def vis_on_loader(self, loader, savedir_images, epoch=None):
self.model.eval()
count = 0
for batch in tqdm.tqdm(loader):
if batch['label'][0][1:].sum() == 0:
continue
cam_dict = self.make_multiscale_cam(batch)
keys = cam_dict['keys']
high_res = cam_dict['high_res']
im_rgb = batch['original'][0]
pred_cam = hu.f2l(hi.gray2cmap(cam_dict['cam_crf']))
hu.save_image(
os.path.join(
savedir_images,
batch['meta'][0]['name'] + '_cam_epoch:%d.jpg' % (epoch)),
0.5 * (np.array(im_rgb / 255.)) + 0.5 * pred_cam)
for i, k in enumerate(keys):
pred = hu.f2l(hi.gray2cmap(high_res[i]))
# im_rgb = hu.denormalize(im, 'rgb')
# im_rgb = hu.f2l(im_rgb)
hu.save_image(
os.path.join(
savedir_images, batch['meta'][0]['name'] +
'_class:%d_epoch:%d.jpg' % (k, epoch)),
0.5 * (np.array(im_rgb / 255.)) + 0.5 * pred)
if count > 3:
break
count += 1
def vis_on_batch(self, batch, savedir_image):
self.eval()
images = batch["images"].to('cpu') #helen changed this from .cuda()
#print(images)
#print(images.shape)
points = batch["points"].long().to(
'cpu') #helen changed this from .cuda()
logits = self.model.forward(images)
probs = logits.sigmoid().cpu().numpy()
blobs = lcfcn_loss.get_blobs(probs=probs)
pred_counts = (np.unique(blobs) != 0).sum()
pred_blobs = blobs
pred_probs = probs.squeeze()
# loc
pred_count = pred_counts.ravel()[0]
pred_blobs = pred_blobs.squeeze()
img_org = hu.get_image(batch["images"], denorm="rgb")
# true points
y_list, x_list = np.where(batch["points"][0].long().numpy().squeeze())
img_peaks = hi.points_on_image(y_list, x_list, img_org, radius=11)
text = "%s ground truth" % (batch["points"].sum().item())
hi.text_on_image(text=text, image=img_peaks)
# pred points
pred_points = lcfcn_loss.blobs2points(pred_blobs).squeeze()
y_list, x_list = np.where(pred_points.squeeze())
img_pred = hi.mask_on_image(img_org, pred_blobs)
#img_pred = hi.points_on_image(y_list, x_list, img_org)
text = "%s predicted" % (len(y_list))
hi.text_on_image(text=text, image=img_pred)
# *************** helen added this code
plt.imshow(
img_pred
) #these lines of code display the image with the model's predications on it
plt.show()
# *************** end of helen's code
# heatmap
heatmap = hi.gray2cmap(pred_probs)
heatmap = hu.f2l(heatmap)
hi.text_on_image(text="lcfcn heatmap", image=heatmap)
img_mask = np.hstack([img_peaks, img_pred, heatmap])
hu.save_image(savedir_image, img_mask)
def get_blob_list(mask_dict, points_mask, img_pil, split_inst=False):
blob_list = []
mask = preds = mask_dict['preds']
probs = mask_dict['probs']
assert probs.shape[1] == preds.shape[0]
assert probs.shape[2] == preds.shape[1]
imask = np.zeros(mask.shape)
cmask = np.zeros(mask.shape)
blob_id = 1
for c in np.unique(mask):
if c == 0:
continue
probs_class = probs[c]
point_ind = points_mask == c
inst_mask = morphology.label(mask==c)
for l in np.unique(inst_mask):
if l == 0:
continue
blob_ind = inst_mask == l
locs = np.where(blob_ind * point_ind)
y_list, x_list = locs
n_points = len(y_list)
if n_points == 0:
continue
if n_points > 1 and split_inst:
# split multiple points
img_points = hi.points_on_image(y_list, x_list, img_pil)
img_masks = hi.mask_on_image(img_pil, mask)
img_masks = hi.mask_on_image(img_points.copy(), blob_ind)
hu.save_image('tmp.jpg', (img_points)*0.5 + hu.f2l(hi.gray2cmap(probs_class))*0.5)
hu.save_image('tmp.jpg', img_masks)
for yi, xi in zip(y_list, x_list):
imask, cmask, blob_list, blob_id = add_mask(yi, xi, points_mask,
blob_ind,
n_points, blob_list, imask, cmask,
blob_id)
else:
# add for that single point
yi, xi = y_list[0], x_list[0]
imask, cmask, blob_list, blob_id = add_mask(yi, xi, points_mask,
blob_ind,
n_points, blob_list, imask, cmask,
blob_id)
return blob_list, cmask.astype('uint8'), imask.astype('uint8')
def vis_on_batch_helen(self, batch, savedir_image):
self.eval()
images = batch.to('cpu')
#print(images) #print statement to check what images is for debugging
#print(images.shape) #print statement to check images has the correct shape
logits = self.model.forward(images)
probs = logits.sigmoid().cpu().numpy()
blobs = lcfcn_loss.get_blobs(probs=probs)
pred_counts = (np.unique(blobs) != 0).sum()
pred_blobs = blobs
pred_probs = probs.squeeze()
# loc
pred_count = pred_counts.ravel()[0]
pred_blobs = pred_blobs.squeeze()
img_org = hu.get_image(images, denorm="rgb")
#this is what was originally written: img_org = hu.get_image(batch["images"],denorm="rgb")
#the following lines are commented out because my own data does not have labels and will thus throw errors
# true points
#y_list, x_list = np.where(batch["points"][0].long().numpy().squeeze())
#img_peaks = hi.points_on_image(y_list, x_list, img_org, radius=11)
#text = "%s ground truth" % (batch["points"].sum().item())
#hi.text_on_image(text=text, image=img_peaks)
# pred points
pred_points = lcfcn_loss.blobs2points(pred_blobs).squeeze()
y_list, x_list = np.where(pred_points.squeeze())
img_pred = hi.mask_on_image(img_org, pred_blobs)
# img_pred = hi.points_on_image(y_list, x_list, img_org)
text = "%s predicted" % (len(y_list))
hi.text_on_image(text=text, image=img_pred)
# these lines of code display the image with the model's predications on it
plt.imshow(img_pred)
plt.show()
# heatmap
heatmap = hi.gray2cmap(pred_probs)
heatmap = hu.f2l(heatmap)
hi.text_on_image(text="lcfcn heatmap", image=heatmap)
img_mask = np.hstack([img_pred, heatmap]) #helen took out im_peaks
#this is what was originally written: img_mask = np.hstack([img_peaks, img_pred, heatmap])
hu.save_image(savedir_image, img_mask)
def mask_on_image(mask, image):
from skimage.color import color_dict, colorlabel
from skimage.segmentation import mark_boundaries
default_colors = [
'red', 'blue', 'yellow', 'magenta', 'green', 'indigo', 'darkorange',
'cyan', 'pink', 'yellowgreen'
]
image = hi.image_as_uint8(image) / 255.
labels = [l for l in np.unique(mask) if l < len(color_dict)]
colors = (default_colors + list(color_dict.keys())[len(default_colors):])
colors = np.array(colors)[labels]
image_label_overlay = label2rgb(mask,
image=hu.f2l(image).squeeze().clip(0, 1),
colors=colors,
bg_label=0,
bg_color=None,
kind='overlay')
return mark_boundaries(image_label_overlay, mask)
def vis_on_batch(self, batch, savedir_image):
self.eval()
images = batch["images"].cuda()
points = batch["points"].long().cuda()
logits = self.model_base.forward(images)
probs = logits.sigmoid().cpu().numpy()
blobs = lcfcn_loss.get_blobs(probs=probs)
pred_counts = (np.unique(blobs)!=0).sum()
pred_blobs = blobs
pred_probs = probs.squeeze()
# loc
pred_count = pred_counts.ravel()[0]
pred_blobs = pred_blobs.squeeze()
img_org = hu.get_image(batch["images"],denorm="rgb")
# true points
y_list, x_list = np.where(batch["points"][0].long().numpy().squeeze())
img_peaks = haven_img.points_on_image(y_list, x_list, img_org)
text = "%s ground truth" % (batch["points"].sum().item())
haven_img.text_on_image(text=text, image=img_peaks)
# pred points
pred_points = lcfcn_loss.blobs2points(pred_blobs).squeeze()
y_list, x_list = np.where(pred_points.squeeze())
img_pred = hi.mask_on_image(img_org, pred_blobs)
# img_pred = haven_img.points_on_image(y_list, x_list, img_org)
text = "%s predicted" % (len(y_list))
haven_img.text_on_image(text=text, image=img_pred)
# heatmap
heatmap = hi.gray2cmap(pred_probs)
heatmap = hu.f2l(heatmap)
haven_img.text_on_image(text="lcfcn heatmap", image=heatmap)
img_mask = np.hstack([img_peaks, img_pred, heatmap])
hu.save_image(savedir_image, img_mask)
def vis_on_batch(self, batch, savedir_image, save_preds=False):
self.eval()
images = batch["images"].cuda()
counts = float(batch["counts"][0])
logits = self.model_base(images)
probs = logits.sigmoid()
# get points from attention
att_dict = self.att_model.get_attention_dict(
images_original=torch.FloatTensor(
hu.denormalize(batch['images'], mode='rgb')),
counts=batch['counts'][0],
probs=probs.squeeze(),
return_roi=True)
blobs = lcfcn.get_blobs(probs.squeeze().detach().cpu().numpy())
org_img = hu.denormalize(images.squeeze(), mode='rgb')
rgb_labels = label2rgb(
blobs,
hu.f2l(org_img),
bg_label=0,
bg_color=None,
)
res1 = mark_boundaries(rgb_labels, blobs)
if att_dict['roi_mask'] is not None:
img_mask = hu.save_image('tmp2.png',
org_img,
mask=att_dict['roi_mask'] == 1,
return_image=True)
res2 = hu.save_image('tmp.png',
np.array(img_mask) / 255.,
points=att_dict['points'],
radius=1,
return_image=True)
os.makedirs(os.path.dirname(savedir_image), exist_ok=True)
# plt.savefig(savedir_image.replace('.jpg', '.png')
hu.save_image(savedir_image.replace('.jpg', '.png'),
np.hstack([res1, np.array(res2) / 255.]))
def bbox_on_image_utils(bbox_xyxy, image, text_list=None):
image = hu.f2l(image.squeeze())
image_uint8 = (image*254).astype("uint8").copy()
H, W, _ = image.shape
for i, bb in enumerate(bbox_xyxy):
x1, y1, x2, y2 = bb
x1, y1 = int(x1*W), int(y1*H)
x2, y2 = int(x2*W), int(y2*H)
# Blue color in BGR
color = (255, 0, 0)
# Line thickness of 2 px
thickness = 2
# Using cv2.rectangle() method
# Draw a rectangle with blue line borders of thickness of 2 px
image_uint8 = cv2.rectangle(image_uint8, (x1, y1), (x2, y2), color, thickness)
if text_list is not None:
image_uint8 = cv2.putText(image_uint8, str(int(text_list[i]*100)),
(x1, y1-10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255) , 1, cv2.LINE_AA)
# hu.save_image("/mnt/datasets/public/issam/prototypes/wscl/tmp.jpg", image_uint8)
return image_uint8 / 255.
def vis_on_batch(self, batch, savedir_image, save_preds=False):
# os.makedirs(savedir_image, exist_ok=True)
self.eval()
# if self.just_one:
# onnx_output = torch.onnx._export(self.model_base, batch['images'].cuda(), 'onnx_model.onnx', verbose=False, opset_version=12)
# self.just_one = False
# onnx_output = torch.onnx._export(self.model_base, torch_input.cuda(), 'onnx_model2.onnx', verbose=False, opset_version=11, operator_export_type=torch.onnx.OperatorExportTypes.ONNX_ATEN_FALLBACK)
# clf
#pred_mask = self.predict_on_batch(batch).cpu()
pred_mask = self.predict_on_batch_onnx(batch).cpu()
# print(pred_mask.sum())
img = hu.f2l(batch['images'])[0]
img += abs(img.min())
img /= img.max()
img = img.repeat(1, 1, 3)
mask_vis = batch["masks"].clone().float()[0][..., None]
mask_vis[mask_vis == 255] = 0
pred_mask_vis = pred_mask.clone().float()[0][..., None]
vmax = 0.1
fig, ax_list = plt.subplots(ncols=3, nrows=1)
ax_list[0].imshow(
img[:, :, 0],
cmap='gray',
# interpolation='sinc', vmin=0, vmax=0.4
)
colors_all = np.array(['black', 'red', 'blue', 'green', 'purple'])
colors = colors_all[np.unique(mask_vis).astype(int)]
vis = label2rgb(mask_vis[:, :, 0].numpy(),
image=img.numpy(),
colors=colors,
bg_label=255,
bg_color=None,
alpha=0.6,
kind='overlay')
vis = mark_boundaries(vis,
mask_vis[:, :, 0].numpy().astype('uint8'),
color=(1, 1, 1))
ax_list[1].imshow(vis, cmap='gray')
colors = colors_all[np.unique(pred_mask_vis).astype(int)]
vis = label2rgb(pred_mask_vis[:, :, 0].numpy(),
image=img.numpy(),
colors=colors,
bg_label=255,
bg_color=None,
alpha=0.6,
kind='overlay')
vis = mark_boundaries(vis,
pred_mask_vis[:, :, 0].numpy().astype('uint8'),
color=(1, 1, 1))
ax_list[2].imshow(vis, cmap='gray')
for i in range(1, self.n_classes):
plt.plot([None], [None], label='group %d' % i, color=colors_all[i])
# ax_list[1].axis('off')
ax_list[0].grid()
ax_list[1].grid()
ax_list[2].grid()
ax_list[0].tick_params(axis='x', labelsize=6)
ax_list[0].tick_params(axis='y', labelsize=6)
ax_list[1].tick_params(axis='x', labelsize=6)
ax_list[1].tick_params(axis='y', labelsize=6)
ax_list[2].tick_params(axis='x', labelsize=6)
ax_list[2].tick_params(axis='y', labelsize=6)
ax_list[0].set_title('Original image', fontsize=8)
ax_list[1].set_title('Ground-truth', fontsize=8)
ax_list[2].set_title('Prediction', fontsize=8)
legend_kwargs = {
"loc": 2,
"bbox_to_anchor": (1.05, 1),
'borderaxespad': 0.,
"ncol": 1
}
ax_list[2].legend(fontsize=6, **legend_kwargs)
plt.savefig(savedir_image.replace('.jpg', '.png'),
bbox_inches='tight',
dpi=300)
plt.close()
# save predictions
if save_preds:
from PIL import Image
pred_dict = {}
pred_numpy = pred_mask.cpu().numpy().squeeze().astype('uint8')
uniques = np.unique(np.array(pred_numpy))
# print(uniques)
meta_dict = batch['meta'][0]
for u in range(self.n_classes):
meta_dict['gt_group%d_n_pixels' % u] = float(
(batch['masks'] == u).float().sum())
meta_dict['pred_group%d_n_pixels' % u] = float(
(pred_mask == u).float().sum())
if u == 0:
continue
pred = Image.fromarray(pred_numpy == u)
pred.save(savedir_image.replace('.jpg', '_group%d.png' % u))
hu.save_json(savedir_image.replace('.jpg', '.json'), meta_dict)
def train_on_batch(self, batch, **extras):
self.train()
images = batch["images"].cuda()
counts = float(batch["counts"][0])
logits = self.model_base(images)
if self.exp_dict['model'].get('loss') == 'lcfcn':
loss = lcfcn.compute_lcfcn_loss(logits, batch["points"].cuda(),
None)
probs = F.softmax(logits, 1)
mask = probs.argmax(
dim=1).cpu().numpy().astype('uint8').squeeze() * 255
# img_mask=hu.save_image('tmp2.png',
# hu.denormalize(images, mode='rgb'), mask=mask, return_image=True)
# hu.save_image('tmp2.png',np.array(img_mask)/255. , radius=3,
# points=batch["points"])
elif self.exp_dict['model'].get('loss') == 'glance':
pred_counts = logits[:, 1].mean()
loss = F.mse_loss(pred_counts.squeeze(), counts.float().squeeze())
elif self.exp_dict['model'].get('loss') == 'att_lcfcn':
probs = logits.sigmoid()
# get points from attention
att_dict = self.att_model.get_attention_dict(
images_original=torch.FloatTensor(
hu.denormalize(batch['images'], mode='rgb')),
counts=batch['counts'][0],
probs=probs.squeeze(),
return_roi=True)
if 1:
blobs = lcfcn.get_blobs(probs.squeeze().detach().cpu().numpy())
org_img = hu.denormalize(images.squeeze(), mode='rgb')
rgb_labels = label2rgb(
blobs,
hu.f2l(org_img),
bg_label=0,
bg_color=None,
)
res1 = mark_boundaries(rgb_labels, blobs)
img_mask = hu.save_image('tmp2.png',
org_img,
return_image=True)
res2 = hu.save_image('tmp.png',
np.array(img_mask) / 255.,
points=att_dict['points'],
radius=1,
return_image=True)
hu.save_image('tmp_blobs.png',
np.hstack([res1, np.array(res2) / 255.]))
loss = lcfcn.compute_loss(
probs=probs,
# batch["points"].cuda(),
points=att_dict['points'].cuda(),
roi_mask=att_dict['roi_mask'])
# loss += .5 * F.cross_entropy(logits,
# torch.from_numpy(1 -
# att_dict['mask_bg']).long().cuda()[None],
# ignore_index=1)
self.opt.zero_grad()
loss.backward()
if self.exp_dict['optimizer'] == 'sps':
self.opt.step(loss=loss)
else:
self.opt.step()
return {"train_loss": float(loss)}
def vis_on_batch(self, batch, savedir_image):
image = batch['images']
index = batch['meta'][0]['index']
gt = np.asarray(batch['masks'], np.float32)
gt /= (gt.max() + 1e-8)
res = self.predict_on_batch(batch)
image = F.interpolate(image,
size=gt.shape[-2:],
mode='bilinear',
align_corners=False)
original = hu.denormalize(image, mode='rgb')[0]
img_res = hu.save_image(savedir_image,
original,
mask=res[0],
return_image=True)
img_gt = hu.save_image(savedir_image,
original,
mask=gt[0],
return_image=True)
img_gt = models.text_on_image('Groundtruth',
np.array(img_gt),
color=(0, 0, 0))
img_res = models.text_on_image('Prediction',
np.array(img_res),
color=(0, 0, 0))
if 'points' in batch:
pts = batch['points'][0].numpy().copy()
pts[pts == 1] = 2
pts[pts == 0] = 1
pts[pts == 255] = 0
img_gt = np.array(
hu.save_image(savedir_image,
img_gt / 255.,
points=pts,
radius=2,
return_image=True))
# score map
if self.heuristic != 'random':
score_map = self.compute_uncertainty(batch['images'],
replicate=True,
scale_factor=1,
method=self.heuristic)
score_map = F.interpolate(score_map[None],
size=gt.shape[-2:],
mode='bilinear',
align_corners=False).squeeze()
h, w = score_map.shape
bbox_yxyx = get_rect_bbox(h, w, n_regions=self.n_regions)
heatmap = hu.f2l(
hi.gray2cmap(
(score_map / score_map.max()).cpu().numpy().squeeze()))
s_list = np.zeros(len(bbox_yxyx))
for i, (y1, x1, y2, x2) in enumerate(bbox_yxyx):
s_list[i] = score_map[y1:y2, x1:x2].mean()
img_bbox = bbox_yxyx_on_image(bbox_yxyx[[s_list.argmax()]],
original)
img_score_map = img_bbox * 0.5 + heatmap * 0.5
img_list = [
np.array(img_gt),
np.array(img_res), (img_score_map * 255).astype('uint8')
]
else:
img_list = [np.array(img_gt), np.array(img_res)]
hu.save_image(savedir_image, np.hstack(img_list))
def save_images(exp_dict):
dataset_name = exp_dict['dataset']['name']
n_classes = exp_dict['dataset']['n_classes']
model = models.get_model(model_dict=exp_dict['model'],
exp_dict=exp_dict,
train_set=None).cuda()
state_dict = hc.load_checkpoint(exp_dict,
savedir_base,
fname='model_best.pth')
model.load_state_dict(state_dict)
model.eval()
np.random.seed(1)
train_set = datasets.get_dataset(dataset_dict={'name': dataset_name},
datadir=None,
split="test",
exp_dict=exp_dict)
n_images = 0
for _ in range(len(train_set)):
i = np.random.choice(len(train_set))
b = train_set[i]
if n_images > 5:
break
if b['masks'].sum() == 0:
print(i)
continue
n_images += 1
batch = ut.collate_fn([b])
image = batch['images']
gt = np.asarray(batch['masks'], np.float32)
gt /= (gt.max() + 1e-8)
image = F.interpolate(image,
size=gt.shape[-2:],
mode='bilinear',
align_corners=False)
img_rgb = hu.f2l(hu.denormalize(image, mode='rgb')[0])
img_rgb = (np.array(img_rgb) * 255.).astype('uint8')
# save rgb
fname_rgb = '.tmp/covid_qualitative/%s/%s/%d_rgb.png' % (exp_group,
'gt', i)
hu.save_image(fname_rgb, img_rgb)
# save pts
fname_pts = '.tmp/covid_qualitative/%s/%s/%d_pts.png' % (exp_group,
'gt', i)
img_gt = np.array(hu.save_image('', img_rgb, return_image=True))
if 'points' in batch:
pts = batch['points'][0].numpy()
pts[pts == 1] = 2
pts[pts == 0] = 1
pts[pts == 255] = 0
img_gt = np.array(
hu.save_image('',
img_gt / 255.,
points=pts,
radius=2,
return_image=True))
hu.save_image(fname_pts, img_gt)
# save mask
fname_mask = '.tmp/covid_qualitative/%s/%s/%d_mask.png' % (exp_group,
'gt', i)
img_mask = np.array(
hu.save_image('', img_rgb, mask=gt[0], return_image=True))
hu.save_image(fname_mask, img_mask)
# pred
fname_pred = '.tmp/covid_qualitative/%s/%s/%d_%s.png' % (
exp_group, 'preds', i, exp_dict['model']['loss'])
res = model.predict_on_batch(batch)
img_res = hu.save_image('', img_rgb, mask=res[0], return_image=True)
hu.save_image(fname_pred, np.array(img_res))
