Python mmcv.ProgressBar() Examples

The following are 30 code examples of mmcv.ProgressBar(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module mmcv , or try the search function .
Example #1
Source File: test.py    From Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection with Apache License 2.0 6 votes vote down vote up 
def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results
Example #2
Source File: test.py    From GCNet with Apache License 2.0 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #3
Source File: test.py    From hrnet with MIT License 6 votes vote down vote up 
def single_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg,
                                     dataset=dataset.CLASSES)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #4
Source File: test.py    From Grid-R-CNN with Apache License 2.0 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #5
Source File: test_ensemble.py    From kaggle-imaterialist with MIT License 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #6
Source File: test_robustness.py    From RDSNet with Apache License 2.0 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #7
Source File: test_robustness.py    From RDSNet with Apache License 2.0 6 votes vote down vote up 
def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results
Example #8
Source File: test.py    From RDSNet with Apache License 2.0 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, score_thr=0.3)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #9
Source File: test.py    From RDSNet with Apache License 2.0 6 votes vote down vote up 
def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results
Example #10
Source File: test.py    From kaggle-imaterialist with MIT License 6 votes vote down vote up 
def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results
Example #11
Source File: test_robustness.py    From IoU-Uniform-R-CNN with Apache License 2.0 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #12
Source File: test_robustness.py    From IoU-Uniform-R-CNN with Apache License 2.0 6 votes vote down vote up 
def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results
Example #13
Source File: test.py    From IoU-Uniform-R-CNN with Apache License 2.0 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #14
Source File: test.py    From kaggle-imaterialist with MIT License 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #15
Source File: test.py    From Reasoning-RCNN with Apache License 2.0 6 votes vote down vote up 
def single_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg,
                                     dataset='vg', score_thr=0.4, save_num='work_dirs/fpn_hkrm/0.3_vghkrm_%08d'%i + '.jpg')
                                     # dataset=dataset.CLASSES)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #16
Source File: test.py    From Grid-R-CNN with Apache License 2.0 6 votes vote down vote up 
def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results
Example #17
Source File: test.py    From Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection with Apache License 2.0 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #18
Source File: test.py    From Libra_R-CNN with Apache License 2.0 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #19
Source File: test.py    From Libra_R-CNN with Apache License 2.0 6 votes vote down vote up 
def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results
Example #20
Source File: test_robustness.py    From Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection with Apache License 2.0 6 votes vote down vote up 
def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results
Example #21
Source File: test_robustness.py    From FoveaBox with Apache License 2.0 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #22
Source File: test_robustness.py    From FoveaBox with Apache License 2.0 6 votes vote down vote up 
def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results
Example #23
Source File: test.py    From FoveaBox with Apache License 2.0 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #24
Source File: test.py    From FoveaBox with Apache License 2.0 6 votes vote down vote up 
def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results
Example #25
Source File: test.py    From FNA with Apache License 2.0 6 votes vote down vote up 
def single_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg,
                                     dataset=dataset.CLASSES)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #26
Source File: test_robustness.py    From Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection with Apache License 2.0 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #27
Source File: test_robustness.py    From Cascade-RPN with Apache License 2.0 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result, dataset.img_norm_cfg)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #28
Source File: test_robustness.py    From Cascade-RPN with Apache License 2.0 6 votes vote down vote up 
def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results
Example #29
Source File: test.py    From Cascade-RPN with Apache License 2.0 6 votes vote down vote up 
def single_gpu_test(model, data_loader, show=False):
    model.eval()
    results = []
    dataset = data_loader.dataset
    prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=not show, **data)
        results.append(result)

        if show:
            model.module.show_result(data, result)

        batch_size = data['img'][0].size(0)
        for _ in range(batch_size):
            prog_bar.update()
    return results
Example #30
Source File: test.py    From Cascade-RPN with Apache License 2.0 6 votes vote down vote up 
def multi_gpu_test(model, data_loader, tmpdir=None):
    model.eval()
    results = []
    dataset = data_loader.dataset
    rank, world_size = get_dist_info()
    if rank == 0:
        prog_bar = mmcv.ProgressBar(len(dataset))
    for i, data in enumerate(data_loader):
        with torch.no_grad():
            result = model(return_loss=False, rescale=True, **data)
        results.append(result)

        if rank == 0:
            batch_size = data['img'][0].size(0)
            for _ in range(batch_size * world_size):
                prog_bar.update()

    # collect results from all ranks
    results = collect_results(results, len(dataset), tmpdir)

    return results