Open wangm-word opened 3 years ago
first,thank you for your Answer,could you give some examples about the 'img_data_with_bbox'?is this a detector model about person?
import matplotlib.pyplot as plt from mmpose.apis.inference import init_pose_model, inference_top_down_pose_model model = init_pose_model(config_path, ckpt_path, device=device) results, heatmaps= inference_top_down_pose_model(model, inputs['image'], img_data_with_bbox, return_heatmap=True, format='xyxy', dataset='TopDownCocoDataset') ## Visualize Results hms =heatmaps[0]['heatmap'] result = results[0] keypoints = ([np.array([v[0],v[1]]) for v in result['keypoints']]) #Plot image and keypoints plt.figure() plt.scatter(*zip(*keypoints)) plt.imshow(result['image']) plt.show() #Plot heatmaps in a grid n_hms = np.shape(hms)[1] f, axarr = plt.subplots(3, 4, figsize=(15,15)) this_col=0 for idx in range(n_hms): this_hm = hms[0,idx,:,:] row = idx % 4 this_ax = axarr[this_col, row] this_ax.set_title(f'{idx}') hm_display = this_ax.imshow(this_hm, cmap='jet', vmin=0, vmax=1) if row == 3: this_col += 1 cb=f.colorbar(hm_display, ax=axarr)
Note that img_data_with_bbox is a list of dicts, where dicts should contain 'bbox' key. For more info checkout the mmpose documentation
img_data_with_bbox
If you care about inference speed, you can fuse conv and batch norm layers in the model. See tools/test.py for the code
tools/test.py
Originally posted by @kuldeepbrd1 in https://github.com/HRNet/Lite-HRNet/issues/23#issuecomment-841660213
first,thank you for your Answer,could you give some examples about the 'img_data_with_bbox'?is this a detector model about person?
Note that
img_data_with_bbox
is a list of dicts, where dicts should contain 'bbox' key. For more info checkout the mmpose documentationIf you care about inference speed, you can fuse conv and batch norm layers in the model. See
tools/test.py
for the codeOriginally posted by @kuldeepbrd1 in https://github.com/HRNet/Lite-HRNet/issues/23#issuecomment-841660213