diff --git a/src/test/resources/target_code/CNNSupervisedTrainer_Alexnet.py b/src/test/resources/target_code/CNNSupervisedTrainer_Alexnet.py index 8a9aeb954f5bbd06a0a44322c71d3cb132daa643..a51a11faea5eed6dd91c43269648f90eaa6280f6 100644 --- a/src/test/resources/target_code/CNNSupervisedTrainer_Alexnet.py +++ b/src/test/resources/target_code/CNNSupervisedTrainer_Alexnet.py @@ -115,7 +115,8 @@ class BLEU(mx.metric.EvalMetric): i *= 2 match_counts = 1 / i - precisions[n] = match_counts / counts + if (match_counts / counts) > 0: + precisions[n] = match_counts / counts bleu = self._get_brevity_penalty() * math.exp(sum(map(math.log, precisions)) / self.N) @@ -320,7 +321,7 @@ class CNNSupervisedTrainer_Alexnet: train_test_iter.reset() metric = mx.metric.create(eval_metric, **eval_metric_params) for batch_i, batch in enumerate(train_test_iter): - if True: + if True: labels = [batch.label[i].as_in_context(mx_context) for i in range(1)] data_ = batch.data[0].as_in_context(mx_context) @@ -354,7 +355,7 @@ class CNNSupervisedTrainer_Alexnet: attention_resized = np.resize(attention.asnumpy(), (8, 8)) ax = fig.add_subplot(max_length//3, max_length//4, l+1) ax.set_title(dict[int(labels[l+1][0].asscalar())]) - img = ax.imshow(train_images[0+test_batch_size*(batch_i)]) + img = ax.imshow(train_images[0+test_batch_size*(batch_i)].transpose(1,2,0)) ax.imshow(attention_resized, cmap='gray', alpha=0.6, extent=img.get_extent()) @@ -378,7 +379,7 @@ class CNNSupervisedTrainer_Alexnet: test_iter.reset() metric = mx.metric.create(eval_metric, **eval_metric_params) for batch_i, batch in enumerate(test_iter): - if True: + if True: labels = [batch.label[i].as_in_context(mx_context) for i in range(1)] data_ = batch.data[0].as_in_context(mx_context) @@ -406,7 +407,7 @@ class CNNSupervisedTrainer_Alexnet: attention_resized = np.resize(attention.asnumpy(), (8, 8)) ax = fig.add_subplot(max_length//3, max_length//4, l+1) ax.set_title(dict[int(mx.nd.slice_axis(mx.nd.argmax(outputs[l+1], axis=1), axis=0, begin=0, end=1).asscalar())]) - img = ax.imshow(test_images[0+test_batch_size*(batch_i)]) + img = ax.imshow(test_images[0+test_batch_size*(batch_i)].transpose(1,2,0)) ax.imshow(attention_resized, cmap='gray', alpha=0.6, extent=img.get_extent()) diff --git a/src/test/resources/target_code/CNNSupervisedTrainer_CifarClassifierNetwork.py b/src/test/resources/target_code/CNNSupervisedTrainer_CifarClassifierNetwork.py index 549e2cb7b743dca3f52531c15a78f9014abb203c..391b5f7860798ad8661ffff401941e6f12b43e16 100644 --- a/src/test/resources/target_code/CNNSupervisedTrainer_CifarClassifierNetwork.py +++ b/src/test/resources/target_code/CNNSupervisedTrainer_CifarClassifierNetwork.py @@ -115,7 +115,8 @@ class BLEU(mx.metric.EvalMetric): i *= 2 match_counts = 1 / i - precisions[n] = match_counts / counts + if (match_counts / counts) > 0: + precisions[n] = match_counts / counts bleu = self._get_brevity_penalty() * math.exp(sum(map(math.log, precisions)) / self.N) @@ -320,7 +321,7 @@ class CNNSupervisedTrainer_CifarClassifierNetwork: train_test_iter.reset() metric = mx.metric.create(eval_metric, **eval_metric_params) for batch_i, batch in enumerate(train_test_iter): - if True: + if True: labels = [batch.label[i].as_in_context(mx_context) for i in range(1)] data_ = batch.data[0].as_in_context(mx_context) @@ -354,7 +355,7 @@ class CNNSupervisedTrainer_CifarClassifierNetwork: attention_resized = np.resize(attention.asnumpy(), (8, 8)) ax = fig.add_subplot(max_length//3, max_length//4, l+1) ax.set_title(dict[int(labels[l+1][0].asscalar())]) - img = ax.imshow(train_images[0+test_batch_size*(batch_i)]) + img = ax.imshow(train_images[0+test_batch_size*(batch_i)].transpose(1,2,0)) ax.imshow(attention_resized, cmap='gray', alpha=0.6, extent=img.get_extent()) @@ -378,7 +379,7 @@ class CNNSupervisedTrainer_CifarClassifierNetwork: test_iter.reset() metric = mx.metric.create(eval_metric, **eval_metric_params) for batch_i, batch in enumerate(test_iter): - if True: + if True: labels = [batch.label[i].as_in_context(mx_context) for i in range(1)] data_ = batch.data[0].as_in_context(mx_context) @@ -406,7 +407,7 @@ class CNNSupervisedTrainer_CifarClassifierNetwork: attention_resized = np.resize(attention.asnumpy(), (8, 8)) ax = fig.add_subplot(max_length//3, max_length//4, l+1) ax.set_title(dict[int(mx.nd.slice_axis(mx.nd.argmax(outputs[l+1], axis=1), axis=0, begin=0, end=1).asscalar())]) - img = ax.imshow(test_images[0+test_batch_size*(batch_i)]) + img = ax.imshow(test_images[0+test_batch_size*(batch_i)].transpose(1,2,0)) ax.imshow(attention_resized, cmap='gray', alpha=0.6, extent=img.get_extent()) diff --git a/src/test/resources/target_code/CNNSupervisedTrainer_VGG16.py b/src/test/resources/target_code/CNNSupervisedTrainer_VGG16.py index a1e7970cac976bf6a5c2c742a82f7354d1534cca..bcffe55929dbe34e5052177dfc9538db841b0e48 100644 --- a/src/test/resources/target_code/CNNSupervisedTrainer_VGG16.py +++ b/src/test/resources/target_code/CNNSupervisedTrainer_VGG16.py @@ -115,7 +115,8 @@ class BLEU(mx.metric.EvalMetric): i *= 2 match_counts = 1 / i - precisions[n] = match_counts / counts + if (match_counts / counts) > 0: + precisions[n] = match_counts / counts bleu = self._get_brevity_penalty() * math.exp(sum(map(math.log, precisions)) / self.N) @@ -320,7 +321,7 @@ class CNNSupervisedTrainer_VGG16: train_test_iter.reset() metric = mx.metric.create(eval_metric, **eval_metric_params) for batch_i, batch in enumerate(train_test_iter): - if True: + if True: labels = [batch.label[i].as_in_context(mx_context) for i in range(1)] data_ = batch.data[0].as_in_context(mx_context) @@ -354,7 +355,7 @@ class CNNSupervisedTrainer_VGG16: attention_resized = np.resize(attention.asnumpy(), (8, 8)) ax = fig.add_subplot(max_length//3, max_length//4, l+1) ax.set_title(dict[int(labels[l+1][0].asscalar())]) - img = ax.imshow(train_images[0+test_batch_size*(batch_i)]) + img = ax.imshow(train_images[0+test_batch_size*(batch_i)].transpose(1,2,0)) ax.imshow(attention_resized, cmap='gray', alpha=0.6, extent=img.get_extent()) @@ -378,7 +379,7 @@ class CNNSupervisedTrainer_VGG16: test_iter.reset() metric = mx.metric.create(eval_metric, **eval_metric_params) for batch_i, batch in enumerate(test_iter): - if True: + if True: labels = [batch.label[i].as_in_context(mx_context) for i in range(1)] data_ = batch.data[0].as_in_context(mx_context) @@ -406,7 +407,7 @@ class CNNSupervisedTrainer_VGG16: attention_resized = np.resize(attention.asnumpy(), (8, 8)) ax = fig.add_subplot(max_length//3, max_length//4, l+1) ax.set_title(dict[int(mx.nd.slice_axis(mx.nd.argmax(outputs[l+1], axis=1), axis=0, begin=0, end=1).asscalar())]) - img = ax.imshow(test_images[0+test_batch_size*(batch_i)]) + img = ax.imshow(test_images[0+test_batch_size*(batch_i)].transpose(1,2,0)) ax.imshow(attention_resized, cmap='gray', alpha=0.6, extent=img.get_extent())