init_cfg=dict(type='Pretrained', checkpoint=pretrained)),
+    decode_head=dict(num_classes=150, in_channels=[192, 384, 768, 1536]),
+    auxiliary_head=dict(num_classes=150, in_channels=768),
+    test_cfg=dict(mode='whole'))
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+crop_size = (640, 640)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='Resize', img_scale=(2560, 640), ratio_range=(0.5, 2.0)),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2560, 640),
+        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='ResizeToMultiple', size_divisor=32),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+optimizer = dict(
+    _delete_=True, type='AdamW', lr=0.00002, betas=(0.9, 0.999), weight_decay=0.05,
+    constructor='CustomLayerDecayOptimizerConstructor',
+    paramwise_cfg=dict(num_layers=39, layer_decay_rate=0.94,
+                       depths=[5, 5, 24, 5], offset_lr_scale=1.0))
+lr_config = dict(_delete_=True, policy='poly',
+                 warmup='linear',
+                 warmup_iters=1500,
+                 warmup_ratio=1e-6,
+                 power=1.0, min_lr=0.0, by_epoch=False)
+# By default, models are trained on 8 GPUs with 2 images per GPU
+data = dict(samples_per_gpu=2,
+            train=dict(pipeline=train_pipeline),
+            val=dict(pipeline=test_pipeline),
+            test=dict(pipeline=test_pipeline))
+runner = dict(type='IterBasedRunner')
+optimizer_config = dict(_delete_=True, grad_clip=dict(max_norm=0.1, norm_type=2))
+checkpoint_config = dict(by_epoch=False, interval=1000, max_keep_ckpts=1)
+evaluation = dict(interval=16000, metric='mIoU', save_best='mIoU')
+# fp16 = dict(loss_scale=dict(init_scale=512))

segmentation/dist_test.sh

+#!/usr/bin/env bash
+
+CONFIG=$1
+CHECKPOINT=$2
+GPUS=$3
+PORT=${PORT:-29510}
+PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \
+python -m torch.distributed.launch --nproc_per_node=$GPUS --master_port=$PORT \
+    $(dirname "$0")/test.py $CONFIG $CHECKPOINT --launcher pytorch ${@:4}

segmentation/dist_train.sh

+#!/usr/bin/env bash
+
+CONFIG=$1
+GPUS=$2
+PORT=${PORT:-29300}
+
+PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \
+python -m torch.distributed.launch --nproc_per_node=$GPUS --master_port=$PORT \
+    $(dirname "$0")/train.py $CONFIG --launcher pytorch ${@:3}